[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MJFGA6F2AG08W7Z1THQ6A1":3,"skill-same:01M6MJFGA6F2AG08W7Z1THQ6A1":67},{"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":38,"linkOnly":39,"markdownContent":40,"markdownBody":41,"frontMatter":42,"refName":43,"commitSha":44,"skillDirectory":45,"forksCount":46,"repositoryHtmlUrl":47,"repositoryHomepageUrl":48,"ownerHtmlUrl":49,"ownerBlogUrl":50,"ownerDescription":51,"updatedAt":52,"install":53,"resources":66},"01M6MJFGA6F2AG08W7Z1THQ6A1","configure-review",null,"Use when configuring or changing a repository's tracked branches, layered review policy, ignored tracked paths, retrieval limits, summary depth, or non-secret task-board metadata.","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\u002Fmimfort\u002Frag_for_git\u002Fplugin\u002Fskills\u002Fconfigure-review\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37],"configure","configure review","review","branches","review policy","ignored","when","limits","depth","layered","retrieval","paths","summary","task","use","board","repository","metadata","policy","2026-11-10 10:12:30",false,"---\nname: configure-review\ndescription: Use when configuring or changing a repository's tracked branches, layered review policy, ignored tracked paths, retrieval limits, summary depth, or non-secret task-board metadata.\n---\n\n# Configure Review\n\nAlways answer the user in Russian. Update only the requested policy values; **Never clobber** foreign\nkeys such as `categories`. This skill is standalone: no reviewer MCP, database, or board connection\nis required for the baseline.\n\n## Scope\n\nManage `summary_cluster_depth`, `summary_cluster_depth_overrides`, `summary_topk_threshold`,\n`summary_paths.ignore`, `paths.ignore`, `context_limits`, and the optional `task_board` block,\nincluding its generic `sync_filter`. An empty `task_board:` disables the board for this repository. Never read, request,\ndisplay, or write credential values in either policy target.\n\nTracked branches are separate from review policy. Manage `repository.primary_branch` and\n`repository.index_branches` only in the home per-repo target. The committed `.review.yml` cannot\nown `repository`, because branch selection must be available before a committed ref can be read.\n\nUntracked `.venv`, `node_modules`, `__pycache__`, `dist`, and `build` are gitignored and never\nenter the index. Do not use a filesystem walk to find them.\n\n## Safe YAML preflight\n\nInspect each selected policy or home YAML file with a local boolean-only process.\nRun this preflight before any tool call that can return file contents.\nReturn only safe\u002Fblocked, never matching lines, values, or exception text. Do not use Read or Grep\nto perform this preflight. The process must reject non-regular or symlinked files, malformed or\nnon-mapping YAML, and credential-like keys at any depth. Also reject duplicate mapping keys,\nincluding duplicate `repository` keys and duplicate branch fields. Reject anchors, aliases, and merge keys.\nReject these cases before reading or mutating the file in model context.\nOnly after a safe result may a content-returning tool read the file for a line-oriented edit.\n\nFor a home target, derive the canonical home config root lexically even when it does not exist.\nCheck every existing parent path component through the destination without following symlinks;\nreject symlinks and non-directories. Missing destinations, including a missing home config root,\nare allowed only when the nearest existing parent is a real directory and the normalized\ndestination remains inside the canonical home config root. After creating any missing directories,\nrun the path preflight again. Also re-check immediately before writing so a changed path never\ninherits an earlier safe result.\n\n## Pipeline\n\n1. Resolve the canonical lowercase repository id and the target branch. Present these targets in\n   this order and ask the user to select one:\n   - **Recommended\u002Fdefault:** `home:repos\u002F\u003Cowner>\u002F\u003Cname>.yml`, stored at\n     `$XDG_CONFIG_HOME\u002Frag-reviewer\u002Frepos\u002F\u003Cowner>\u002F\u003Cname>.yml` (or\n     `~\u002F.config\u002Frag-reviewer\u002F...` when `XDG_CONFIG_HOME` is unset). It needs no commit and is not\n     visible to the team.