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 metagit-ai/metagit-cli --skill metagit-agent-accessgit clone --depth 1 https://github.com/metagit-ai/metagit-cliWrote 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/metagit-ai/metagit-cli/metagit-agent-access)<a href="https://agentmods.dev/skills/metagit-ai/metagit-cli/metagit-agent-access"><img src="https://agentmods.dev/badge/skills/metagit-ai/metagit-cli/metagit-agent-access/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/metagit-ai/metagit-cli/metagit-agent-access"><img src="https://agentmods.dev/badge/skills/metagit-ai/metagit-cli/metagit-agent-access.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 | $0.00060 | $0.01254 |
| Opus 5 | $0.00030 | $0.00627 |
| Sonnet 5 | $0.00012 | $0.00251 |
| Haiku 4.5 | $0.00006 | $0.00125 |
Grade A, and why
metagit-agent-access scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Metagit agent access optimizer
On-demand workflow to make a target repository easy for AI agents to grasp with minimal tokens, using conventions that stay out of the human reading path where possible.
When to use
- User asks to optimize agent access, agent onboarding, or
llms.txt - User wants hidden agent metadata in an existing project
- After adding major CLI/MCP features to a product repo (refresh agent surfaces)
Do not run proactively on every task.
Execution modes
| Mode | When |
|---|---|
| Script first | Default — fast audit + scaffold |
| Subagent | Large/unknown repo or user wants full editorial pass |
1) Script (run first)
Hermes skill_manage installs SKILL.md only — local ./scripts/ paths will not exist.
Prefer the PyPI package path (always available when metagit-cli is installed) or
metagit skills install --skill metagit-agent-access for a full skill tree.
From the target repository root (not necessarily metagit-cli):
SKILL_ROOT="$(python3 -c "import metagit, pathlib; print(pathlib.Path(metagit.__file__).parent / 'data/skills/metagit-agent-access')")"
"$SKILL_ROOT/scripts/optimize-agent-access.sh" . --apply --json
After metagit skills install --skill metagit-agent-access:
"${HERMES_HOME:-$HOME/.hermes}/skills/metagit-agent-access/scripts/optimize-agent-access.sh" . --apply --json
Inline fallback (no scripts)
Run the optimizer Python entrypoint from the installed package:
SKILL_ROOT="$(python3 -c "import metagit, pathlib; print(pathlib.Path(metagit.__file__).parent / 'data/skills/metagit-agent-access')")"
python3 "$SKILL_ROOT/scripts/optimize_agent_access.py" . --json
python3 "$SKILL_ROOT/scripts/optimize_agent_access.py" . --apply --json
If uv is available in the target repo, the shell wrapper is equivalent:
uv run python "$SKILL_ROOT/scripts/optimize_agent_access.py" . --json
Manual audit when scripts cannot run: check for llms.txt, AGENTS.md, docs/agents.md, and
<!-- agent-access:start --> in README; scaffold from $SKILL_ROOT/templates/ only after
dry-run review.
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 133 lines · 60 tokens per session scan A 006f25f48f89
metagit-agent-access is a skill published in the GitHub repository metagit-ai/metagit-cli (3 stars, last pushed today), licensed MIT. It adds 60 tokens to every session and 1,254 once invoked, about $0.0003 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
clawrium-release-announcements
Daily — draft a release blog post, open a PR, iterate on comments until merged.
blog-author
Watch ric03uec/clawrium release tags; draft a short blog post per user-visible feature as a PR against blog/.
release-watcher
Watch upstream Claw releases and clawrium discussions; surface top 3 feature candidates to Devashish via Discord DM for approve/skip.
perseus
Use when you need a bounded, local Perseus context render before an assistant reads project state. Perseus resolves selected workspace inputs such as git, services, sessions, and task notes into markdown. Use for deterministic session starts, workspace audits, and explicit context handoffs.
pypi-release
This skill should be used when releasing tunacode-cli to PyPI. It keeps the existing local release checks, then hands the actual PyPI upload to a GitHub Actions workflow that uses the repository's PYPIAPITOKEN secret.
memory-commit
Use when the user explicitly says "remember this", "save this", "ghi nho", "luu lai", "save for next time", or otherwise asks to persist the immediately preceding context. Captures with the appropriate contexttype (decision, preference, fact, skill, task, conversation) so future sessions can retrieve it accurately.