bananasjim/openplan-skill/openplan-garden
Claude Code and agent skill by bananasjim/openplan-skill
- community
Checking that the SKILL.md file is still in the repository.
Inspect and improve documentation quality using OpenPlan-style document gardening. Use when Codex or Claude Code must check memory, docs, design notes, handoff snapshots, review reports, specs, or generated documentation for goal/intent drift, broken structure, missing rationale, stale claims, duplicated content, unclear authority, poor future-agent readability, zero-context comprehension gaps, or periodic documentation maintenance. This skill is platform-neutral and read-only by default; local link checkers and linters are optional evidence sources, not required gates.
Install
npx vskill@latest install bananasjim/openplan-skill/openplan-gardenSKILL.md
OpenPlan Garden
Use this after $openplan-core for document quality, periodic documentation maintenance, and semantic drift inspection. Garden is about preserving the clarity of human goal/intent over time.
Core Rule
Garden first reports. It does not rewrite durable docs or memory unless the user explicitly asks for a cleanup/edit pass.
What Garden Checks
- Goal/intent clarity: can a future human or agent tell why this exists?
- Authority clarity: is this source of truth, draft, handoff, review, or temporary brief?
- Layer clarity: does it mix goal/intent, design, spec, implementation, and review without labels?
- Rationale: are decisions explained, not just stated?
- Staleness: are time-sensitive or superseded claims marked?
- Duplication: is content copied where a reference would work?
- Traceability: are important claims tied to sources or evidence?
- Zero-context readability: can a competent reader understand it without the chat?
- Human-decision boundary: does it record human decisions separately from agent suggestions?
- Next-action clarity: does it say what should happen next, if anything?
Periodic Garden Pass
Use garden as the periodic documentation cleanup workflow. A periodic pass checks:
- stale or superseded documents;
- duplicated rationale that should become references;
- missing or unclear authority labels;
- memory/docs conflicts;
- abandoned TODOs or unresolved questions;
- research/review/handoff artifacts that should be archived, promoted, or left alone;
- docs that no longer pass zero-context comprehension.
Garden first reports proposed cleanup. It may edit only when the user explicitly asks for a cleanup pass, and durable goal/intent changes still require $openplan-record and human confirmation through the human-facing coordinator.
Workflow
- Identify document type: memory, design, decision, spec, handoff, review, tutorial, temporary brief.
- Identify the docs root when a whole documentation surface is being reviewed.
- Load only the document and directly referenced context needed to judge it.
- Run optional deterministic checks if available and safe.
- Apply
references/checklist.md. - Report findings using
references/report-contract.md. - If the user requests cleanup, use
$openplan-recordbefore editing durable memory/docs. - For periodic maintenance, separate safe mechanical cleanup from human-owned meaning changes.
Docs Root
Garden can operate on any docs root: .openplan/, docs/, repo root, a separate docs repo, or a path supplied by the user. Treat document-map paths as relative to the selected root. If the root is ambiguous, report the ambiguity before scanning broadly.
Severity
G0: misleading human goal/intent, wrong source of truth, or future agent likely to act incorrectly.G1: missing rationale, stale unmarked claim, authority/layer confusion, or broken decision boundary.G2: duplicated content, weak traceability, incomplete next action, or zero-context readability gap.G3: wording, formatting, title, or navigation improvement.
Optional Checks
Use deterministic tools only when available:
- markdown link check;
- local docs linter;
- grep for TODO/stale/duplicate markers;
- template section checks.
If not available, continue with semantic review and state checks not run.
Claude Code
Use assets/claude-code-command.md as a slash command or prompt seed.
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/openplan-garden/SKILL.md
Popularity
- 7-day trend score
- 0
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/bananasjim/openplan-skill/openplan-garden)