\n   - **Team-visible:** committed `.review.yml` at the selected target ref. It is committed and\n     visible to the team; read it from that ref, never from an uncommitted worktree file.\n   For a nested id such as `group\u002Fservice`, use `home:repos\u002Fgroup\u002Fservice.yml`. A home policy is\n   owned by the OS account running reviewer: on a shared service account it can affect that\n   account's workloads, so use committed policy for team-owned settings.\n2. After the target is selected, verify the repository with `git rev-parse --git-dir`, run the Safe\n   YAML preflight, and only then read the selected file, preserving unrelated keys and comments.\n   Do not inspect or copy credentials.\n3. Scan only tracked Python files:\n   ```bash\n   git -C \u003Cpath> ls-tree -r --name-only \u003Cbranch> | grep '\\.py$'\n   ```\n   Count directory prefixes at depths 1–3. This is not a filesystem walk.\n4. Measure churn with `git log --since=\"6 months ago\" --name-only --pretty=format: -- '*.py'`.\n   If history is too short or unavailable, say so and recommend from structure alone.\n5. Propose depth and ignore changes. Ask the user about every candidate for `paths.ignore` and\n    **never write it silently**. Assemble a draft that preserves the selected file's unrelated\n    keys\u002Fcomments, then request final confirmation before writing it. Follow the exact rebuild map\n   below; suggest but **do NOT run** a follow-up skill. When branch and policy changes share a run,\n   assemble both drafts first, show both paths and diffs, and request one final confirmation before\n   either write.\n\n## Repository branches\n\nHandle branches before policy analysis whenever the user asks to inspect or change tracked\nbranches.\n\n1. Resolve the local repository without network calls:\n   - `git rev-parse --show-toplevel` gives the git root;\n   - `git remote get-url origin` gives the canonical SSH\u002FHTTPS remote candidate;\n   - normalize it to lowercase `\u003Cowner\u002Fname>` with the same SSH\u002FHTTPS forms accepted by reviewer;\n   - if origin is absent or unrecognized, ask for `\u003Cowner\u002Fname>` explicitly.\n   Network git commands are forbidden.\n2. Run `reviewer config show --repo \u003Cowner\u002Fname> --json` and show the effective primary branch,\n   ordered index branches, and source. A policy\u002FVCS diagnostic error does not erase the returned\n   branch section; a malformed home config is a blocking error and must not fall back silently.\n3. Ask for `repository.primary_branch`, then ask for the complete ordered unique\n   `repository.index_branches`. The primary must be present in the index list. Reject empty names,\n   duplicates, and a primary outside the list.\n4. The destination is always\n   `$XDG_CONFIG_HOME\u002Frag-reviewer\u002Frepos\u002F\u003Cowner>\u002F\u003Cname>.yml` (or the equivalent\n   `~\u002F.config\u002Frag-reviewer\u002F...` path when XDG is unset).\n   Never write `repository` to committed `.review.yml`, even when committed policy is selected for\n   other keys. If policy and branches\n   change together, treat them as two targets in one preview.\n5. Run the Safe YAML preflight on the destination before reading it. Stop on every blocked result.\n   Build a line-oriented patch: if `repository` is absent, append the canonical block; if it exists,\n   replace only `primary_branch` and `index_branches`. Preserve all top-level keys and unknown repository subkeys.\n   Preserve comments, line endings, and surrounding YAML style.\n   Never serialize the complete file with `yaml.safe_dump`.\n6. Show the destination, source, old and new branch values, and the exact patch. Request one\n   final confirmation before any branch or policy write. A rejection leaves every target unchanged.\n7. After writing, run `reviewer config show --repo \u003Cowner\u002Fname> --json` again and require the\n   exact primary\u002Findex\u002Fsource expected from the home per-repo layer. Report a mismatch as an error.\n\nIf newly added index branches are not indexed, suggest `rag-reviewer:sync-codebase` once per new\nbranch, but do not run it. A primary change to an already indexed branch needs no rebuild. Removing\na branch stops reviewer from selecting it but does not delete its old base index automatically.