[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6JTG7S72GD095EAN18MNYB7":3,"skill-same:01M6JTG7S72GD095EAN18MNYB7":69},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":40,"linkOnly":41,"markdownContent":42,"markdownBody":43,"frontMatter":44,"refName":45,"commitSha":46,"skillDirectory":47,"forksCount":48,"repositoryHtmlUrl":49,"repositoryHomepageUrl":50,"ownerHtmlUrl":51,"ownerBlogUrl":52,"ownerDescription":53,"updatedAt":54,"install":55,"resources":68},"01M6JTG7S72GD095EAN18MNYB7","using-bgs-modding-superpowers",null,"Use when starting ANY conversation involving Bethesda Game Studio modding, MO2, xEdit, or modpack curation. Bootstrap that loads the toolkit overview, lists available task skills, and enforces the hard rules of this plugin. Auto-injected by the OpenCode plugin's chat.messages.transform hook and by the hooks\u002F session-start chain in Claude Code and Codex.","hashgraph-online\u002Fawesome-codex-plugins","hashgraph-online","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F160371962?v=4","01M6CNB6NRJVNNGN14TR01Q6D3","HOL (Hashgraph Online)","01M6JT1HSKKG9V68KQAQGBA7XP",1575,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FBB-84C\u002Fbgs-modding-superpowers\u002Fskills\u002Fusing-bgs-modding-superpowers\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39],"using bgs modding superpowers","superpowers","when","code","studio","curation","hook","loads","transform","chain","conversation","opencode","hooks","auto","use","overview","session","game","start","messages","game studio","2026-11-10 10:12:30",false,"---\nname: using-bgs-modding-superpowers\ndescription: \"Use when starting ANY conversation involving Bethesda Game Studio modding, MO2, xEdit, or modpack curation. Bootstrap that loads the toolkit overview, lists available task skills, and enforces the hard rules of this plugin. Auto-injected by the OpenCode plugin's chat.messages.transform hook and by the hooks\u002F session-start chain in Claude Code and Codex.\"\n---\n\n\u003CEXTREMELY_IMPORTANT_BGS_MODDING_SUPERPOWERS>\nThis is the bgs-modding-superpowers per-session bootstrap. If you are reading this,\nthe plugin injected it into the first user message of this session. Do NOT discard\nit. Do NOT respond to the user yet without first checking whether one of the task\nskills below applies.\n\u003C\u002FEXTREMELY_IMPORTANT_BGS_MODDING_SUPERPOWERS>\n\n# Using BGS Modding Superpowers\n\nYou are operating with the `bgs-modding-superpowers` plugin loaded. This plugin\ngives you an agent-driven toolkit for Bethesda Game Studio modpack curation:\nMO2 control plane, xEdit MCP, conflict-audit workflow, and runtime asset skills\nfor dev-log and release-changelog maintenance.\n\n## Available skills (auto-trigger on these intents)\n\n| Skill | Auto-triggers when |\n|---|---|\n| `setting-up-bgs-modding-environment` | First conversation in a project; MO2 or xEdit not yet detected; user says \"set up\", \"install\", \"bootstrap\", \"configure\" |\n| `maintaining-modding-environments` | After first-run: \"ongoing\", \"maintain\", \"register custom pack\", \"prune cache\", \"update knowledge base\", \"modding environment health check\" |\n| `evaluating-bgs-mods` | Deciding whether a mod belongs in the pack; \"should I add this mod\", \"is this mod good\", \"评估这个mod\", \"这个mod值得装吗\", \"this mod looks too good to be true\" |\n| `interpreting-mod-author-instructions` | After INCLUDE verdict, before download\u002Finstall; \"how do I install\", \"FOMOD choices\", \"which file to download\", \"author说明\", \"which variant\", \"按作者说明安装\" |\n| `curating-bgs-modpack` | Whole-pack incremental build strategy; \"plan the pack\", \"batch strategy\", \"rollback point\", \"naming convention\", \"declare 风格\", \"策展整合包\", \"整合包规划\" |\n| `diagnosing-bgs-problems` | It broke — symptom-first triage; \"CTD\", \"crash log\", \"FPS drop\", \"stuttering\", \"Buffout\", \"freeze\", \"won't start\", \"崩溃\", \"掉帧\", \"卡顿\" |\n| `testing-bgs-modpack` | Proactive post-install verification of a batch; \"test the pack\", \"verification\", \"post-install check\", \"is it stable\", \"what should I test\", \"测试整合包\", \"验证安装\" |\n| `xedit-automation` | Any task involving `.esp\u002F.esm\u002F.esl` plugin files, FormIDs, masters, conflicts, ESL flagging, ITM\u002FUDR cleaning, Pascal scripts |\n| `xedit-conflict-audit` | \"Why is this override not winning?\", \"Which plugins overlap on this record?\", \"Is this load order safe?\" |\n| `writing-bgs-load-order` | Reading\u002Fediting\u002Fgenerating `plugins.txt` or `loadorder.txt`; enabling\u002Fdisabling\u002Freordering\u002Fadding\u002Fremoving plugins; launching xEdit with a custom plugins file; \"load order\", \"enable this plugin\", \"disable that plugin\", \"what does the asterisk mean\" |\n| `using-bgs-translator` | Translate a Bethesda plugin's text to another language; \"translate this mod\", \"汉化这个 mod\", \"localize mod to chinese\", \"build SST for\", \"use my LLM to translate plugins\" |\n| `using-bgs-archive` | unpack\u002Fpack BA2\u002FBSA archives; inspect archive format\u002Fcontents; extract assets |\n| `using-bgs-papyrus` | compile\u002Fdecompile Papyrus PSC\u003C->PEX for Skyrim\u002FFO4\u002FStarfield |\n| `writing-modpack-devlog` | \"Log this\", \"record what I did\", \"note this change\", \"add to dev-log\", \"track this decision\" |\n| `writing-modpack-changelog` | \"Cut a release\", \"release notes\", \"what changed since v1.2\", \"prepare release for Nexus\" |\n\nWhen the user's intent matches one of these, invoke the corresponding skill\nthrough your skill tool BEFORE replying. Do not paraphrase the skill from memory;\nlet the skill load.