[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MKJQW9MHSM8NH33BC02N43":3,"skill-same:01M6MKJQW9MHSM8NH33BC02N43":56},{"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":26,"linkOnly":27,"markdownContent":28,"markdownBody":29,"frontMatter":30,"refName":33,"commitSha":34,"skillDirectory":35,"forksCount":36,"repositoryHtmlUrl":37,"repositoryHomepageUrl":38,"ownerHtmlUrl":39,"ownerBlogUrl":40,"ownerDescription":41,"updatedAt":42,"install":43,"resources":55},"01M6MKJQW9MHSM8NH33BC02N43","plan",null,"Open the plan room to explore the code and design the work with the owner, building nothing until the owner leaves.","hashgraph-online\u002Fawesome-codex-plugins","hashgraph-online","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F160371962?v=4","01M6CNB6NRJVNNGN14TR01Q6D3","HOL (Hashgraph Online)","01M6JT1HSKKG9V68KQAQGBA7XP",1575,"MIT","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Forwa-mahmoud\u002Fnightshift\u002Fskills\u002Fplan\u002FSKILL.md",[],[5,19,20,21,22,23,24,25],"explore","true","open","design","code","with","work","2026-11-10 10:12:30",false,"---\nname: plan\ndescription: Open the plan room to explore the code and design the work with the owner, building nothing until the owner leaves.\nlicense: MIT\nmetadata:\n  internal: true\n---\n\nPlan with the owner in the plan room. Here the conversation explores, weighs options and draws the\nplan; nothing gets implemented until the owner leaves the room on purpose. While the room binds this\nconversation, each owner message carries a reminder that it is planning, the edit tools write only\nthe plan's own files, and the commands and tools on the owner's `planRoom` lists in `rules.json` are\nblocked (by default `git commit`, `git push` and `git tag`). Everything else runs, so research is\nfree: read, search, the web, `gh`, the browser, helper agents and questions.\n\nResolve the installed plugin root to an absolute `$NIGHTSHIFT_PLUGIN_ROOT` — `${CLAUDE_PLUGIN_ROOT}`\non Claude Code, `$PLUGIN_ROOT` on Codex when set, otherwise the absolute path this skill was\nattached from (`skills\u002Fplan\u002FSKILL.md`). Run every command below through\n`\"$NIGHTSHIFT_PLUGIN_ROOT\u002Fruntime\u002Fns\"` — native Windows: `& \"$NIGHTSHIFT_PLUGIN_ROOT\\runtime\\windows\\ns.ps1\"`\nin the PowerShell tool, same verbs — which resolves the host and the workspace; `ns help` lists the\nverbs, and `ns bind` prints the six resolved facts (`TASK_ROOT`, `NIGHTSHIFT_WORKSPACE`, `NS`,\n`NIGHTSHIFT_PLUGIN_ROOT`, `HOST`, `SOURCE`); `$NS` below is that `NS`. Never a bare relative path: the working\ndirectory persists between calls. Each `$NS\u002F...` path below is where the current layout keeps that file;\n`ns path \u003Ckey>` prints where this workspace keeps it, and `ns path --list` names every key.\n\n## 1. Enter the room\n\nPass the host you are running on (`claude`, `codex` or `cursor`):\n\n```bash\n\"$NIGHTSHIFT_PLUGIN_ROOT\u002Fruntime\u002Fns\" plan-enter --host claude\n```\n\nNative Windows: `& \"$NIGHTSHIFT_PLUGIN_ROOT\\runtime\\windows\\ns.ps1\" plan-enter --host claude`.\n\nThe room opens unbound. **The very next tool call is the probe that binds it to this\nconversation** — nothing in between, not even a read:\n\n```bash\n: nightshift-plan-probe\n```\n\n```powershell\n$null = 'nightshift-plan-probe'\n```\n\n- The probe runs cleanly: the room is bound to this conversation. Tell the owner in one line that the\n  plan room is open, that nothing is implemented here, and how they leave it (section 7).\n- The probe is denied because the room is bound to another conversation: tell the owner, and stop.\n  They plan in that conversation, or leave the room first.\n- The probe is denied because this conversation is working the shift: no room was opened. Tell the\n  owner; they plan in another conversation, or stop the shift first.\n- `plan-enter` reports no `.nightshift\u002F`: the project has no Nightshift workspace. Tell the owner to run\n  Setup, and stop.\n\nAn open room bound to this conversation (after compaction, say) needs no new entry: run\n`plan-enter` and the probe again, and both pass.\n\n**Resume before anything else.