\nBranch changes never trigger subsystem-summary work.\n\n## Rebuild guidance\n\n- Changed `paths.ignore` → suggest `rag-reviewer:sync-codebase`.\n- Changed `summary_cluster_depth` → suggest `rag-reviewer:summarize-subsystems`.\n- Changed `summary_cluster_depth_overrides` → suggest `rag-reviewer:summarize-subsystems`.\n- Changed `summary_paths.ignore` → this key is part of the summary `layout_token`; suggest\n  `rag-reviewer:summarize-subsystems` and warn it forces a **full rebuild of every subsystem\n  summary** (same `layout_token` invalidation as `summary_cluster_depth`\u002F\n  `summary_cluster_depth_overrides`).\n- Changed `summary_topk_threshold` → no rebuild needed.\n- Changed `context_limits` → no rebuild needed.\n- Changed `task_board.sync_filter` → suggest `rag-reviewer:sync-tasks` for a full unlimited run\n  (`limit=null`); do **NOT run** it automatically.\n\n## Generic board metadata\n\nAsk whether to keep, disable, or configure `task_board`. A configured block uses only this shape:\n\n```yaml\ntask_board:\n  type: \u003Cregistered board_type>\n  project: \u003Coptional project prefix>\n  key_pattern: '\u003Coptional task-key pattern>'\n  create_target: \u003Cselected target id or null>\n  done_target: \u003Cselected target id or null>\n  options: {}\n  sync_filter:\n    max_age_days: \u003Cinteger >= 1, or omit for no age limit>\n    include_archived: \u003Cboolean, default true>\n```\n\n`project` scopes board sync and task retrieval. Explain that an empty `task_board.project` can mix\nall projects, then ask for the intended project prefix.\n\n`sync_filter` is a generic sibling of provider `options`. The `sync_filter` block is optional.\nNever put `sync_filter` under `options`. Ask two separate questions:\n\n- `max_age_days`: choose an integer greater than or equal to 1, or no age limit.\n- `include_archived`: choose whether archived tasks are included; the default is `true`.\n\nAge uses task last-modified time and an inclusive cutoff: a task modified exactly at the cutoff is\neligible. Archive is distinct from terminal\u002Fdone; `include_archived: false` excludes only tasks\nknown to be archived. Age filtering runs first. Only while `include_archived: false`, unknown\narchive metadata does not itself exclude the row; an archive warning is emitted only then and only\nwhen age filtering did not already exclude the row.\n\n### Editing `sync_filter` safely\n\nWhen changing only `sync_filter`, use this deterministic materialization procedure:\n\n1. Read policy layers in precedence order: non-secret ENV\u002Fdeploy `task_board` defaults,\n   `home:review.yml`, committed `.review.yml`, then `home:repos\u002F\u003Cowner>\u002F\u003Cname>.yml`; stop at the\n   selected target. Never inspect or copy credential env values. For a committed target, do not\n   read the higher repo-home layer. For the recommended home per-repo target, include all layers.\n2. If the selected layer has a non-empty `task_board` mapping, use that mapping alone as the edit\n   base. Preserve every sibling and field-attached comment already present, but do not copy or\n   overlay omitted fields from lower layers: the selected mapping already shadows the complete\n   lower block.\n3. If the selected layer has no `task_board` key, resolve only the lower layers with normal\n   whole-block replacement, then materialize the complete lower effective non-secret `task_board`\n   into the selected-layer draft. Copy `type`, `project`, `key_pattern`, `url_template`,\n   `create_target`, `done_target`, `options`, every other non-secret sibling, and field-attached\n   comments. If no lower board exists, ask for a fully configured board; never write a new partial\n   `task_board` containing only the filter.\n4. If the selected layer explicitly contains null or an empty mapping, preserve that disable and do\n   not add `sync_filter`. Only proceed when the user explicitly chooses to replace it with a fully\n   configured board assembled from confirmed values; never resurrect lower fields silently.\n5. For cases 2 or 3, patch only `sync_filter` in the chosen or materialized block. The selected layer\n   remains a self-contained whole-block replacement.