\n\n## Available MCP tools\n\nThe bundled `xedit` MCP server (declared in `.mcp.json` for Claude Code \u002F Codex,\ndeclared via the OpenCode plugin's `config.mcp.xedit` hook) is fully\n**non-blocking**: every tool returns immediately. The xEdit daemon's lifecycle\nis tracked in the server's in-memory state machine, and domain tools fast-fail\nwith `code: \"not_ready\"` if you call them before the daemon is ready.\n\n### Lifecycle \u002F health tools\n\n| Tool | Use |\n|---|---|\n| `xedit_status` | Pure read. Returns `{ status: \"not_started\" \\| \"starting\" \\| \"ready\" \\| \"failed\", ... }`. Never modifies state. Use this to POLL while waiting for a launch. |\n| `xedit_start` | Kicks off an asynchronous daemon launch if not already starting\u002Fready. Returns immediately. Accepts optional overrides: `{ launcherPath?, gameMode?, dataPath?, pluginsFile?, moProfile? }`. Use `dataPath` (MO2 `gamePath + \"\\\\Data\"`) to override xEdit's registry-discovered platform path; use `pluginsFile` to point at a custom load order (see `writing-bgs-load-order`). The launch itself takes 60-240s; that work happens in the background. |\n| `xedit_health` | When ready: sends `system.ping` through the named pipe to catch zombies. After a flush exit timeout, rechecks the retained managed PID so a delayed normal exit can clear lifecycle state without force. |\n| `xedit_dirty` | Returns xEdit dirty state plus authoritative contract-0.23 pending-rename readback when available, with a local fail-closed fallback for older daemons. Pending saves remain visible even when daemon dirty state is false. |\n| `xedit_flush` | Contract-0.23 durability boundary. Requires consent, drains pending renames, validates the response, waits for the managed daemon's promised self-exit, and reports complete, partial, or unknown outcome. Failed in-band renames get one final exit-time retry; fresh-daemon readback decides durability. |\n| `xedit_stop` | Stops the daemon and clears MCP runtime state. It refuses unsaved edits or pending-shutdown saves unless `force: true` is explicitly chosen; forced abandonment is reported and audited. |\n| `xedit_restart` | Stops the daemon with the same dirty\u002Fpending-save safety, then kicks off a fresh async launch. Use only when no pending save is tracked; `force: true` is explicit abandonment, not a flush. |\n\n### Domain tools (6) — require ready, fast-fail otherwise\n\n| Tool | Use |\n|---|---|\n| `xedit_session` | If ready: returns the full session envelope (gameMode, loadOrderSize, daemonPid). If not_started: auto-initiates the launch. Otherwise: returns the current status. Always non-blocking. |\n| `xedit_list_capabilities` | Curated 50-command contract-0.23 digest + live drift report. |\n| `xedit_find_record` | Locate by `{file, formId}` or `{editorId}`. |\n| `xedit_read_record` | Fields + base record + winning override. |\n| `xedit_inspect_conflicts` | W2 verdict tool: `no_conflict \u002F itpo \u002F itm \u002F minor \u002F breaking`. |\n| `xedit_call(command, args)` | Atomic passthrough for native daemon commands; in-harness. Lifecycle-owned `session.flush` is refused here and must use `xedit_flush`. |\n\n### Canonical lifecycle pattern (do this every session that touches xEdit)\n\n```\n1. xedit_start({})                  -> { status: \"starting\" }      (or \"ready\")\n2. xedit_status({})                 -> poll until status=\"ready\"   (sleep 5-15s between calls)\n3. xedit_health({})                 -> confirm responsive=true\n4. xedit_session({}) \u002F xedit_*      -> normal domain work\n5. xedit_dirty({})                  -> check dirty state and pendingShutdownSave\n6. xedit_flush({})                  -> when pending > 0, drain + confirm daemon self-exit\n7. xedit_start({ ... })             -> fresh daemon for persistence readback after flush\n8. xedit_stop({}) \u002F restart({ ... }) -> only when no dirty or pending state exists\n```\n\nNEVER call a domain tool in a tight loop expecting it to \"wait.\" If\n`xedit_status` reports `status: \"failed\"`, surface `data.error` to the user and\nstop — common causes are MO2 not running visibly, the Python plugin not loaded,\nthe xEdit binary missing, or xEdit's automation-serve tripping on the active\nload order.\n\nThe structured daemon-command and workflow reference now lives in KB records.\nUse `bgs_kb_query` \u002F `bgs_kb_get` for deep reference retrieval; the old\n`skills\u002Fxedit-automation\u002Fxedit-knowledgebase.md` path is a redirect only.\n\n### BGS knowledge-base tools (3) — curated knowledge, no xEdit daemon\n\nThe sibling BGS knowledge-base MCP is for curated modding knowledge, not live\nruntime state. It works before MO2 \u002F xEdit are configured; use xEdit MCP for\nactual plugin, load-order, and record readback.