** `plan-enter` also prints `plan record \u003Cpath>` and one\n`open plan: \u003Centry>` line for each plan the record still holds open (`open plan: none` when there is\nnone). With an open plan, read the record first and pick up exactly where its `Where we are` line\nleft off: say in a sentence or two what was decided and what comes next, so the owner never repeats\nthemselves. With more than one open plan, ask which one this conversation continues.\n\n## 2. Review what the last shift left\n\n`plan-enter` ends with `review` lines: what waits for the owner's word. `review none` means there is\nnothing, and the room is plain planning. Otherwise, before new planning, offer to walk the owner\nthrough them, one at a time, in this order:\n\n- `review morning` and `review receipts` — the morning page (under `ns path receipts`) and the\n  receipts index (`ns path receipts-index`). Read them first and give the owner the outcome in a few\n  lines: what shipped, what did not, what needs a decision.\n- `review parked` — each open decision in the parking lot (`ns path parking-lot`). Show the default\n  the shift chose and why, and ask whether it stands. Record the answer by appending\n  ` · answered: \u003Cthe owner's decision>` to that entry.\n- `review snag` — each snag with no disposition in the snag log (`ns path snag-log`). Ask what to do:\n  the owner's decision becomes its disposition (` · rejected-because: \u003Cwhy>` or\n  ` · accepted-tradeoff: \u003Cwhy>`), and a snag to fix becomes an item drafted for the next shift (section\n  6), its disposition written once the fix lands.\n- `review open` and `review stopped` — the items still open, and those closed at their hard budget,\n  in the punch list (`ns path punch-list`). Ask for each: keep it for the next shift as it is, rework\n  it (draft the new version, section 6), or drop it. The punch list is the owner's to edit: a box to\n  reopen, reword or remove is theirs to change, and the room cannot write it.\n\nNothing is written without the owner's answer to that entry. The parking lot, the snag log, the\ndrafting table, the plan files and the plan record are the only files the room writes; an archived shift reads the\nsame way, from what Archive left live.\n\n## 3. Choose the plan, and how deep — once\n\nEach plan is its own file: a complete punch list with its own contract, gates and items, waiting\nits turn. `plan-enter` prints one `plan file: \u003Ckey> · \u003Cname> · \u003Cn> open` line per plan, or\n`plan file: none`. Before the discussion starts, ask one question that covers: continue one of\nthose plans or start a new one, and for a new one, its name; what the owner wants to plan; how they\nwant to brainstorm it (an edge-case pass, a pre-mortem, an ordering and risk check, research); and\nwhether to suggest evidence lines for each item, and if so whether a missing evidence file is\nhard-checked (`block`), only reported (`report`) or not checked (`off`). The default is none of them. For a new plan, create its file:\n\n```bash\n\"$NIGHTSHIFT_PLUGIN_ROOT\u002Fruntime\u002Fns\" plan-new --name \"\u003Cthe owner's name for it>\"\n```\n\nIt copies the punch list's contract and gates into `$NS\u002Fstaging\u002Fplans\u002F\u003Ckey>.md` under\n`# Punch List — \u003Cname>`, and keeps a plan that already has that key. Everything this plan writes\ngoes into that one file, so plans never mix. When `plan-new` says the workspace keeps plans in its\ndrafting table, write the plan there under a `## Plan: \u003Ctitle>` heading instead.\n\nTake one answer and do not follow up. Record it in the plan record as\n`Decided: planning depth — none` or one `Decided:` line per option picked. Skip the question when\nresuming an open plan whose record already holds that line.\n\nWith none, never raise these options again for that plan; the owner may still ask for any of them\nat any time. With some picked, read\n`$NIGHTSHIFT_PLUGIN_ROOT\u002Fskills\u002Fnightshift\u002Freferences\u002Fplan\u002Fmenu.md` and apply only those, as the work\ntakes shape: evidence and edge-case lines on each item as it is drafted, research when an open\nquestion needs it, the ordering and risk check once there are several items, and the pre-mortem when\nthe item list is nearly complete. The owner keeps, edits or drops every line they propose. Evidence\nshows the work. check off leaves the tick alone, report names a missing file, and block keeps the\nstop open.