Borrowing it
Nothing to install: this file belongs to gcake119/joplin-llm-wiki. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/gcake119/joplin-llm-wiki/main/.agents/skills/knowledge-capture-policy/SKILL.mdgit clone --depth 1 https://github.com/gcake119/joplin-llm-wikiWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/gcake119/joplin-llm-wiki/knowledge-capture-policy)<a href="https://agentmods.dev/skills/gcake119/joplin-llm-wiki/knowledge-capture-policy"><img src="https://agentmods.dev/badge/skills/gcake119/joplin-llm-wiki/knowledge-capture-policy/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/gcake119/joplin-llm-wiki/knowledge-capture-policy"><img src="https://agentmods.dev/badge/skills/gcake119/joplin-llm-wiki/knowledge-capture-policy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00038 | $0.00888 |
| Opus 5.5 | $0.00015 | $0.00355 |
| Sonnet 5.5 | $0.00008 | $0.00178 |
| Haiku 4.5 | $0.00004 | $0.00089 |
Grade A, and why
knowledge-capture-policy scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Knowledge Capture Policy
Use this policy from other skills when a conversation, workflow, debug session, archive, or architecture explanation has produced reusable knowledge. The goal is to create useful pending capture drafts, not to write formal notes automatically.
Tool Boundary
- Use
joplin_brainstormwhen the output is an exploratory note, decision record, debugging lesson, archive summary, or architecture mental model. - Use
joplin_querywhen the output is grounded in an explicit knowledge-base question and should preserve query sources. - Use
joplin_show_captureonly to inspect an existing pending capture. - Use
joplin_confirm_captureonly after the user explicitly confirms that the pending capture should become a formal note. - Do not call joplin_confirm_capture automatically.
- Do not write files directly under
brainstorming/,artifacts/,raw/, orwiki/as a substitute for MCP tools. - If MCP tools are not available, tell the user the MCP server is not loaded and ask them to restart or reload Codex or Cursor after checking MCP config.
Signal Levels
Strong Signal
Create a pending capture draft when the work has reached one of these outcomes:
- A Spectra archive completed and produced durable decisions, spec changes, or verification evidence.
- A debugging session verified a root cause and fix.
- An architecture explanation produced a reusable mental model.
- Brainstorming converged on a decision, rejected alternatives, or next steps.
- A handoff prompt or workflow rule can be reused in future sessions.
Medium Signal
Ask the user whether to create a pending capture when:
- The discussion is valuable but still unresolved.
- The classification between
brainstormingandartifactsis unclear. - The content may contain sensitive context that the user should review first.
- A Spectra proposal or design already exists, but extra rationale may be worth saving separately.
Low Signal
Do not prompt or create a capture for:
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2mo ago First seen · 110 lines · 38 tokens per session scan A 3161cb30ed33
knowledge-capture-policy is a skill published in the GitHub repository gcake119/joplin-llm-wiki (2 stars, last pushed 4mo ago), licensed MIT. It adds 38 tokens to every session and 888 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
karpathy-llm-wiki
Use when building or maintaining a personal LLM-powered knowledge base. Triggers: ingesting sources into a wiki, querying wiki knowledge, linting wiki quality, 'add to wiki', 'what do I know about', or any mention of 'LLM wiki' or 'Karpathy wiki'.
knowit
Persistent, structured project memory for AI coding agents via the Knowit MCP server. Use before planning or editing code to load relevant rules, architecture, decisions, patterns, and conventions; use after finishing work to save durable learnings. Triggers on "remember this", "what are our conventions", "project…
how-we-define-chaos
How Context scores a workspace's chaos, and how to organize notes so it goes down. Use when the user asks you to tidy, organize, clean up or restructure their notes or folders, asks about their chaos score, or when a write or move answer reports the score got messier.
context
Use whenever the user asks about their own work, projects, decisions, people, preferences or past sessions, and before ending any session that produced something worth keeping. The user's Context is their own notes, reached through the context MCP server; this skill says when to read it and how to write back.
grounded-knowledge-workflow
Use Grounded Knowledge Engine to select an isolated workspace, answer from local evidence, resume an explicitly identified project, create an explicit project checkpoint, and retain durable knowledge. Trigger when a user asks about their documents, workspace or client context, previous research, project state…
debrief
Use at the end of a session (or midway through a long one) to deliberately capture what was learned — lessons, decisions, workflows, state changes, and facts — into the knowledge base. The nightly harvest is a safety net for lessons; unless the host opted into KBHARVESTFACTS, /debrief is the only thing that records…