\n\n| Tool | Use |\n|---|---|\n| `bgs_kb_status` | Reports loaded KB packs, versions, games, domains, cache root, and user pack roots. |\n| `bgs_kb_query` | Searches loaded packs for ranked knowledge snippets with game\u002Fdomain filters and sources. |\n| `bgs_kb_get` | Fetches a full record by id, merging game-specific variants when `game` is provided. |\n\n## Hard rules (non-negotiable)\n\n1. **The user's `\u003CMO2_Root>` and any `\u003CMO2_Root>\u002F\u003Cgame>\u002FData\u002F` (or equivalent\n   \"Stock Game\" tree) is real game state.** Never write into it directly. Any\n   game-local change is expressed as an MO2 mod overlay under\n   `\u003CMO2_Root>\u002Fmods\u002F\u003Cmod-name>\u002F`. The MO2 VFS projects it at runtime.\n2. **All xEdit work goes through the bundled `xedit` MCP.** Never spawn\n   `xEdit.exe` directly from the shell, never parse `.esp\u002F.esm\u002F.esl` files with\n   your own Python\u002FJS, never invoke `xedit-client.ps1` from raw shell. The MCP\n   exists so the harness can enforce validation, state, rules, and audit on\n   every call. Atomic passthrough (`xedit_call`) is the documented escape hatch\n   when an intent tool does not fit — it is still in-harness.\n3. **Mutating operations require explicit user consent and a daemon launched\n   with `-IKnowWhatImDoing`.** Read the `xedit-automation` skill BEFORE any\n   destructive work. The anti-pattern list there is binding.\n4. **A `session.save` response is not durability.** A nonzero\n   `savedFilesPendingShutdown` \u002F `savePendingShutdownCount` is deferred. On\n   contract 0.23, `xedit_dirty` reconciles that fallback with the daemon's\n   authoritative pending queue and `xedit_flush` is the only supported in-band\n   drain. It validates the response and confirms daemon self-exit before clearing\n   the blocking guard. A partial or unknown outcome remains visible as\n   `lastFlush`; after relaunch it is labelled `previousSessionFlush` with the old\n   PID and timestamp. Failed in-band renames receive one normal exit-time retry,\n   so fresh-daemon readback, not the partial envelope alone, decides durability.\n   `force:true` on stop\u002Frestart is still explicit abandonment, never durability proof.\n5. **Large scope (many records, broad conflict survey) → delegate to a\n   read-only investigator subagent FIRST.** The subagent burns its own context\n   and returns a distilled summary. Do not loop hundreds of records through\n   your own context.\n6. **BGS domain knowledge routes through the KB first.** For questions about\n   how BGS modding works — Papyrus semantics, plugin-format gotchas, archive\n   precedence, load-order conventions, common engine quirks, or game-specific\n   toolchain gotchas — call `bgs_kb_status` \u002F `bgs_kb_query` before\n   improvising or reaching for web search. If the question is about what the\n   current local load order, plugin, or record actually is, use `xedit_*` or the\n   relevant file\u002FCLI surface instead. The KB is advisory; xEdit readback remains\n   authoritative for actual state. If `bgs_kb_status` reports no packs or the\n   needed game pack is missing, fall back to web research using the roadmap\n   Appendix source list or route setup\u002Fmaintenance work to install the pack.\n7. **First-run state**: if MO2 \u002F xEdit \u002F the control-plane Python plugin are\n   not yet set up on this machine, invoke `setting-up-bgs-modding-environment`\n   BEFORE any modpack work. That skill orchestrates detection and install.\n8. **Nexus credentials and Premium download paths**: MO2 stores the user's\n   Nexus API key globally in Windows Credential Manager under target\n   `ModOrganizer2_APIKEY` (legacy) \u002F `ModOrganizer2_NEXUS_OAUTH_TOKENS`\n   (modern OAuth). Reading the key requires explicit per-session user consent\n   and the key must be masked in any visible output. The agent-friendly\n   refresh path for Nexus update state is \"Option B\" — direct API call to\n   `\u002Fv1\u002Fgames\u002F{game}\u002Fmods\u002F{id}.json` + write back to `meta.ini` via\n   `mo2_edit_meta`, no MO2 GUI launch needed. Both workflows are documented in\n   the `maintaining-modding-environments` skill and in KB records\n   `install-planning.mo2-windows-credential-mining.v1` +\n   `install-planning.nexus-direct-api-update-check.v1`. For Premium-account\n   direct downloads, use `POST \u002Fv1\u002Fgames\u002F{game}\u002Fmods\u002F{id}\u002Ffiles\u002F{file_id}\u002Fdownload_link.json`\n   (returns 7 CDN mirrors) — Premium-only; free accounts must use the Nexus\n   browser flow.\n\n## How to use this bootstrap\n\n- This skill loads automatically on every new session. You do not need to\n  re-invoke it.\n- When a user intent matches a task skill in the table above, invoke that skill\n  via your skill tool. Do not paraphrase.\n- When the user asks about \"what can you do\", reference the skills inventory\n  here; do not invent capabilities the plugin does not have.\n- When answering BGS modding-domain questions, prefer local KB retrieval before\n  web search. The bundled core pack ships inline; per-game packs may be\n  installed later via setup \u002F maintenance skills; end-user packs may be\n  registered via `$BGS_KB_USER_PACKS` through `maintaining-modding-environments`.\n- When you would normally write code that touches BGS plugin files (`.esp\u002F.esm\u002F\n  .esl`), STOP and route through `xedit-automation` instead.