Borrowing it
Nothing to install: this file belongs to moberghr/mtk-agent-toolkit. 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/moberghr/mtk-agent-toolkit/main/.claude/skills/claude-md-capture/SKILL.mdgit clone --depth 1 https://github.com/moberghr/mtk-agent-toolkitWrote 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/moberghr/mtk-agent-toolkit/claude-md-capture)<a href="https://agentmods.dev/skills/moberghr/mtk-agent-toolkit/claude-md-capture"><img src="https://agentmods.dev/badge/skills/moberghr/mtk-agent-toolkit/claude-md-capture/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/moberghr/mtk-agent-toolkit/claude-md-capture"><img src="https://agentmods.dev/badge/skills/moberghr/mtk-agent-toolkit/claude-md-capture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Agent Snooping · line 115 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
- medium Agent Snooping · line 158 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00043 | $0.02045 |
| Opus 5 | $0.00022 | $0.01022 |
| Sonnet 5 | $0.00009 | $0.00409 |
| Haiku 4.5 | $0.00004 | $0.00204 |
Grade A, and why
claude-md-capture 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 yesterday.
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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md Capture
Current Targets
echo "--- Writable CLAUDE.md files ---"
{ find . -maxdepth 6 -name CLAUDE.md -not -path "./.git/*" -not -path "*/node_modules/*" 2>/dev/null; } | sort -u
echo "--- Personal (gitignored) ---"
test -f .claude.local.md && echo ".claude.local.md (present)" || echo ".claude.local.md (absent — create for personal-only notes)"
echo "--- Line budget of root CLAUDE.md ---"
test -f CLAUDE.md && echo "CLAUDE.md: $(wc -l < CLAUDE.md) lines (root cap 120)" || echo "(no root CLAUDE.md — run /mtk-setup first)"
Overview
A session often surfaces context that CLAUDE.md was missing — a build command you had to discover, a gotcha you hit, an env quirk, a pattern the codebase follows. That knowledge should compound into project memory so the next session starts where this one ended. This skill reflects on the finished session, drafts minimal additions, shows them as diffs, and applies only what the engineer approves.
It is distinct from its two siblings:
claude-md-auditre-grades what is already in CLAUDE.md against a rubric and fixes rot. Capture adds new knowledge this session produced.correction-capturerecords engineer corrections as reusable lessons inlessons.md. Capture records project facts (commands, gotchas, env) into CLAUDE.md — the prompt every session loads.
It honors S1.5 (CLAUDE.md is protected): append-only by default, Edit never
Write, no additions applied before approval.
When To Use
- At the end of a session that revealed context CLAUDE.md was missing
- When the engineer says "save what we learned", "update CLAUDE.md", "remember this for next time", or invokes the equivalent end-of-session capture
- After discovering a non-obvious command, env requirement, or codebase pattern that future sessions will need
When NOT To Use
- First-time repo setup — use
/mtk-setup(runssetup-bootstrap) - Mid-task — capture at a natural stopping point, not while work is in flight
- Re-grading or fixing stale content — use
claude-md-audit - Recording an engineer correction — use
correction-capture(writes a lesson, not a CLAUDE.md fact) - The session surfaced nothing durable — say so and stop. Do not manufacture additions to look useful.
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.
- yesterday Changed 753a1dcf7bdb
- 10d ago First seen · 189 lines · 43 tokens per session scan A 8939ee547bd9
claude-md-capture is a skill published in the GitHub repository moberghr/mtk-agent-toolkit (7 stars, last pushed today), licensed MIT. It adds 43 tokens to every session and 2,045 once invoked, about $0.0002 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
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
shellm
Reference for the shellm system — recursive LLM shell, identity management, memory, skills, trajectory, and all CLI tools. Use when working on shellm itself, debugging agent behavior, or understanding how the pieces fit together.