\n\n## 4. Think with the owner\n\nThis is a conversation, not a procedure. Follow the owner's direction and pace; do not impose phases,\ntemplates or a checklist while discussing.\n\n- **Read before you ask or propose.** Open the files, tests and history the question touches\n  (`git log`, `git show`, `git blame` and every read-only tool are free here). Name paths and lines.\n  A question the code already answers is not one to ask the owner.\n- **Lay out real options.** For a decision that matters, give two or three options with what each\n  costs and buys, then say which one you would pick and why. A survey with no recommendation hands\n  the work back.\n- **Draw it.** An ASCII diagram of a flow, a state machine or a component boundary often settles what\n  a paragraph cannot. Use one when it helps, not by default.\n- **Ask freely.** Questions are the point of this room. Ask one at a time when the answer changes what\n  comes next.\n- **Keep what was decided visible.** When the discussion moves on, restate the decision in one line\n  so it is not reopened by accident.\n\nWhen the owner says \"just do it\" or \"implement it\": the room still holds. Say plainly that nothing\ncan be built in this conversation while the plan room is open, and give the exits (section 6). Build\nnothing through any tool, the shell included: no code written into the staging folder to copy out\nlater, no scripts that change the project, and no asking another conversation to make the change.\n\n## 5. Keep the plan record current\n\nThe plan record (`ns path plan-record`) is the room's notebook. Write it as the discussion moves —\nit needs no permission, and it is what lets compaction, a closed tab or a new day lose nothing. Keep\none entry per plan, below the record's rule, in the shape its header shows:\n\n```text\n- **\u003Ctopic>** · open since \u003CYYYY-MM-DD HH:MM (UTC±HH:MM)>\n  - Where we are: \u003Cthe exact point the conversation reached, and the next question>\n  - Decided: \u003Cdecision> — \u003Cwhy>\n  - Rejected: \u003Coption> — \u003Cthe reason>\n  - Open: \u003Ca question still waiting for an answer>\n```\n\n- Start an entry when a new plan starts, in the device's local time with its offset.\n- Add a `Decided:`, `Rejected:` or `Open:` line the moment one is settled or raised, and rewrite\n  `Where we are` at every natural pause. Answered `Open:` lines become `Decided:` lines.\n- **A rejected option stays rejected.** Never propose it again unless there is new evidence, and then\n  name the evidence and the earlier reason together.\n- When the owner sets a plan aside, append ` · dropped: \u003Cwhy>` to the entry's first line.\n\n## 6. Draft as you go — each write on the owner's yes\n\nPlanning is continuous. Draft an item as soon as the discussion settles it, and keep going to the\nnext. When the owner agrees with an item, write it under `## Items` in the plan's file and say what\nwas written. When the discussion changes an item already\nwritten, edit it in place and say what changed. Agreement with the item itself is the yes; agreement\nwith an idea is not. Nothing reaches the plan that the owner has not agreed to.\n\nKeep the plan's notes in a `## Plan` section just above `## Items`, written with its first item and\nkept current as the plan grows. Leave the contract and gates above it as `plan-new` copied them,\nunless the owner changes them, and never touch another plan's file:\n\n```text\n## Plan\n\nWhy: \u003Cthe problem, and why now>\nScope: \u003Cwhat this plan covers>\nNon-goals: \u003Cwhat it deliberately leaves out>\nDesign notes: \u003Cthe decisions taken, and the options rejected with the reason>\nRecord: `staging\u002Fplan-record.md` — \u003Ctopic>\nEstimate: \u003Cthe shift-estimate figures for these items, or \"no history yet\">\n\n- [ ] **1. \u003Ctitle>.