\n- When the user is deciding whether to add or keep a mod (\"should I install X\",\n  \"is this good\", \"评估\"), route to `evaluating-bgs-mods` BEFORE any\n  install\u002Fdownload action.\n- When an INCLUDE verdict is in and the user needs to read author instructions \u002F\n  pick FOMOD options \u002F choose a file or variant, route to\n  `interpreting-mod-author-instructions`.\n- When the user is planning the whole pack, sizing batches, deciding rollback\n  boundaries, or declaring 风格, route to `curating-bgs-modpack`.\n- When the user reports a crash, CTD, FPS drop, freeze, or stutter (\"崩溃\",\n  \"掉帧\", \"卡顿\"), route to `diagnosing-bgs-problems` for symptom-first triage\n  BEFORE any blame attribution.\n- When the user wants to verify a freshly installed batch (\"test the pack\",\n  \"is it stable\", \"验证安装\"), route to `testing-bgs-modpack`.\n- When the user wants to translate plugin text or emit SST dictionaries for a\n  mod, route to `using-bgs-translator` instead of xEdit; translator reads plugin\n  text and emits dictionaries, it does not modify plugin binaries.\n- When the user wants to inspect, unpack, extract, or pack BA2\u002FBSA archives,\n  route to `using-bgs-archive`; archive packing must write to MO2 overlays, not\n  game `Data` or Stock-Game trees.\n- When the user wants to compile or decompile Papyrus scripts (`.psc` \u002F `.pex`),\n  route to `using-bgs-papyrus`; compiled `.pex` output must go to MO2 overlays,\n  not game `Data` or Stock-Game trees.\n- When the user asks to \"log\", \"record\", \"track\", or \"note\" modpack work,\n  route to `writing-modpack-devlog`. When the user asks to \"cut a release\" or\n  prepare release notes, route to `writing-modpack-changelog`.\n\n## See also\n\n- `setting-up-bgs-modding-environment` — first-run setup orchestrator.\n- `maintaining-modding-environments` — ongoing environment care, KB updates,\n  custom-pack registration, cache pruning, and health checks after first-run.\n- `evaluating-bgs-mods` — judgment skill: should this mod go in the pack (BGS\n  systemic-design fit, quality\u002Frisk\u002Fpack-value); hands off to\n  `interpreting-mod-author-instructions` on INCLUDE.\n- `interpreting-mod-author-instructions` — judgment skill: how to correctly\n  download\u002Finstall per author说明 (FOMOD reasoning, file\u002Fvariant selection,\n  prerequisites). Downstream from `evaluating-bgs-mods` INCLUDE verdict.\n- `curating-bgs-modpack` — judgment skill: whole-pack incremental strategy\n  (batch sizing, rollback boundaries, attribution\u002Fnaming, declaring 风格);\n  cross-stage skill that the per-mod skills feed.\n- `diagnosing-bgs-problems` — judgment skill: symptom-first triage for CTD \u002F\n  FPS \u002F freeze \u002F stutter; escalates to `xedit-conflict-audit` or\n  `using-bgs-archive` once root-cause class is identified.\n- `testing-bgs-modpack` — judgment skill: proactive post-install verification\n  of an install batch; escalates to `diagnosing-bgs-problems` on failure.\n- `xedit-automation` — hub skill for all xEdit work; routing doctrine,\n  anti-patterns, sub-agent recipes.\n- BGS KB records under `knowledge\u002Fbgs-kb\u002Fpacks\u002Fcore\u002Frecords\u002F` — deep reference\n  for daemon commands, error codes, save semantics, glossary, and durable gotchas.\n- `xedit-conflict-audit` — the W2 conflict-audit workflow.\n- `using-bgs-translator` — CLI + Tk workflow for LLM-assisted plugin text\n  translation and SST dictionary export.\n- `using-bgs-archive` — BA2\u002FBSA archive inspection, extraction, and safe\n  overlay-only packing.\n- `using-bgs-papyrus` — Papyrus PSC\u002FPEX compile\u002Fdecompile workflows for Skyrim,\n  Fallout 4, and Starfield.\n- `writing-modpack-devlog`, `writing-modpack-changelog` — runtime asset\n  skills for project documentation.\n\n---\n\n> Plugin: `bgs-modding-superpowers`. Repo: https:\u002F\u002Fgithub.com\u002FBB-84C\u002Fbgs-modding-superpowers.\n> If any environmental component (MO2, xEdit, control-plane Python plugin) is missing,\n> route through `setting-up-bgs-modding-environment` before continuing.\n","\u003CEXTREMELY_IMPORTANT_BGS_MODDING_SUPERPOWERS>\nThis is the bgs-modding-superpowers per-session bootstrap. If you are reading this,\nthe plugin injected it into the first user message of this session. Do NOT discard\nit. Do NOT respond to the user yet without first checking whether one of the task\nskills below applies.\n\u003C\u002FEXTREMELY_IMPORTANT_BGS_MODDING_SUPERPOWERS>\n\n# Using BGS Modding Superpowers\n\nYou are operating with the `bgs-modding-superpowers` plugin loaded. This plugin\ngives you an agent-driven toolkit for Bethesda Game Studio modpack curation:\nMO2 control plane, xEdit MCP, conflict-audit workflow, and runtime asset skills\nfor dev-log and release-changelog maintenance.