claudecodex

docs-guardian

Documentation freshness, accuracy and coverage checks, plus commit and push guards that resolve the target repository and map outgoing source changes to documentation.

88 on GitHubby xiaolaiv0.3.0ISCupdated 19 days agodeveloper-tools
/

Plugin docs-guardian from marketplace xiaolai in xiaolai/claude-plugin-marketplace. Commands read from the repo's manifest — 19 days ago.

This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.

What it installs

Skills (35)

  • docs-guardian-accuracy-checker

    Deep analysis of documentation accuracy — reads code and docs side by side to find mismatches in API signatures, parameters, return values, examples and behavioral claims, e.g. after a refactor changed signatures. Part of $docs-guardian-audit. Read-only. Not for coverage (use $docs-guardian-coverage

  • docs-guardian-audit

    Full documentation audit — runs the staleness, accuracy, coverage and quality checks (in parallel subagents when available), then writes one report with a fixing plan to .claude/docs-guardian/audit-report.md.

  • docs-guardian-coverage-scanner

    Find undocumented public APIs and compute documentation coverage per file and overall, ranked by severity. Runs standalone via $docs-guardian-coverage or inside $docs-guardian-audit. Read-only. Not for checking existing docs against code (use $docs-guardian-accuracy-checker) or writing docs (use $do

  • docs-guardian-coverage

    Check documentation coverage — find undocumented public APIs and report per-file and overall coverage percentage.

  • docs-guardian-detection

    Detect language and docs framework from markers like package.json and mkdocs.yml.

  • docs-guardian-doc-writer

    Generate or update documentation for undocumented or stale code — reads the source, understands the behavior, and writes docs in the project's documentation framework format. Run by $docs-guardian-generate after the user confirms which symbols to document. Not for auditing docs without changing them

  • docs-guardian-fw-docusaurus

    Docusaurus docs: detection, config parsing, doc root, code-to-doc mapping, template.

  • docs-guardian-fw-mkdocs

    MkDocs docs: detection, config parsing, doc root, code-to-doc mapping, template.

  • docs-guardian-fw-plain-markdown

    Plain Markdown docs: detection, doc root, layout, code-to-doc mapping, template.

  • docs-guardian-fw-sphinx

    Sphinx docs: detection, config parsing, doc root, code-to-doc mapping, template.

  • docs-guardian-fw-vitepress

    VitePress docs: detection, config parsing, doc root, code-to-doc mapping, template.

  • docs-guardian-generate

    Generate missing documentation — find coverage gaps, confirm the symbols with the user, then write docs in the project's framework format. Optional argument: a file or directory to scope to.

  • docs-guardian-init

    Initialize docs-guardian for this project — detect language and doc framework, propose code-to-doc mappings, set commit-hook strictness, and write .claude/docs-guardian/config.json. Optional arguments: language and framework.

  • docs-guardian-lang-generic

    Docs for languages with no dedicated skill: docstrings, API extraction, heuristics.

  • docs-guardian-lang-go

    Go documentation: doc comment conventions, API doc extraction, Go-specific patterns.

  • docs-guardian-lang-python

    Python documentation: docstring conventions, API doc extraction, Python patterns.

  • docs-guardian-lang-rust

    Rust documentation: doc comment conventions, API doc extraction, Rust patterns.

  • docs-guardian-lang-typescript

    TypeScript documentation: doc comment conventions, API doc extraction, TS patterns.

  • docs-guardian-mapping

    Map source files to their docs: which docs cover which code, gaps, doc-to-code links.

  • docs-guardian-quality-rater

    Rate documentation quality — empty sections, TODO markers, broken internal links, missing examples, inconsistent formatting — e.g. before publishing a docs site. Part of $docs-guardian-audit. Read-only. Not for accuracy or coverage (use $docs-guardian-accuracy-checker or $docs-guardian-coverage-scan

  • docs-guardian-staleness-detector

    Detect stale documentation by comparing git timestamps of source files and their mapped doc files — e.g. docs untouched since a major refactor. Runs scripts/docs-guardian/staleness-check.sh, then classifies each stale pair. Part of $docs-guardian-audit. Not for checking whether doc content matches t

  • docs-guardian-standards

    Documentation quality standards: completeness, accuracy, freshness, project rules.

  • detection

    Detect language and docs framework from markers like package.json and mkdocs.yml.

  • fw-docusaurus

    Docusaurus docs: detection, config parsing, doc root, code-to-doc mapping, template.

  • fw-mkdocs

    MkDocs docs: detection, config parsing, doc root, code-to-doc mapping, template.