**\n  - \u003Cwhat to build, plainly>\n  - Budget: \u003Conly on an item at real risk of getting stuck, and only when the owner takes it: soft 30m \u002F 1.5M tokens, hard 1h \u002F 3M tokens>\n  - Verify:\n    - WHEN \u003Csituation> THEN \u003Cobservable result>\n    - WHEN \u003Cedge or failure case> THEN \u003Cobservable result>\n    - \u003Cthe commands that check them>\n  - Evidence: \u003Conly when the owner takes evidence lines: what shows the work at a glance>\n  - Commit: `\u003Ctype: message>`\n```\n\n- **Commits follow the owner's contract.** Under the shipped contract each item is one commit, so an\n  item that would need two is two items. Order is dependency order: nothing is built twice.\n- **Verify is acceptance, not activity.** Each WHEN\u002FTHEN states behaviour someone could observe and a\n  test could fail on. \"Tests pass\" or \"it works\" is not a scenario. Add the commands that check the\n  scenarios.\n- **The item shape is a punch list's**: one top-level checkbox per item, everything else plain\n  indented bullets, never a nested checkbox — a nested box counts as an open item once the item is\n  promoted.\n- In artifact mode, an item names its receipt instead of a `Commit:` line.\n- **Size it from the owner's history.** Once the list is nearly complete, or when the owner asks, run\n  `\"$NIGHTSHIFT_PLUGIN_ROOT\u002Fruntime\u002Fns\" shift-estimate --items \u003CN>` for the N items drafted. It reads\n  the Time and Tokens totals of past ticked receipts and prints per-item figures, a total and a\n  suggested deadline. Show them as an estimate from the owner's own receipts, never a limit, and\n  keep a missing reading missing. Set a deadline only if the owner takes it. When it reports too few\n  readings, say there is no history to estimate from yet.\n- **Offer a budget only where an item could get stuck.** Most items need none, and a limit on every\n  item is a burden for the owner. Offer a `Budget:` line only for an item with a high chance of\n  getting stuck: open-ended investigation, a flaky or unreproduced failure, an unfamiliar dependency,\n  or an approach the plan could not settle. Say why that item is at risk, propose limits from the\n  estimate, and write the line only if the owner takes it.\n\nWhen the owner says the plan is complete, close the record's entry by appending\n` · captured: \u003Cthe plan's file>` to its first line; Archive files it with the shift. The `Record:`\nline names the record by its path inside `.nightshift\u002F`, so it stays right when Start moves the\nplan into place as the punch list.\n\nBefore naming the way to build it, run\n`\"$NIGHTSHIFT_PLUGIN_ROOT\u002Fruntime\u002Fns\" check-items --file \u003Cthe plan's file>`. It names, per item, a missing or empty `Verify:`, a `Verify:` that names nothing\ncheckable (a question, since a plain sentence can be checkable), a missing `Commit:`, an\n`Evidence:` that names nothing, a `Budget:` that does not parse, a nested checkbox, and any\ncheckbox no item owns. Show the owner every finding.\nCorrect one only with their yes. The check refuses nothing: whether to start the plan is the\nowner's call.\n\nThen name the way to build it: leave the plan room by typing `\u002Fnightshift:start`, the same in\nClaude Code, Codex, and Cursor. With an empty\npunch list, Start offers the waiting plans by name. With open items already in the punch list,\nStart works those, and the plan waits its turn.\n\n## 7. Leaving is the owner's\n\nOnly the owner closes the room. On Claude Code and Cursor they type `\u002Fnightshift:plan-exit`, or\n`\u002Fnightshift:start` to leave and start the shift in one step. On Codex they type\n`$nightshift:plan-exit` or `$nightshift:start`. In any terminal they run\n`\"$NIGHTSHIFT_PLUGIN_ROOT\u002Fruntime\u002Fns\" plan-exit`.\n\nNever run `plan-exit`, never touch the room's marker, and never invoke the Start or plan-exit skill\nyourself to get out: the hooks refuse the first two, Start refuses while the room is open, and none\nof it closes the room. If the owner asks you to leave it for them, give them the exit to type.