Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add ckorhonen/swe-skills --skill capture-knowledgegit clone --depth 1 https://github.com/ckorhonen/swe-skillsWrote 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/ckorhonen/swe-skills/capture-knowledge)<a href="https://agentmods.dev/skills/ckorhonen/swe-skills/capture-knowledge"><img src="https://agentmods.dev/badge/skills/ckorhonen/swe-skills/capture-knowledge/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/ckorhonen/swe-skills/capture-knowledge"><img src="https://agentmods.dev/badge/skills/ckorhonen/swe-skills/capture-knowledge.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 | $0.00097 | $0.01332 |
| Opus 5 | $0.00048 | $0.00666 |
| Sonnet 5 | $0.00019 | $0.00266 |
| Haiku 4.5 | $0.00010 | $0.00133 |
Grade A, and why
swe:capture-knowledge 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 8d 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 — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SWE Capture Knowledge
What This Skill Does
Use this skill to convert implicit repo knowledge into explicit guidance that future agents can follow reliably.
The job is not to summarize the repo. The job is to compare:
- What the repo actually does
- What the existing agent guidance already says
- What high-signal guidance is still missing
Then draft the missing entries and stop for review before writing anything.
When To Use
Use this skill when the user wants to:
- Capture undocumented repo conventions
- Turn repeated implementation patterns into reusable agent guidance
- Find what current rules or skills are missing
- Draft agent-facing guidance updates before saving them
Do Not Use
Do not use this skill for:
- A general repo orientation report with no writing goal
- A broad architecture review that will not produce guidance updates
- A documentation audit for human-facing docs only
- Automatic write-back without an explicit review step
Inputs To Confirm
Before doing deep work, confirm or infer:
- The repo or paths in scope
- Which guidance files count as agent-facing guidance
- Whether the user wants draft-only output or draft-plus-write after approval
- Any write restrictions for where approved entries may be saved
If the scope is missing, ask for the narrowest clarification needed before proceeding.
Instructions
Step 1: Inventory Existing Guidance
Inspect the current agent-facing guidance first, such as:
AGENTS.md,CLAUDE.md, and repo-level workflow docs- Existing skills
- Agent rules, prompts, or operating docs
- Any docs that future agents are expected to follow
Capture what is already documented so you do not restate it later.
Step 2: Inspect Repo Reality
Inspect the codebase, configs, tests, and representative implementations to understand how the repo is actually built and maintained.
Focus on repeated or operationally important patterns such as:
- Architectural boundaries
- Naming and file placement conventions
- Testing and release expectations
- Dependency or package management norms
- Repeated extension points or adapter patterns
- Local rules that override framework defaults
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.
- 8d ago First seen · 216 lines · 97 tokens per session scan A 28e573426a7a
swe:capture-knowledge is a skill published in the GitHub repository ckorhonen/swe-skills (3 stars, last pushed 1mo ago), licensed MIT. It adds 97 tokens to every session and 1,332 once invoked, about $0.0005 per session on Opus 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
watch
File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…
review
5-pass structured code review — correctness, security, performance, readability, consistency.
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.
marshal
Meta-orchestrator that takes any direction — broad, specific, or vague — and autonomously chains skills and context into actionable work. Gathers context from codebase, docs, and memory. Only asks the user when it genuinely cannot proceed. Single-session orchestrator.
wiki
Markdown-first knowledge base where the LLM acts as librarian. Ingests raw sources, compiles and interlinks topic files, self-maintains an index. No vector DB or embeddings required -- uses LLM-native navigation over structured markdown up to 400K words.
design-sync-upload
An uploader for design-system files such as DESIGN.md, tokens, logos, fonts, and images into Claude Design. It can either use an authenticated connection or prepare a folder and guide for manual upload.