\n\n## Available skills (auto-trigger on these intents)\n\n| Skill | Auto-triggers when |\n|---|---|\n| `setting-up-bgs-modding-environment` | First conversation in a project; MO2 or xEdit not yet detected; user says \"set up\", \"install\", \"bootstrap\", \"configure\" |\n| `maintaining-modding-environments` | After first-run: \"ongoing\", \"maintain\", \"register custom pack\", \"prune cache\", \"update knowledge base\", \"modding environment health check\" |\n| `evaluating-bgs-mods` | Deciding whether a mod belongs in the pack; \"should I add this mod\", \"is this mod good\", \"评估这个mod\", \"这个mod值得装吗\", \"this mod looks too good to be true\" |\n| `interpreting-mod-author-instructions` | After INCLUDE verdict, before download\u002Finstall; \"how do I install\", \"FOMOD choices\", \"which file to download\", \"author说明\", \"which variant\", \"按作者说明安装\" |\n| `curating-bgs-modpack` | Whole-pack incremental build strategy; \"plan the pack\", \"batch strategy\", \"rollback point\", \"naming convention\", \"declare 风格\", \"策展整合包\", \"整合包规划\" |\n| `diagnosing-bgs-problems` | It broke — symptom-first triage; \"CTD\", \"crash log\", \"FPS drop\", \"stuttering\", \"Buffout\", \"freeze\", \"won't start\", \"崩溃\", \"掉帧\", \"卡顿\" |\n| `testing-bgs-modpack` | Proactive post-install verification of a batch; \"test the pack\", \"verification\", \"post-install check\", \"is it stable\", \"what should I test\", \"测试整合包\", \"验证安装\" |\n| `xedit-automation` | Any task involving `.esp\u002F.esm\u002F.esl` plugin files, FormIDs, masters, conflicts, ESL flagging, ITM\u002FUDR cleaning, Pascal scripts |\n| `xedit-conflict-audit` | \"Why is this override not winning?\", \"Which plugins overlap on this record?\", \"Is this load order safe?\" |\n| `writing-bgs-load-order` | Reading\u002Fediting\u002Fgenerating `plugins.txt` or `loadorder.txt`; enabling\u002Fdisabling\u002Freordering\u002Fadding\u002Fremoving plugins; launching xEdit with a custom plugins file; \"load order\", \"enable this plugin\", \"disable that plugin\", \"what does the asterisk mean\" |\n| `using-bgs-translator` | Translate a Bethesda plugin's text to another language; \"translate this mod\", \"汉化这个 mod\", \"localize mod to chinese\", \"build SST for\", \"use my LLM to translate plugins\" |\n| `using-bgs-archive` | unpack\u002Fpack BA2\u002FBSA archives; inspect archive format\u002Fcontents; extract assets |\n| `using-bgs-papyrus` | compile\u002Fdecompile Papyrus PSC\u003C->PEX for Skyrim\u002FFO4\u002FStarfield |\n| `writing-modpack-devlog` | \"Log this\", \"record what I did\", \"note this change\", \"add to dev-log\", \"track this decision\" |\n| `writing-modpack-changelog` | \"Cut a release\", \"release notes\", \"what changed since v1.2\", \"prepare release for Nexus\" |\n\nWhen the user's intent matches one of these, invoke the corresponding skill\nthrough your skill tool BEFORE replying. Do not paraphrase the skill from memory;\nlet the skill load.\n\n## Available MCP tools\n\nThe bundled `xedit` MCP server (declared in `.mcp.json` for Claude Code \u002F Codex,\ndeclared via the OpenCode plugin's `config.mcp.xedit` hook) is fully\n**non-blocking**: every tool returns immediately. The xEdit daemon's lifecycle\nis tracked in the server's in-memory state machine, and domain tools fast-fail\nwith `code: \"not_ready\"` if you call them before the daemon is ready.\n\n### Lifecycle \u002F health tools\n\n| Tool | Use |\n|---|---|\n| `xedit_status` | Pure read. Returns `{ status: \"not_started\" \\| \"starting\" \\| \"ready\" \\| \"failed\", ... }`. Never modifies state. Use this to POLL while waiting for a launch. |\n| `xedit_start` | Kicks off an asynchronous daemon launch if not already starting\u002Fready. Returns immediately. Accepts optional overrides: `{ launcherPath?, gameMode?, dataPath?, pluginsFile?, moProfile? }`. Use `dataPath` (MO2 `gamePath + \"\\\\Data\"`) to override xEdit's registry-discovered platform path; use `pluginsFile` to point at a custom load order (see `writing-bgs-load-order`). The launch itself takes 60-240s; that work happens in the background. |\n| `xedit_health` | When ready: sends `system.ping` through the named pipe to catch zombies. After a flush exit timeout, rechecks the retained managed PID so a delayed normal exit can clear lifecycle state without force. |\n| `xedit_dirty` | Returns xEdit dirty state plus authoritative contract-0.23 pending-rename readback when available, with a local fail-closed fallback for older daemons. Pending saves remain visible even when daemon dirty state is false. |\n| `xedit_flush` | Contract-0.23 durability boundary. Requires consent, drains pending renames, validates the response, waits for the managed daemon's promised self-exit, and reports complete, partial, or unknown outcome. Failed in-band renames get one final exit-time retry; fresh-daemon readback decides durability. |\n| `xedit_stop` | Stops the daemon and clears MCP runtime state. It refuses unsaved edits or pending-shutdown saves unless `force: true` is explicitly chosen; forced abandonment is reported and audited. |\n| `xedit_restart` | Stops the daemon with the same dirty\u002Fpending-save safety, then kicks off a fresh async launch. Use only when no pending save is tracked; `force: true` is explicit abandonment, not a flush. |\n\n### Domain tools (6) — require ready, fast-fail otherwise\n\n| Tool | Use |\n|---|---|\n| `xedit_session` | If ready: returns the full session envelope (gameMode, loadOrderSize, daemonPid). If not_started: auto-initiates the launch. Otherwise: returns the current status. Always non-blocking. |\n| `xedit_list_capabilities` | Curated 50-command contract-0.23 digest + live drift report. |\n| `xedit_find_record` | Locate