\n","Plan with the owner in the plan room. Here the conversation explores, weighs options and draws the\nplan; nothing gets implemented until the owner leaves the room on purpose. While the room binds this\nconversation, each owner message carries a reminder that it is planning, the edit tools write only\nthe plan's own files, and the commands and tools on the owner's `planRoom` lists in `rules.json` are\nblocked (by default `git commit`, `git push` and `git tag`). Everything else runs, so research is\nfree: read, search, the web, `gh`, the browser, helper agents and questions.\n\nResolve the installed plugin root to an absolute `$NIGHTSHIFT_PLUGIN_ROOT` — `${CLAUDE_PLUGIN_ROOT}`\non Claude Code, `$PLUGIN_ROOT` on Codex when set, otherwise the absolute path this skill was\nattached from (`skills\u002Fplan\u002FSKILL.md`). Run every command below through\n`\"$NIGHTSHIFT_PLUGIN_ROOT\u002Fruntime\u002Fns\"` — native Windows: `& \"$NIGHTSHIFT_PLUGIN_ROOT\\runtime\\windows\\ns.ps1\"`\nin the PowerShell tool, same verbs — which resolves the host and the workspace; `ns help` lists the\nverbs, and `ns bind` prints the six resolved facts (`TASK_ROOT`, `NIGHTSHIFT_WORKSPACE`, `NS`,\n`NIGHTSHIFT_PLUGIN_ROOT`, `HOST`, `SOURCE`); `$NS` below is that `NS`. Never a bare relative path: the working\ndirectory persists between calls. Each `$NS\u002F...` path below is where the current layout keeps that file;\n`ns path \u003Ckey>` prints where this workspace keeps it, and `ns path --list` names every key.\n\n## 1. Enter the room\n\nPass the host you are running on (`claude`, `codex` or `cursor`):\n\n```bash\n\"$NIGHTSHIFT_PLUGIN_ROOT\u002Fruntime\u002Fns\" plan-enter --host claude\n```\n\nNative Windows: `& \"$NIGHTSHIFT_PLUGIN_ROOT\\runtime\\windows\\ns.ps1\" plan-enter --host claude`.\n\nThe room opens unbound. **The very next tool call is the probe that binds it to this\nconversation** — nothing in between, not even a read:\n\n```bash\n: nightshift-plan-probe\n```\n\n```powershell\n$null = 'nightshift-plan-probe'\n```\n\n- The probe runs cleanly: the room is bound to this conversation. Tell the owner in one line that the\n  plan room is open, that nothing is implemented here, and how they leave it (section 7).\n- The probe is denied because the room is bound to another conversation: tell the owner, and stop.\n  They plan in that conversation, or leave the room first.\n- The probe is denied because this conversation is working the shift: no room was opened. Tell the\n  owner; they plan in another conversation, or stop the shift first.\n- `plan-enter` reports no `.nightshift\u002F`: the project has no Nightshift workspace. Tell the owner to run\n  Setup, and stop.\n\nAn open room bound to this conversation (after compaction, say) needs no new entry: run\n`plan-enter` and the probe again, and both pass.\n\n**Resume before anything else.** `plan-enter` also prints `plan record \u003Cpath>` and one\n`open plan: \u003Centry>` line for each plan the record still holds open (`open plan: none` when there is\nnone). With an open plan, read the record first and pick up exactly where its `Where we are` line\nleft off: say in a sentence or two what was decided and what comes next, so the owner never repeats\nthemselves. With more than one open plan, ask which one this conversation continues.\n\n## 2. Review what the last shift left\n\n`plan-enter` ends with `review` lines: what waits for the owner's word. `review none` means there is\nnothing, and the room is plain planning. Otherwise, before new planning, offer to walk the owner\nthrough them, one at a time, in this order:\n\n- `review morning` and `review receipts` — the morning page (under `ns path receipts`) and the\n  receipts index (`ns path receipts-index`). Read them first and give the owner the outcome in a few\n  lines: what shipped, what did not, what needs a decision.\n- `review parked` — each open decision in the parking lot (`ns path parking-lot`). Show the default\n  the shift chose and why, and ask whether it stands. Record the answer by appending\n  ` · answered: \u003Cthe owner's decision>` to that entry.\n- `review snag` — each snag with no disposition in the snag log (`ns path snag-log`). Ask what to do:\n  the owner's decision becomes its disposition (` · rejected-because: \u003Cwhy>` or\n  ` · accepted-tradeoff: \u003Cwhy>`), and a snag to fix becomes an item drafted for the next shift (section\n  6), its disposition written once the fix lands.