  • fw-plain-markdown

    Plain Markdown docs: detection, doc root, layout, code-to-doc mapping, template.

  • fw-sphinx

    Sphinx docs: detection, config parsing, doc root, code-to-doc mapping, template.

  • fw-vitepress

    VitePress docs: detection, config parsing, doc root, code-to-doc mapping, template.

  • lang-generic

    Docs for languages with no dedicated skill: docstrings, API extraction, heuristics.

  • lang-go

    Go documentation: doc comment conventions, API doc extraction, Go-specific patterns.

  • lang-python

    Python documentation: docstring conventions, API doc extraction, Python patterns.

  • lang-rust

    Rust documentation: doc comment conventions, API doc extraction, Rust patterns.

  • lang-typescript

    TypeScript documentation: doc comment conventions, API doc extraction, TS patterns.

  • mapping

    Map source files to their docs: which docs cover which code, gaps, doc-to-code links.

  • standards

    Documentation quality standards: completeness, accuracy, freshness, project rules.

Slash commands (5)

  • /docs-guardian:audit

    Full documentation audit — launch staleness, accuracy, coverage, and quality agents in parallel, then synthesize a report with a fixing plan

  • /docs-guardian:coverage

    Check documentation coverage — find undocumented public APIs and report coverage percentage

  • /docs-guardian:generate

    Auto-generate missing documentation — scan for coverage gaps, then write docs in the project's framework format

  • /docs-guardian:init

    Initialize docs-guardian for this project — auto-detect language and doc framework, propose code-to-doc mappings, configure hook strictness

  • /docs-guardian:shared:validate-config

    Shared config validation step — reads and validates docs-guardian config, stops with init instructions if missing.

Subagents (5)

  • accuracy-checker

    Use this agent for deep analysis of documentation accuracy — reads both code and docs to find mismatches in API signatures, parameter descriptions, return values, examples, and behavioral claims, including after a migration or refactor that changed function signatures. Not for measuring how much of

  • coverage-scanner

    Use this agent to find undocumented public APIs and calculate documentation coverage percentage, or to list which public functions lack documentation, ranked by severity. Works standalone via /coverage or as part of a full audit. Not for checking whether existing docs match the code (use accuracy-ch

  • doc-writer

    Use this agent to generate or update documentation for undocumented or stale code, including refreshing a module's docs after it was rewritten. Reads source code, understands behavior, and writes docs in the project's documentation framework format. Not for auditing docs without changing them; the o

  • quality-rater

    Use this agent to rate documentation quality — checks for empty sections, TODO markers, broken links, missing examples, inconsistent formatting, and other quality issues, for example before publishing a docs site. Not for accuracy or coverage problems (use accuracy-checker or coverage-scanner), and

  • staleness-detector

    Use this agent to detect stale documentation by comparing git timestamps between source files and their corresponding doc files, for example to flag docs untouched since a major refactor before a release. Runs staleness-check.sh for mechanical git work, then interprets the results. Not for checking

Hooks (1)

  • PreToolUse

    node "${CLAUDE_PLUGIN_ROOT}/scripts/docs-guardian/commit-guard.js"

View source on GitHub

More from xiaolai/claude-plugin-marketplace

All 19 plugins →

cc-suite

claude

One plugin to bridge and delegate across Claude Code, Codex CLI, and Antigravity — single-source AGENTS.md, shared skills, mirrored hooks and MCP servers, full Claude↔Codex bidirectional delegation (including Codex reading Claude's session history), a Claude→Grok Build delegation lane over ACP, a bounded read-only Claude→Qwen Code review lane (Safe Mode + Plan mode + sandbox, isolated target copies, verified tool boundary), project-scoped advisor agents, opt-in bridging to more coding agents (Grok Build, opencode, Qwen Code, Kimi CLI) via a tool-profile registry, never-stale model selection (the config records the 'latest' policy), a structured diagnostics engine (enabled-tools-aware health checks with verified auto-repair), and a cross-repo sweep that finds every project on the machine cc-suite has bridged and repairs bridge leftovers in one pass — dead MCP registrations, and skills symlinks left pointing at a pruned plugin version, which SessionStart now also re-points on its own. Supersedes cc-bridge and codex-toolkit.