by `{file, formId}` or `{editorId}`. |\n| `xedit_read_record` | Fields + base record + winning override. |\n| `xedit_inspect_conflicts` | W2 verdict tool: `no_conflict \u002F itpo \u002F itm \u002F minor \u002F breaking`. |\n| `xedit_call(command, args)` | Atomic passthrough for native daemon commands; in-harness. Lifecycle-owned `session.flush` is refused here and must use `xedit_flush`. |\n\n### Canonical lifecycle pattern (do this every session that touches xEdit)\n\n```\n1. xedit_start({})                  -> { status: \"starting\" }      (or \"ready\")\n2. xedit_status({})                 -> poll until status=\"ready\"   (sleep 5-15s between calls)\n3. xedit_health({})                 -> confirm responsive=true\n4. xedit_session({}) \u002F xedit_*      -> normal domain work\n5. xedit_dirty({})                  -> check dirty state and pendingShutdownSave\n6. xedit_flush({})                  -> when pending > 0, drain + confirm daemon self-exit\n7. xedit_start({ ... })             -> fresh daemon for persistence readback after flush\n8. xedit_stop({}) \u002F restart({ ... }) -> only when no dirty or pending state exists\n```\n\nNEVER call a domain tool in a tight loop expecting it to \"wait.\" If\n`xedit_status` reports `status: \"failed\"`, surface `data.error` to the user and\nstop — common causes are MO2 not running visibly, the Python plugin not loaded,\nthe xEdit binary missing, or xEdit's automation-serve tripping on the active\nload order.\n\nThe structured daemon-command and workflow reference now lives in KB records.\nUse `bgs_kb_query` \u002F `bgs_kb_get` for deep reference retrieval; the old\n`skills\u002Fxedit-automation\u002Fxedit-knowledgebase.md` path is a redirect only.\n\n### BGS knowledge-base tools (3) — curated knowledge, no xEdit daemon\n\nThe sibling BGS knowledge-base MCP is for curated modding knowledge, not live\nruntime state. It works before MO2 \u002F xEdit are configured; use xEdit MCP for\nactual plugin, load-order, and record readback.\n\n| Tool | Use |\n|---|---|\n| `bgs_kb_status` | Reports loaded KB packs, versions, games, domains, cache root, and user pack roots. |\n| `bgs_kb_query` | Searches loaded packs for ranked knowledge snippets with game\u002Fdomain filters and sources. |\n| `bgs_kb_get` | Fetches a full record by id, merging game-specific variants when `game` is provided. |\n\n## Hard rules (non-negotiable)\n\n1. **The user's `\u003CMO2_Root>` and any `\u003CMO2_Root>\u002F\u003Cgame>\u002FData\u002F` (or equivalent\n   \"Stock Game\" tree) is real game state.** Never write into it directly. Any\n   game-local change is expressed as an MO2 mod overlay under\n   `\u003CMO2_Root>\u002Fmods\u002F\u003Cmod-name>\u002F`. The MO2 VFS projects it at runtime.\n2. **All xEdit work goes through the bundled `xedit` MCP.** Never spawn\n   `xEdit.exe` directly from the shell, never parse `.esp\u002F.esm\u002F.esl` files with\n   your own Python\u002FJS, never invoke `xedit-client.ps1` from raw shell. The MCP\n   exists so the harness can enforce validation, state, rules, and audit on\n   every call. Atomic passthrough (`xedit_call`) is the documented escape hatch\n   when an intent tool does not fit — it is still in-harness.\n3. **Mutating operations require explicit user consent and a daemon launched\n   with `-IKnowWhatImDoing`.** Read the `xedit-automation` skill BEFORE any\n   destructive work. The anti-pattern list there is binding.\n4. **A `session.save` response is not durability.** A nonzero\n   `savedFilesPendingShutdown` \u002F `savePendingShutdownCount` is deferred. On\n   contract 0.23, `xedit_dirty` reconciles that fallback with the daemon's\n   authoritative pending queue and `xedit_flush` is the only supported in-band\n   drain. It validates the response and confirms daemon self-exit before clearing\n   the blocking guard. A partial or unknown outcome remains visible as\n   `lastFlush`; after relaunch it is labelled `previousSessionFlush` with the old\n   PID and timestamp. Failed in-band renames receive one normal exit-time retry,\n   so fresh-daemon readback, not the partial envelope alone, decides durability.\n   `force:true` on stop\u002Frestart is still explicit abandonment, never durability proof.\n5. **Large scope (many records, broad conflict survey) → delegate to a\n   read-only investigator subagent FIRST.** The subagent burns its own context\n   and returns a distilled summary. Do not loop hundreds of records through\n   your own context.\n6. **BGS domain knowledge routes through the KB first.** For questions about\n   how BGS modding works — Papyrus semantics, plugin-format gotchas, archive\n   precedence, load-order conventions, common engine quirks, or game-specific\n   toolchain gotchas — call `bgs_kb_status` \u002F `bgs_kb_query` before\n   improvising or reaching for web search. If the question is about what the\n   current local load order, plugin, or record actually is, use `xedit_*` or the\n   relevant file\u002FCLI surface instead. The KB is advisory; xEdit readback remains\n   authoritative for actual state. If `bgs_kb_status` reports no packs or the\n   needed game pack is missing, fall back to web research using the roadmap\n   Appendix source list or route setup\u002Fmaintenance work to install the pack.