\n- `review open` and `review stopped` — the items still open, and those closed at their hard budget,\n  in the punch list (`ns path punch-list`). Ask for each: keep it for the next shift as it is, rework\n  it (draft the new version, section 6), or drop it. The punch list is the owner's to edit: a box to\n  reopen, reword or remove is theirs to change, and the room cannot write it.\n\nNothing is written without the owner's answer to that entry. The parking lot, the snag log, the\ndrafting table, the plan files and the plan record are the only files the room writes; an archived shift reads the\nsame way, from what Archive left live.\n\n## 3. Choose the plan, and how deep — once\n\nEach plan is its own file: a complete punch list with its own contract, gates and items, waiting\nits turn. `plan-enter` prints one `plan file: \u003Ckey> · \u003Cname> · \u003Cn> open` line per plan, or\n`plan file: none`. Before the discussion starts, ask one question that covers: continue one of\nthose plans or start a new one, and for a new one, its name; what the owner wants to plan; how they\nwant to brainstorm it (an edge-case pass, a pre-mortem, an ordering and risk check, research); and\nwhether to suggest evidence lines for each item, and if so whether a missing evidence file is\nhard-checked (`block`), only reported (`report`) or not checked (`off`). The default is none of them. For a new plan, create its file:\n\n```bash\n\"$NIGHTSHIFT_PLUGIN_ROOT\u002Fruntime\u002Fns\" plan-new --name \"\u003Cthe owner's name for it>\"\n```\n\nIt copies the punch list's contract and gates into `$NS\u002Fstaging\u002Fplans\u002F\u003Ckey>.md` under\n`# Punch List — \u003Cname>`, and keeps a plan that already has that key. Everything this plan writes\ngoes into that one file, so plans never mix. When `plan-new` says the workspace keeps plans in its\ndrafting table, write the plan there under a `## Plan: \u003Ctitle>` heading instead.\n\nTake one answer and do not follow up. Record it in the plan record as\n`Decided: planning depth — none` or one `Decided:` line per option picked. Skip the question when\nresuming an open plan whose record already holds that line.\n\nWith none, never raise these options again for that plan; the owner may still ask for any of them\nat any time. With some picked, read\n`$NIGHTSHIFT_PLUGIN_ROOT\u002Fskills\u002Fnightshift\u002Freferences\u002Fplan\u002Fmenu.md` and apply only those, as the work\ntakes shape: evidence and edge-case lines on each item as it is drafted, research when an open\nquestion needs it, the ordering and risk check once there are several items, and the pre-mortem when\nthe item list is nearly complete. The owner keeps, edits or drops every line they propose. Evidence\nshows the work. check off leaves the tick alone, report names a missing file, and block keeps the\nstop open.\n\n## 4. Think with the owner\n\nThis is a conversation, not a procedure. Follow the owner's direction and pace; do not impose phases,\ntemplates or a checklist while discussing.\n\n- **Read before you ask or propose.** Open the files, tests and history the question touches\n  (`git log`, `git show`, `git blame` and every read-only tool are free here). Name paths and lines.\n  A question the code already answers is not one to ask the owner.\n- **Lay out real options.** For a decision that matters, give two or three options with what each\n  costs and buys, then say which one you would pick and why. A survey with no recommendation hands\n  the work back.\n- **Draw it.** An ASCII diagram of a flow, a state machine or a component boundary often settles what\n  a paragraph cannot. Use one when it helps, not by default.\n- **Ask freely.** Questions are the point of this room. Ask one at a time when the answer changes what\n  comes next.\n- **Keep what was decided visible.** When the discussion moves on, restate the decision in one line\n  so it is not reopened by accident.\n\nWhen the owner says \"just do it\" or \"implement it\": the room still holds. Say plainly that nothing\ncan be built in this conversation while the plan room is open, and give the exits (section 6). Build\nnothing through any tool, the shell included: no code written into the staging folder to copy out\nlater, no scripts that change the project, and no asking another conversation to make the change.