\n\nBecause policy layers replace the whole `task_board` block, preserve every sibling field and\ncomment when changing `sync_filter`. Repositories using the same project share one task corpus, so\ndifferent retention views require different project scopes. Keep home per-repo as the recommended\ntarget for repository-specific policy. A filter change is evaluated on the next successful full\nsync and backfills newly eligible tasks; purge remains explicit and is never enabled by a filter\nchange.\n\nWhen a board type is selected, call the read-only discovery tool:\n\n```\nget_board_targets(board_type=\u003Ctype>, project=\u003Cproject>, provider_options=\u003Ctask_board.options or {}>)\n```\n\nIts normalized response is `{board_type, project, targets, options, warnings}`. Present a\n**pick-list** of `targets` by `label`; use `purposes` to select `create_target` and `done_target`.\nFor every option whose `required_for` contains `sync`, `create`, or `finish`, present its `choices`\nby label and write the selected `id` into `task_board.options`. If discovery is unavailable, empty,\nor returns an error, **fall back to asking** the user for each required generic value. Do not guess\ntargets or options.\n\nThe resulting values are non-secret metadata. Board access is configured outside this file; do not\nrequest, display, or write credentials.\n\n## Retrieval profile\n\nChoose one profile from tracked-file structure and write all real `context_limits` fields:\n\n| Profile | Condition | search_codebase: floor \u002F ceiling \u002F ratio \u002F abs_floor \u002F candidate_pool \u002F ann_distance_max | graph: hops \u002F callers_topk |\n|---|---|---|---|\n| tiny-util | fewer than 80 tracked Python files and one package | 3 \u002F 8 \u002F 0.60 \u002F 0.35 \u002F 20 \u002F 0.65 | 1 \u002F 20 |\n| standard | 80–800 files | 4 \u002F 15 \u002F 0.50 \u002F 0.30 \u002F 30 \u002F 0.65 | 1 \u002F 25 |\n| large \u002F monorepo | over 800 files or at least three large packages | 4 \u002F 25 \u002F 0.45 \u002F 0.30 \u002F 40 \u002F 0.60 | 1 \u002F 30 |\n\nMap `count_tasks(project)` to `search_tasks` deterministically: `\u003C 150` → `3 \u002F 8`;\n`150–800` → `3 \u002F 10`; `800+` → `4 \u002F 14`. A missing tool, zero count, or unavailable corpus\n**falls back to asking** the user for small\u002Fmedium\u002Flarge, then uses the same mapping.\n\n`context_limits.code_section` is the file budget for the task-context `code` section\n(`prepare_task_context`): `max_files: 20`, `max_chunks_per_file: 1`, `chars_per_file: 975`,\n`max_augmented_files: 3`. These four defaults are the same across all three profiles above —\nthere is no measurement backing a per-profile split, so do not invent one. The budget unit here\nis the FILE, not the chunk; there is no separate character-cap key, the effective character\nceiling is derived from `max_files`\u002F`max_chunks_per_file`\u002F`chars_per_file`. `max_augmented_files`\n(PRI-257) is a RESERVE of file slots inside `max_files` for diff paths mixed in from similar\ntasks (`similar-diffs`, the section's only augmentation source) — not a cap applied to whatever\nthe hybrid search leaves over. Write it alongside the other real `context_limits` fields:\n\n```yaml\ncontext_limits:\n  search_codebase:\n    floor: \u003Cprofile value>\n    ceiling: \u003Cprofile value>\n    ratio: \u003Cprofile value>\n    abs_floor: \u003Cprofile value>\n    candidate_pool: \u003Cprofile value>\n    ann_distance_max: \u003Cprofile value>\n  search_tasks:\n    floor: \u003Cboard-size value>\n    ceiling: \u003Cboard-size value>\n  graph:\n    hops: \u003Cprofile value>\n    callers_topk: \u003Cprofile value>\n  code_section:\n    max_files: 20\n    max_chunks_per_file: 1\n    chars_per_file: 975\n    max_augmented_files: 3\n```\n\nPreserve every other configuration key and ask for confirmation before writing the assembled draft.\n\n## Completion\n\nReport old\u002Fnew branches, the selected branch source, changed policy keys, selected generic\ntargets\u002Foptions, and any recommended follow-up. This skill makes configuration-only recommendations\nand has no index side effects.\n","# Configure Review\n\nAlways answer the user in Russian. Update only the requested policy values; **Never clobber** foreign\nkeys such as `categories`. This skill is standalone: no reviewer MCP, database, or board connection\nis required for the baseline.