\n7. **First-run state**: if MO2 \u002F xEdit \u002F the control-plane Python plugin are\n   not yet set up on this machine, invoke `setting-up-bgs-modding-environment`\n   BEFORE any modpack work. That skill orchestrates detection and install.\n8. **Nexus credentials and Premium download paths**: MO2 stores the user's\n   Nexus API key globally in Windows Credential Manager under target\n   `ModOrganizer2_APIKEY` (legacy) \u002F `ModOrganizer2_NEXUS_OAUTH_TOKENS`\n   (modern OAuth). Reading the key requires explicit per-session user consent\n   and the key must be masked in any visible output. The agent-friendly\n   refresh path for Nexus update state is \"Option B\" — direct API call to\n   `\u002Fv1\u002Fgames\u002F{game}\u002Fmods\u002F{id}.json` + write back to `meta.ini` via\n   `mo2_edit_meta`, no MO2 GUI launch needed. Both workflows are documented in\n   the `maintaining-modding-environments` skill and in KB records\n   `install-planning.mo2-windows-credential-mining.v1` +\n   `install-planning.nexus-direct-api-update-check.v1`. For Premium-account\n   direct downloads, use `POST \u002Fv1\u002Fgames\u002F{game}\u002Fmods\u002F{id}\u002Ffiles\u002F{file_id}\u002Fdownload_link.json`\n   (returns 7 CDN mirrors) — Premium-only; free accounts must use the Nexus\n   browser flow.\n\n## How to use this bootstrap\n\n- This skill loads automatically on every new session. You do not need to\n  re-invoke it.\n- When a user intent matches a task skill in the table above, invoke that skill\n  via your skill tool. Do not paraphrase.\n- When the user asks about \"what can you do\", reference the skills inventory\n  here; do not invent capabilities the plugin does not have.\n- When answering BGS modding-domain questions, prefer local KB retrieval before\n  web search. The bundled core pack ships inline; per-game packs may be\n  installed later via setup \u002F maintenance skills; end-user packs may be\n  registered via `$BGS_KB_USER_PACKS` through `maintaining-modding-environments`.\n- When you would normally write code that touches BGS plugin files (`.esp\u002F.esm\u002F\n  .esl`), STOP and route through `xedit-automation` instead.\n- When the user is deciding whether to add or keep a mod (\"should I install X\",\n  \"is this good\", \"评估\"), route to `evaluating-bgs-mods` BEFORE any\n  install\u002Fdownload action.\n- When an INCLUDE verdict is in and the user needs to read author instructions \u002F\n  pick FOMOD options \u002F choose a file or variant, route to\n  `interpreting-mod-author-instructions`.\n- When the user is planning the whole pack, sizing batches, deciding rollback\n  boundaries, or declaring 风格, route to `curating-bgs-modpack`.\n- When the user reports a crash, CTD, FPS drop, freeze, or stutter (\"崩溃\",\n  \"掉帧\", \"卡顿\"), route to `diagnosing-bgs-problems` for symptom-first triage\n  BEFORE any blame attribution.\n- When the user wants to verify a freshly installed batch (\"test the pack\",\n  \"is it stable\", \"验证安装\"), route to `testing-bgs-modpack`.\n- When the user wants to translate plugin text or emit SST dictionaries for a\n  mod, route to `using-bgs-translator` instead of xEdit; translator reads plugin\n  text and emits dictionaries, it does not modify plugin binaries.\n- When the user wants to inspect, unpack, extract, or pack BA2\u002FBSA archives,\n  route to `using-bgs-archive`; archive packing must write to MO2 overlays, not\n  game `Data` or Stock-Game trees.\n- When the user wants to compile or decompile Papyrus scripts (`.psc` \u002F `.pex`),\n  route to `using-bgs-papyrus`; compiled `.pex` output must go to MO2 overlays,\n  not game `Data` or Stock-Game trees.\n- When the user asks to \"log\", \"record\", \"track\", or \"note\" modpack work,\n  route to `writing-modpack-devlog`. When the user asks to \"cut a release\" or\n  prepare release notes, route to `writing-modpack-changelog`.\n\n## See also\n\n- `setting-up-bgs-modding-environment` — first-run setup orchestrator.\n- `maintaining-modding-environments` — ongoing environment care, KB updates,\n  custom-pack registration, cache pruning, and health checks after first-run.\n- `evaluating-bgs-mods` — judgment skill: should this mod go in the pack (BGS\n  systemic-design fit, quality\u002Frisk\u002Fpack-value); hands off to\n  `interpreting-mod-author-instructions` on INCLUDE.\n- `interpreting-mod-author-instructions` — judgment skill: how to correctly\n  download\u002Finstall per author说明 (FOMOD reasoning, file\u002Fvariant selection,\n  prerequisites). Downstream from `evaluating-bgs-mods` INCLUDE verdict.\n- `curating-bgs-modpack` — judgment skill: whole-pack incremental strategy\n  (batch sizing, rollback boundaries, attribution\u002Fnaming, declaring 风格);\n  cross-stage skill that the per-mod skills feed.\n- `diagnosing-bgs-problems` — judgment skill: symptom-first triage for CTD \u002F\n  FPS \u002F freeze \u002F stutter; escalates to `xedit-conflict-audit` or\n  `using-bgs-archive` once root-cause class is identified.\n- `testing-bgs-modpack` — judgment skill: proactive post-install verification\n  of an install batch; escalates to `diagnosing-bgs-problems` on failure.\n- `xedit-automation` — hub skill for all xEdit work; routing doctrine,\n  anti-patterns, sub-agent recipes.