\n\n## 5. Keep the plan record current\n\nThe plan record (`ns path plan-record`) is the room's notebook. Write it as the discussion moves —\nit needs no permission, and it is what lets compaction, a closed tab or a new day lose nothing. Keep\none entry per plan, below the record's rule, in the shape its header shows:\n\n```text\n- **\u003Ctopic>** · open since \u003CYYYY-MM-DD HH:MM (UTC±HH:MM)>\n  - Where we are: \u003Cthe exact point the conversation reached, and the next question>\n  - Decided: \u003Cdecision> — \u003Cwhy>\n  - Rejected: \u003Coption> — \u003Cthe reason>\n  - Open: \u003Ca question still waiting for an answer>\n```\n\n- Start an entry when a new plan starts, in the device's local time with its offset.\n- Add a `Decided:`, `Rejected:` or `Open:` line the moment one is settled or raised, and rewrite\n  `Where we are` at every natural pause. Answered `Open:` lines become `Decided:` lines.\n- **A rejected option stays rejected.** Never propose it again unless there is new evidence, and then\n  name the evidence and the earlier reason together.\n- When the owner sets a plan aside, append ` · dropped: \u003Cwhy>` to the entry's first line.\n\n## 6. Draft as you go — each write on the owner's yes\n\nPlanning is continuous. Draft an item as soon as the discussion settles it, and keep going to the\nnext. When the owner agrees with an item, write it under `## Items` in the plan's file and say what\nwas written. When the discussion changes an item already\nwritten, edit it in place and say what changed. Agreement with the item itself is the yes; agreement\nwith an idea is not. Nothing reaches the plan that the owner has not agreed to.\n\nKeep the plan's notes in a `## Plan` section just above `## Items`, written with its first item and\nkept current as the plan grows. Leave the contract and gates above it as `plan-new` copied them,\nunless the owner changes them, and never touch another plan's file:\n\n```text\n## Plan\n\nWhy: \u003Cthe problem, and why now>\nScope: \u003Cwhat this plan covers>\nNon-goals: \u003Cwhat it deliberately leaves out>\nDesign notes: \u003Cthe decisions taken, and the options rejected with the reason>\nRecord: `staging\u002Fplan-record.md` — \u003Ctopic>\nEstimate: \u003Cthe shift-estimate figures for these items, or \"no history yet\">\n\n- [ ] **1. \u003Ctitle>.**\n  - \u003Cwhat to build, plainly>\n  - Budget: \u003Conly on an item at real risk of getting stuck, and only when the owner takes it: soft 30m \u002F 1.5M tokens, hard 1h \u002F 3M tokens>\n  - Verify:\n    - WHEN \u003Csituation> THEN \u003Cobservable result>\n    - WHEN \u003Cedge or failure case> THEN \u003Cobservable result>\n    - \u003Cthe commands that check them>\n  - Evidence: \u003Conly when the owner takes evidence lines: what shows the work at a glance>\n  - Commit: `\u003Ctype: message>`\n```\n\n- **Commits follow the owner's contract.** Under the shipped contract each item is one commit, so an\n  item that would need two is two items. Order is dependency order: nothing is built twice.\n- **Verify is acceptance, not activity.** Each WHEN\u002FTHEN states behaviour someone could observe and a\n  test could fail on. \"Tests pass\" or \"it works\" is not a scenario. Add the commands that check the\n  scenarios.\n- **The item shape is a punch list's**: one top-level checkbox per item, everything else plain\n  indented bullets, never a nested checkbox — a nested box counts as an open item once the item is\n  promoted.\n- In artifact mode, an item names its receipt instead of a `Commit:` line.\n- **Size it from the owner's history.** Once the list is nearly complete, or when the owner asks, run\n  `\"$NIGHTSHIFT_PLUGIN_ROOT\u002Fruntime\u002Fns\" shift-estimate --items \u003CN>` for the N items drafted. It reads\n  the Time and Tokens totals of past ticked receipts and prints per-item figures, a total and a\n  suggested deadline. Show them as an estimate from the owner's own receipts, never a limit, and\n  keep a missing reading missing. Set a deadline only if the owner takes it. When it reports too few\n  readings, say there is no history to estimate from yet.