\n\n## Scope\n\nManage `summary_cluster_depth`, `summary_cluster_depth_overrides`, `summary_topk_threshold`,\n`summary_paths.ignore`, `paths.ignore`, `context_limits`, and the optional `task_board` block,\nincluding its generic `sync_filter`. An empty `task_board:` disables the board for this repository. Never read, request,\ndisplay, or write credential values in either policy target.\n\nTracked branches are separate from review policy. Manage `repository.primary_branch` and\n`repository.index_branches` only in the home per-repo target. The committed `.review.yml` cannot\nown `repository`, because branch selection must be available before a committed ref can be read.\n\nUntracked `.venv`, `node_modules`, `__pycache__`, `dist`, and `build` are gitignored and never\nenter the index. Do not use a filesystem walk to find them.\n\n## Safe YAML preflight\n\nInspect each selected policy or home YAML file with a local boolean-only process.\nRun this preflight before any tool call that can return file contents.\nReturn only safe\u002Fblocked, never matching lines, values, or exception text. Do not use Read or Grep\nto perform this preflight. The process must reject non-regular or symlinked files, malformed or\nnon-mapping YAML, and credential-like keys at any depth. Also reject duplicate mapping keys,\nincluding duplicate `repository` keys and duplicate branch fields. Reject anchors, aliases, and merge keys.\nReject these cases before reading or mutating the file in model context.\nOnly after a safe result may a content-returning tool read the file for a line-oriented edit.\n\nFor a home target, derive the canonical home config root lexically even when it does not exist.\nCheck every existing parent path component through the destination without following symlinks;\nreject symlinks and non-directories. Missing destinations, including a missing home config root,\nare allowed only when the nearest existing parent is a real directory and the normalized\ndestination remains inside the canonical home config root. After creating any missing directories,\nrun the path preflight again. Also re-check immediately before writing so a changed path never\ninherits an earlier safe result.\n\n## Pipeline\n\n1. Resolve the canonical lowercase repository id and the target branch. Present these targets in\n   this order and ask the user to select one:\n   - **Recommended\u002Fdefault:** `home:repos\u002F\u003Cowner>\u002F\u003Cname>.yml`, stored at\n     `$XDG_CONFIG_HOME\u002Frag-reviewer\u002Frepos\u002F\u003Cowner>\u002F\u003Cname>.yml` (or\n     `~\u002F.config\u002Frag-reviewer\u002F...` when `XDG_CONFIG_HOME` is unset). It needs no commit and is not\n     visible to the team.\n   - **Team-visible:** committed `.review.yml` at the selected target ref. It is committed and\n     visible to the team; read it from that ref, never from an uncommitted worktree file.\n   For a nested id such as `group\u002Fservice`, use `home:repos\u002Fgroup\u002Fservice.yml`. A home policy is\n   owned by the OS account running reviewer: on a shared service account it can affect that\n   account's workloads, so use committed policy for team-owned settings.\n2. After the target is selected, verify the repository with `git rev-parse --git-dir`, run the Safe\n   YAML preflight, and only then read the selected file, preserving unrelated keys and comments.\n   Do not inspect or copy credentials.\n3. Scan only tracked Python files:\n   ```bash\n   git -C \u003Cpath> ls-tree -r --name-only \u003Cbranch> | grep '\\.py$'\n   ```\n   Count directory prefixes at depths 1–3. This is not a filesystem walk.\n4. Measure churn with `git log --since=\"6 months ago\" --name-only --pretty=format: -- '*.py'`.\n   If history is too short or unavailable, say so and recommend from structure alone.\n5. Propose depth and ignore changes. Ask the user about every candidate for `paths.ignore` and\n    **never write it silently**. Assemble a draft that preserves the selected file's unrelated\n    keys\u002Fcomments, then request final confirmation before writing it. Follow the exact rebuild map\n   below; suggest but **do NOT run** a follow-up skill. When branch and policy changes share a run,\n   assemble both drafts first, show both paths and diffs, and request one final confirmation before\n   either write.