13 skills · 46 commands · hooks

88

tdd-guardian

claudecodex

Enforces strict TDD discipline across unit/integration/e2e/contract lanes — specification-strength levels S1-S6 with property tooling, adversarial spec review before implementation, red receipts proving spec/implementation separation, per-path critical thresholds, 9-format coverage merging, and mutation testing

32 skills · 16 commands · 7 agents · hooks

88

nlpm

claudecodex

Natural-Language Programming Manager — score, check, fix, and test NL artifacts across Claude Code, Codex CLI, and Antigravity. Tier-aware scoring with per-tool overlays. v1.0.0 marks the multi-tool branded release: nlpm:conventions splits into universal floor + per-tool overlays (conventions-claude, conventions-codex, conventions-antigravity); the scoring rubric splits Hooks per tool (the three event vocabularies are not 1:1 mappable); new artifact rows for .codex-plugin/plugin.json, .agents/plugins/marketplace.json, agents/openai.yaml sidecars, gemini-extension.json, LSP, monitors. Standalone Python validator (bin/nlpm-check) remains tool-agnostic and Claude-Code-free for pre-commit hooks and CI.

17 skills · 15 commands · 8 agents · hooks

88

english-buddy

claudecodex

English coaching with configurable on-demand and sampled modes, bounded provider calls, literal-preservation checks and progress reports; the original user prompt remains authoritative.

23 skills · 10 commands · 4 agents · hooks

88

mac-it-guy-pro

claudecodex

Personal IT guy for non-technical macOS users — 12 plain-language commands, 4 agents, observation-first onboarding, a machine profile that retires its own stale beliefs by retesting them, a locked and transactional state writer, a PreToolUse guard that blocks destructive shell commands, a toolbox that turns repeated chores into reusable micro-tools and offers automations you did not know to ask for, learning maps built from your own measurements, and answers in your chosen language while everything on disk stays English. Ships a Codex layout with the same hooks. macOS only. 129 assertions.

8 skills · 12 commands · 4 agents · hooks

88

bureau

claude

Turn AI sessions into a maintained, human-reviewed knowledge base: capture sessions to append-only logbooks, compile into consistency-checked cabinet dossiers gated by trust tiers (proposed → verified → canonical), and render an offline gazette (built by the bundled press). A typed review queue (bureau:review) orders the backlog upstream-first and names the exact action per page (approve / reapprove / confirm / resolve / repair); a human applies decisions one at a time or as a reviewed, content-bound, commit-gated batch (approve --from a manifest, or --all with a warning). Record architecture decisions as MADR ADR pages (bureau:adr) with typed supersedes edges — a superseded decision leaves current fact only once the superseding ADR is content-bound approved (ADR-0006). Delegate the review queue to Codex as your representative (bureau:codex-review): it recommends approve/hold, and where a workspace opts the codex authority into trust_policy it commits under --by codex — an honest machine authority, never a human one (ADR-0007). Bulk-approve the whole backlog in one confirmation (bureau:approve-all): the AI shows the batch and confirms, then hands you the single --by human line to fire yourself — it never signs for you. A deterministic recursion engine tracks claim-level dependencies (rests_on + author-anchored spans) via an append-only decision log, per-span revisions, an early-cutoff gate, and an fsck byte-fixpoint — so changing an upstream claim flags every downstream page for review. A live Engine view (bureau:serve) paints three signals onto the board as you edit — dependency freshness (needs-review/stale), artifact currency (a verified file that drifted out from under a claim), and a convergence trend (is the canon settling or thrashing) — and git-backed versioning renders any past board (build --at), diffs two versions, and pins named snapshots. Enable a crew of specialized agents or author your own. Karpathy LLM-wiki pattern + session provenance + a human rev

4 skills · 18 commands · hooks

88

Similar plugins

Claude API and SDK documentation skill for building LLM-powered applications

19 skills

anthropics/skills 193,780

Agentic QE (external: maintained in proffesor-for-testing/agentic-qe, pinned to v3.15.17): a quality-engineering fleet with 11 QE agents, 9 skills, 9 commands, the agentic-qe MCP server pinned to the plugin version, and the aqe-mod guard that refuses destructive operations on AQE learning data

9 skills · 9 commands · 11 agents · 1 MCP server

ruvnet/ruflo 81,589

Generate natively editable PPTX from PDF / DOCX / URL / Markdown — real DrawingML shapes, text boxes, charts, and animations. Note: run `pip install -r requirements.txt` inside the installed plugin directory for the Python post-processing scripts to work.

1 skill

hugohe3/ppt-master 76,375

context7

claudecodex

Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.

1 MCP server

upstash/context7 64,709

slidev

claude

Claude Code skill for creating and presenting Slidev slidedecks

1 skill

slidevjs/slidev 49,452

Maintain docs-guardian?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins19 plugins