bananasjim/openplan-skill/openplan-record

Claude Code and agent skill by bananasjim/openplan-skill

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Organize, update, and reconcile memory and documentation as human goal/intent records in an OpenPlan-style workflow. Use when Codex or Claude Code must classify or propose what belongs in memory, docs, handoff snapshots, review reports, or temporary briefs; when consolidating user preferences, project philosophy, design decisions, workflow constraints, or lessons learned; or when preventing agent inference from being recorded as the human goal/intent. This skill is for goal/intent preservation and documentation maintenance, not code implementation.

Install

npx vskill@latest install bananasjim/openplan-skill/openplan-record

SKILL.md

OpenPlan Record

Use this after $openplan-core when conversation, review, or implementation output needs to become durable memory or documentation.

Core Principle

Memory and docs represent the human goal/intent. Do not record agent guesses as the human goal/intent. If the source is not explicit, mark it as inference or pending confirmation.

Record Types

TypePurposeLifetimeExamples
MemoryStanding human preference or operating constraintLong-lived, compact"Do not checkout without permission", "docs in Chinese"
DocsProject source of truth and rationaleLong-lived, structuredarchitecture, workflow, ADR, conventions
HandoffCross-agent/session continuityShort/medium-livedcurrent objective, blockers, next safe action
ReviewEvidence-backed quality findingSnapshotblocking issue, residual risk
HTML briefTemporary human frontendDisposablevisual summary, teaching page

Update Flow

  1. Classify the information:
  • explicit human goal/intent;
  • agent observation;
  • evidence-backed project fact;
  • temporary session state;
  • unresolved question.
  1. Choose destination:
  • durable preference -> memory;
  • project rule/rationale -> docs;
  • current continuation state -> handoff;
  • quality issue -> review;
  • human-facing visualization -> HTML brief.
  1. Resolve destination root:
  • memory location from platform or user instruction;
  • docs root such as .openplan/, docs/, repo root, separate docs repo, or user-provided path;
  • temporary output path for disposable briefs.
  1. Preserve provenance:
  • source statement or artifact;
  • date/session when useful;
  • confidence;
  • scope.
  1. Deduplicate before adding.
  2. Mark stale or superseded entries instead of silently overwriting when history matters.
  3. Before changing durable goal/intent from ambiguous input, ask only if this agent is the human-facing coordinator; otherwise report Human decisions required.

Memory Rules

  • Keep memory short and operational.
  • Record only stable preferences, constraints, and project-level lessons.
  • Do not store transient task progress in memory.
  • Do not store secrets.
  • Do not inflate memory with explanations that belong in docs.
  • If a memory contradicts current docs, report the conflict instead of choosing silently.

Docs Rules

  • Docs carry rationale, structure, and shared project truth.
  • Separate stable docs from drafts.
  • Design/rationale changes need a decision record in projects that use decision records.
  • Do not rewrite docs just to mirror conversation unless the human goal/intent is clear.
  • Prefer references over duplicated content.
  • Keep docs readable by a zero-context future agent or human.
  • Treat docs paths as relative to the selected docs root. Do not assume project root.

Output

When asked to update records, produce:

markdown
Record classification:
Proposed destination:
Destination root:
Source evidence:
Exact update:
Requires human confirmation: yes/no
Staleness/conflict notes:

If editing is authorized, make the narrowest update and report the changed path.

Use $openplan-garden before broad documentation cleanup, and use it after cleanup when zero-context readability matters.

References

  • references/record-policy.md: detailed memory/docs decision policy.
  • references/update-contract.md: update proposal and changelog contract.
  • assets/claude-code-command.md: Claude Code prompt seed.

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

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
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/bananasjim/openplan-skill/openplan-record/badge)](https://verified-skill.com/skills/bananasjim/openplan-skill/openplan-record)

Something wrong with this skill or its page? Tell us.