\n\n## Repository branches\n\nHandle branches before policy analysis whenever the user asks to inspect or change tracked\nbranches.\n\n1. Resolve the local repository without network calls:\n   - `git rev-parse --show-toplevel` gives the git root;\n   - `git remote get-url origin` gives the canonical SSH\u002FHTTPS remote candidate;\n   - normalize it to lowercase `\u003Cowner\u002Fname>` with the same SSH\u002FHTTPS forms accepted by reviewer;\n   - if origin is absent or unrecognized, ask for `\u003Cowner\u002Fname>` explicitly.\n   Network git commands are forbidden.\n2. Run `reviewer config show --repo \u003Cowner\u002Fname> --json` and show the effective primary branch,\n   ordered index branches, and source. A policy\u002FVCS diagnostic error does not erase the returned\n   branch section; a malformed home config is a blocking error and must not fall back silently.\n3. Ask for `repository.primary_branch`, then ask for the complete ordered unique\n   `repository.index_branches`. The primary must be present in the index list. Reject empty names,\n   duplicates, and a primary outside the list.\n4. The destination is always\n   `$XDG_CONFIG_HOME\u002Frag-reviewer\u002Frepos\u002F\u003Cowner>\u002F\u003Cname>.yml` (or the equivalent\n   `~\u002F.config\u002Frag-reviewer\u002F...` path when XDG is unset).\n   Never write `repository` to committed `.review.yml`, even when committed policy is selected for\n   other keys. If policy and branches\n   change together, treat them as two targets in one preview.\n5. Run the Safe YAML preflight on the destination before reading it. Stop on every blocked result.\n   Build a line-oriented patch: if `repository` is absent, append the canonical block; if it exists,\n   replace only `primary_branch` and `index_branches`. Preserve all top-level keys and unknown repository subkeys.\n   Preserve comments, line endings, and surrounding YAML style.\n   Never serialize the complete file with `yaml.safe_dump`.\n6. Show the destination, source, old and new branch values, and the exact patch. Request one\n   final confirmation before any branch or policy write. A rejection leaves every target unchanged.\n7. After writing, run `reviewer config show --repo \u003Cowner\u002Fname> --json` again and require the\n   exact primary\u002Findex\u002Fsource expected from the home per-repo layer. Report a mismatch as an error.\n\nIf newly added index branches are not indexed, suggest `rag-reviewer:sync-codebase` once per new\nbranch, but do not run it. A primary change to an already indexed branch needs no rebuild. Removing\na branch stops reviewer from selecting it but does not delete its old base index automatically.\nBranch changes never trigger subsystem-summary work.\n\n## Rebuild guidance\n\n- Changed `paths.ignore` → suggest `rag-reviewer:sync-codebase`.\n- Changed `summary_cluster_depth` → suggest `rag-reviewer:summarize-subsystems`.\n- Changed `summary_cluster_depth_overrides` → suggest `rag-reviewer:summarize-subsystems`.\n- Changed `summary_paths.ignore` → this key is part of the summary `layout_token`; suggest\n  `rag-reviewer:summarize-subsystems` and warn it forces a **full rebuild of every subsystem\n  summary** (same `layout_token` invalidation as `summary_cluster_depth`\u002F\n  `summary_cluster_depth_overrides`).\n- Changed `summary_topk_threshold` → no rebuild needed.\n- Changed `context_limits` → no rebuild needed.\n- Changed `task_board.sync_filter` → suggest `rag-reviewer:sync-tasks` for a full unlimited run\n  (`limit=null`); do **NOT run** it automatically.\n\n## Generic board metadata\n\nAsk whether to keep, disable, or configure `task_board`. A configured block uses only this shape:\n\n```yaml\ntask_board:\n  type: \u003Cregistered board_type>\n  project: \u003Coptional project prefix>\n  key_pattern: '\u003Coptional task-key pattern>'\n  create_target: \u003Cselected target id or null>\n  done_target: \u003Cselected target id or null>\n  options: {}\n  sync_filter:\n    max_age_days: \u003Cinteger >= 1, or omit for no age limit>\n    include_archived: \u003Cboolean, default true>\n```\n\n`project` scopes board sync and task retrieval. Explain that an empty `task_board.project` can mix\nall projects, then ask for the intended project prefix.\n\n`sync_filter` is a generic sibling of provider `options`. The `sync_filter` block is optional.