\n- **Offer a budget only where an item could get stuck.** Most items need none, and a limit on every\n  item is a burden for the owner. Offer a `Budget:` line only for an item with a high chance of\n  getting stuck: open-ended investigation, a flaky or unreproduced failure, an unfamiliar dependency,\n  or an approach the plan could not settle. Say why that item is at risk, propose limits from the\n  estimate, and write the line only if the owner takes it.\n\nWhen the owner says the plan is complete, close the record's entry by appending\n` · captured: \u003Cthe plan's file>` to its first line; Archive files it with the shift. The `Record:`\nline names the record by its path inside `.nightshift\u002F`, so it stays right when Start moves the\nplan into place as the punch list.\n\nBefore naming the way to build it, run\n`\"$NIGHTSHIFT_PLUGIN_ROOT\u002Fruntime\u002Fns\" check-items --file \u003Cthe plan's file>`. It names, per item, a missing or empty `Verify:`, a `Verify:` that names nothing\ncheckable (a question, since a plain sentence can be checkable), a missing `Commit:`, an\n`Evidence:` that names nothing, a `Budget:` that does not parse, a nested checkbox, and any\ncheckbox no item owns. Show the owner every finding.\nCorrect one only with their yes. The check refuses nothing: whether to start the plan is the\nowner's call.\n\nThen name the way to build it: leave the plan room by typing `\u002Fnightshift:start`, the same in\nClaude Code, Codex, and Cursor. With an empty\npunch list, Start offers the waiting plans by name. With open items already in the punch list,\nStart works those, and the plan waits its turn.\n\n## 7. Leaving is the owner's\n\nOnly the owner closes the room. On Claude Code and Cursor they type `\u002Fnightshift:plan-exit`, or\n`\u002Fnightshift:start` to leave and start the shift in one step. On Codex they type\n`$nightshift:plan-exit` or `$nightshift:start`. In any terminal they run\n`\"$NIGHTSHIFT_PLUGIN_ROOT\u002Fruntime\u002Fns\" plan-exit`.\n\nNever run `plan-exit`, never touch the room's marker, and never invoke the Start or plan-exit skill\nyourself to get out: the hooks refuse the first two, Start refuses while the room is open, and none\nof it closes the room. If the owner asks you to leave it for them, give them the exit to type.\n",{"name":5,"license":15,"metadata":31,"description":7},{"internal":32},true,"main","70b6a3a3a7c774671e45af646306e1448baf0511","plugins\u002Forwa-mahmoud\u002Fnightshift\u002Fskills\u002Fplan",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":44,"prompt":54,"zipAvailable":32},[45,48,51],{"tool":46,"command":47},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill plan",{"tool":49,"command":50},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill plan",{"tool":52,"command":53},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill plan","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Forwa-mahmoud\u002Fnightshift\u002Fskills\u002Fplan\u002FSKILL.md",[],[57,66,74,82,90,98],{"skillNo":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":61,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":65},"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.","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":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":70,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":65},"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":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":78,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":65},"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":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":86,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":65},"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":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":94,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":65},"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":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":102,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":65},"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",[],[]]