\n- BGS KB records under `knowledge\u002Fbgs-kb\u002Fpacks\u002Fcore\u002Frecords\u002F` — deep reference\n  for daemon commands, error codes, save semantics, glossary, and durable gotchas.\n- `xedit-conflict-audit` — the W2 conflict-audit workflow.\n- `using-bgs-translator` — CLI + Tk workflow for LLM-assisted plugin text\n  translation and SST dictionary export.\n- `using-bgs-archive` — BA2\u002FBSA archive inspection, extraction, and safe\n  overlay-only packing.\n- `using-bgs-papyrus` — Papyrus PSC\u002FPEX compile\u002Fdecompile workflows for Skyrim,\n  Fallout 4, and Starfield.\n- `writing-modpack-devlog`, `writing-modpack-changelog` — runtime asset\n  skills for project documentation.\n\n---\n\n> Plugin: `bgs-modding-superpowers`. Repo: https:\u002F\u002Fgithub.com\u002FBB-84C\u002Fbgs-modding-superpowers.\n> If any environmental component (MO2, xEdit, control-plane Python plugin) is missing,\n> route through `setting-up-bgs-modding-environment` before continuing.\n",{"name":5,"description":7},"main","b0f0a87593c578a7898eccaf1b363f7f87c1f99b","plugins\u002FBB-84C\u002Fbgs-modding-superpowers\u002Fskills\u002Fusing-bgs-modding-superpowers",491,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins","https:\u002F\u002Fhol.org\u002Fplugins\u002Fbest-codex-plugins","https:\u002F\u002Fgithub.com\u002Fhashgraph-online","https:\u002F\u002Fhol.org","Open-source standards and developer tools for interoperable AI agents: discovery, identity, communication, payments, privacy and security.","2026-11-14 14:06:13",{"source":8,"skillName":5,"commands":56,"prompt":66,"zipAvailable":67},[57,60,63],{"tool":58,"command":59},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill using-bgs-modding-superpowers",{"tool":61,"command":62},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill using-bgs-modding-superpowers",{"tool":64,"command":65},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill using-bgs-modding-superpowers","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FBB-84C\u002Fbgs-modding-superpowers\u002Fskills\u002Fusing-bgs-modding-superpowers\u002FSKILL.md",true,[],[70,80,88,96,104,112],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":74,"licenseFileUrl":75,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":79},"01M7DV332YQMGD8WTRJ9DZQXTB","worktable-review-with-annotations","Create, inspect, reply to, update, or resolve situated Worktable annotations. Use when feedback belongs to a Doc section, block, text range, or HTML Doc, or when the user asks to address existing review feedback and coordinate a requested artifact edit.","MIT","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":74,"licenseFileUrl":84,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":79},"01M7DV2YGHCZVBEB1AHYB6CGHE","worktable-find-and-synthesize-context","Find, assess, and synthesize context from Worktable Docs and Records. Use when the user asks what a workspace contains, wants workspace-backed research, needs current facts reconciled across artifacts, or requests a cited synthesis without changing workspace state.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FSKILL.md",[],[],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":74,"licenseFileUrl":92,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":79},"01M7DV2TQN1H11ME2SAF9MXN7V","worktable-create-or-update-docs","Create, edit, rename, or maintain narrative Worktable Docs. Use for plans, decisions, briefs, notes, research syntheses, and other durable prose when the user requests a new artifact or a safe update to an existing one.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FSKILL.md",[],[],{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":74,"licenseFileUrl":100,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":79},"01M7DV2NE452NEA8TXATKSNAJH","worktable-create-or-manage-records","Organize repeated structured information as durable Worktable Records. Use for research datasets, inventories, directories, pipelines, trackers, and other collections whose items need identity, fields, filtering, links, validation, or individual updates.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FSKILL.md",[],[],{"skillNo":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":74,"licenseFileUrl":108,"sourceHtmlUrl":109,"categories":110,"keywords":111,"publishedAt":79},"01M7DV2HENRBR2KSCVM064WH0Y","worktable-create-or-manage-interactive-html","Create or improve durable visual and interactive artifacts in Worktable. Use for dashboards, trackers, calculators, mini apps, slide presentations, and other requests that benefit from a polished HTML Doc.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FSKILL.md",[],[],{"skillNo":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":74,"licenseFileUrl":116,"sourceHtmlUrl":117,"categories":118,"keywords":119,"publishedAt":79},"01M7DV2CADR5R7RQFFYPNAGR9Y","worktable-collaborate-threads","Read, answer, and hand off messages through durable Worktable threads with users or other authenticated participants. Use when the user asks to check addressed messages, reply to a participant, continue a thread, request another agent's help, wait briefly for a response, or watch for comments and messages sent to the agent.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FSKILL.md",[],[]]