\nNever put `sync_filter` under `options`. Ask two separate questions:\n\n- `max_age_days`: choose an integer greater than or equal to 1, or no age limit.\n- `include_archived`: choose whether archived tasks are included; the default is `true`.\n\nAge uses task last-modified time and an inclusive cutoff: a task modified exactly at the cutoff is\neligible. Archive is distinct from terminal\u002Fdone; `include_archived: false` excludes only tasks\nknown to be archived. Age filtering runs first. Only while `include_archived: false`, unknown\narchive metadata does not itself exclude the row; an archive warning is emitted only then and only\nwhen age filtering did not already exclude the row.\n\n### Editing `sync_filter` safely\n\nWhen changing only `sync_filter`, use this deterministic materialization procedure:\n\n1. Read policy layers in precedence order: non-secret ENV\u002Fdeploy `task_board` defaults,\n   `home:review.yml`, committed `.review.yml`, then `home:repos\u002F\u003Cowner>\u002F\u003Cname>.yml`; stop at the\n   selected target. Never inspect or copy credential env values. For a committed target, do not\n   read the higher repo-home layer. For the recommended home per-repo target, include all layers.\n2. If the selected layer has a non-empty `task_board` mapping, use that mapping alone as the edit\n   base. Preserve every sibling and field-attached comment already present, but do not copy or\n   overlay omitted fields from lower layers: the selected mapping already shadows the complete\n   lower block.\n3. If the selected layer has no `task_board` key, resolve only the lower layers with normal\n   whole-block replacement, then materialize the complete lower effective non-secret `task_board`\n   into the selected-layer draft. Copy `type`, `project`, `key_pattern`, `url_template`,\n   `create_target`, `done_target`, `options`, every other non-secret sibling, and field-attached\n   comments. If no lower board exists, ask for a fully configured board; never write a new partial\n   `task_board` containing only the filter.\n4. If the selected layer explicitly contains null or an empty mapping, preserve that disable and do\n   not add `sync_filter`. Only proceed when the user explicitly chooses to replace it with a fully\n   configured board assembled from confirmed values; never resurrect lower fields silently.\n5. For cases 2 or 3, patch only `sync_filter` in the chosen or materialized block. The selected layer\n   remains a self-contained whole-block replacement.\n\nBecause policy layers replace the whole `task_board` block, preserve every sibling field and\ncomment when changing `sync_filter`. Repositories using the same project share one task corpus, so\ndifferent retention views require different project scopes. Keep home per-repo as the recommended\ntarget for repository-specific policy. A filter change is evaluated on the next successful full\nsync and backfills newly eligible tasks; purge remains explicit and is never enabled by a filter\nchange.\n\nWhen a board type is selected, call the read-only discovery tool:\n\n```\nget_board_targets(board_type=\u003Ctype>, project=\u003Cproject>, provider_options=\u003Ctask_board.options or {}>)\n```\n\nIts normalized response is `{board_type, project, targets, options, warnings}`. Present a\n**pick-list** of `targets` by `label`; use `purposes` to select `create_target` and `done_target`.\nFor every option whose `required_for` contains `sync`, `create`, or `finish`, present its `choices`\nby label and write the selected `id` into `task_board.options`. If discovery is unavailable, empty,\nor returns an error, **fall back to asking** the user for each required generic value. Do not guess\ntargets or options.\n\nThe resulting values are non-secret metadata. Board access is configured outside this file; do not\nrequest, display, or write credentials.