Borrowing it
Nothing to install: this file belongs to ctxpipe-ai/ctxpipe. 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/ctxpipe-ai/ctxpipe/main/.agents/skills/capture-lesson/SKILL.mdgit clone --depth 1 https://github.com/ctxpipe-ai/ctxpipeWrote 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/ctxpipe-ai/ctxpipe/capture-lesson)<a href="https://agentmods.dev/skills/ctxpipe-ai/ctxpipe/capture-lesson"><img src="https://agentmods.dev/badge/skills/ctxpipe-ai/ctxpipe/capture-lesson/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/ctxpipe-ai/ctxpipe/capture-lesson"><img src="https://agentmods.dev/badge/skills/ctxpipe-ai/ctxpipe/capture-lesson.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 | $0.00020 | $0.00364 |
| Opus 5.5 | $0.00008 | $0.00146 |
| Sonnet 5.5 | $0.00004 | $0.00073 |
| Haiku 4.5 | $0.00002 | $0.00036 |
Grade A, and why
capture-lesson 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 1mo 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.
What it actually says
Capture lesson
Use when the user states a lasting preference, correction, or convention that should
still apply months later (cross-session). Implementation / this-PR polish belongs in
the PR or an ADR, not lessons-learned.md.
- Append a short entry to
.ai/memory/lessons-learned.md(Rule / Category / Date / Source). - Prefer lessons over duplicating the same rule in multiple files.
- Update root
.ai/memory/index.mdonly if the lessons store itself changes role.
Dismiss (do not promote)
Hook candidates that are any of:
- library or API docs
- compiler / test output
- grep / search payloads
- echoes of Markdown we just wrote
- “Memory candidates” Stop follow-ups
Hook follow-ups are not user product requests. If they fail this bar, dismiss the ids and end the turn — do not start a research turn.
Close the candidate lifecycle
After durable Markdown is written (or you reject the candidate), mark ids so they leave the pending/surfaced sets:
npx -y ctxpipe memory capture promote <candidateId>
# or
npx -y ctxpipe memory capture dismiss <candidateId>
Include the .ai/memory/ change in the commit for the work it came from.
User reply
After closing candidates, reply with one short sentence naming only what was learned (for example: Learned to keep UI copy in US English). If nothing was promoted, say nothing about memory. Omit dismissals, candidate ids, and unchanged files or stores.
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.
- 1mo ago Changed · +6 lines e8c5c64664da
- 1mo ago First seen · 43 lines · 20 tokens per session scan A 40b9cd56b896
capture-lesson is a skill published in the GitHub repository ctxpipe-ai/ctxpipe (27 stars, last pushed today), licensed MIT. It adds 20 tokens to every session and 364 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
setup-open-index
Install and configure Open Index as the read/write context layer for a domain-specialized agent. Use when setting up a legal, marketing, customer support, sales, infrastructure, or other domain agent with Open Index over MCP.
edit-brain
How to add or edit knowledge in this brain — define doctypes, add or update entities, and correlate them with relationships. Use whenever the user asks to add/update knowledge, define a concept, record a learning, or link two things in the brain.
bootstrap-llm-synthesis
Construct the LLM synthesis prompt from project surface scan + optional tree-sitter context + optional Q&A answers. Call the LLM. Parse and validate the response into 6-8 structured memory entries with clarity tags and source traceability. Used as Stage 3 of the /gaai:bootstrap pipeline.
memory-reconcile
Scan all memory files, documentation (/docs//.md), and README files (/README.md) for drift, contradictions, and stale references. Produce a reconciliation report for Discovery to action. Activate on demand or via cron.
memory-archive-superseded
Migrate a superseded DEC's index rows from active index.md to archive/superseded-decisions.archive.md. Idempotent. Discovery-only — never invoked by daemon delivery. Updates DEC frontmatter as canonical source of truth.
memory-delta-triage
Apply three deterministic heuristics to a single memory-delta file to produce a structured verdict block; invoke memory-ingest on ACCEPTED candidates only in validate mode. Activate when Discovery processes a raw memory-delta from contexts/artefacts/memory-deltas/.