\n\n## Retrieval profile\n\nChoose one profile from tracked-file structure and write all real `context_limits` fields:\n\n| Profile | Condition | search_codebase: floor \u002F ceiling \u002F ratio \u002F abs_floor \u002F candidate_pool \u002F ann_distance_max | graph: hops \u002F callers_topk |\n|---|---|---|---|\n| tiny-util | fewer than 80 tracked Python files and one package | 3 \u002F 8 \u002F 0.60 \u002F 0.35 \u002F 20 \u002F 0.65 | 1 \u002F 20 |\n| standard | 80–800 files | 4 \u002F 15 \u002F 0.50 \u002F 0.30 \u002F 30 \u002F 0.65 | 1 \u002F 25 |\n| large \u002F monorepo | over 800 files or at least three large packages | 4 \u002F 25 \u002F 0.45 \u002F 0.30 \u002F 40 \u002F 0.60 | 1 \u002F 30 |\n\nMap `count_tasks(project)` to `search_tasks` deterministically: `\u003C 150` → `3 \u002F 8`;\n`150–800` → `3 \u002F 10`; `800+` → `4 \u002F 14`. A missing tool, zero count, or unavailable corpus\n**falls back to asking** the user for small\u002Fmedium\u002Flarge, then uses the same mapping.\n\n`context_limits.code_section` is the file budget for the task-context `code` section\n(`prepare_task_context`): `max_files: 20`, `max_chunks_per_file: 1`, `chars_per_file: 975`,\n`max_augmented_files: 3`. These four defaults are the same across all three profiles above —\nthere is no measurement backing a per-profile split, so do not invent one. The budget unit here\nis the FILE, not the chunk; there is no separate character-cap key, the effective character\nceiling is derived from `max_files`\u002F`max_chunks_per_file`\u002F`chars_per_file`. `max_augmented_files`\n(PRI-257) is a RESERVE of file slots inside `max_files` for diff paths mixed in from similar\ntasks (`similar-diffs`, the section's only augmentation source) — not a cap applied to whatever\nthe hybrid search leaves over. Write it alongside the other real `context_limits` fields:\n\n```yaml\ncontext_limits:\n  search_codebase:\n    floor: \u003Cprofile value>\n    ceiling: \u003Cprofile value>\n    ratio: \u003Cprofile value>\n    abs_floor: \u003Cprofile value>\n    candidate_pool: \u003Cprofile value>\n    ann_distance_max: \u003Cprofile value>\n  search_tasks:\n    floor: \u003Cboard-size value>\n    ceiling: \u003Cboard-size value>\n  graph:\n    hops: \u003Cprofile value>\n    callers_topk: \u003Cprofile value>\n  code_section:\n    max_files: 20\n    max_chunks_per_file: 1\n    chars_per_file: 975\n    max_augmented_files: 3\n```\n\nPreserve every other configuration key and ask for confirmation before writing the assembled draft.\n\n## Completion\n\nReport old\u002Fnew branches, the selected branch source, changed policy keys, selected generic\ntargets\u002Foptions, and any recommended follow-up. This skill makes configuration-only recommendations\nand has no index side effects.\n",{"name":5,"description":7},"main","2b63f856ce19c2a797929cacabd9e0fc936812fa","plugins\u002Fmimfort\u002Frag_for_git\u002Fplugin\u002Fskills\u002Fconfigure-review",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":54,"prompt":64,"zipAvailable":65},[55,58,61],{"tool":56,"command":57},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill configure-review",{"tool":59,"command":60},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill configure-review",{"tool":62,"command":63},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill configure-review","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fmimfort\u002Frag_for_git\u002Fplugin\u002Fskills\u002Fconfigure-review\u002FSKILL.md",true,[],[68,78,86,94,102,110],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":72,"licenseFileUrl":73,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":77},"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":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":72,"licenseFileUrl":82,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":77},"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":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":72,"licenseFileUrl":90,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":77},"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":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":72,"licenseFileUrl":98,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":77},"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":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":72,"licenseFileUrl":106,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":77},"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":111,"name":112,"nameZh":6,"description":113,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":72,"licenseFileUrl":114,"sourceHtmlUrl":115,"categories":116,"keywords":117,"publishedAt":77},"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",[],[]]