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 agentmods add skills/egregore-labs/egregore/commitnpx skills add egregore-labs/egregore --skill commitgit clone --depth 1 https://github.com/egregore-labs/egregoreWhat 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 | $0.00038 | $0.01268 |
| Opus 5 | $0.00019 | $0.00634 |
| Sonnet 5 | $0.00008 | $0.00254 |
| Haiku 4.5 | $0.00004 | $0.00127 |
Grade A, and why
commit 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 2d 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stage changes and commit with a message.
When to invoke
User says: "/commit", "commit this", "stage and commit", "save this change locally"
Not this: sharing your commit with others → /push · opening a pull request → /pr
Message (optional): $ARGUMENTS
Loom routing
Skip this section if your prompt contains LOOM-EXECUTOR — you are the executor; run the skill as specced below. Full protocol: .claude/context/loom.md.
- Resolve:
ROUTE=$(bash bin/loom.sh route commit), thenDECISION_ID=$(printf '%s\n' "$ROUTE" | jq -r '.decision_id // empty'). - If
mode≠delegate, or the user signalled depth ("deep", "think hard",--deep) → run this skill inline as normal. On a depth override, printbash bin/loom.sh footer commit --overrideafter the output and set"override":truein telemetry. - Otherwise delegate: spawn the Agent tool with
subagent_type: "loom-executor",model= the route'stier, prompt =LOOM-DECISION-ID: $DECISION_IDon its own first line, thenLOOM-EXECUTOR: Execute .claude/skills/commit/SKILL.md, plus the user's arguments and any context the spec needs from the session. Print the executor's final output verbatim, then print the output ofbash bin/loom.sh footer commit. - If the spawn fails or the executor's first line is
LOW_CONFIDENCE:— triage the reason: needs-user-interaction or a main-loop-only tool → take over and finish this skill inline (no escalation); genuine uncertainty or failure → reassignROUTE=$(bash bin/loom.sh escalate commit "<reason>"), refreshDECISION_IDfromROUTE, then re-spawn once on the new tier carrying the returned decision ID (sticky for this session). - Telemetry (fire-and-forget):
bash bin/telemetry.sh emit "command" '{"command":"commit","routed":true,"mode":"delegate","model":"<actual>","route_tier":"<table tier>","class":"<class>","escalated":<bool>,"override":<bool>,"source":"<source>"}' 2>/dev/null &
Before anything else
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.
- 2d ago First seen · 120 lines · 38 tokens per session scan A 413fbcf41c00
commit is a skill published in the GitHub repository egregore-labs/egregore (280 stars, last pushed 6d ago), licensed MIT. It adds 38 tokens to every session and 1,268 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 2026-08-30.
Other skills, from other repositories
commit-review
Review staged/unstaged changes and generate grouped, production-grade commit messages following Conventional Commits. Use when the user asks to review changes, write commits, prepare commits, or says "commit", "review changes", or "what did I change".
github-pr-workflow
Prepare a GitHub pull request from a feature branch — branch hygiene, commit shape, title/body, verification notes, screenshots for UI work, and replies to review comments.
submit-pr-from-current-changes
Create a branch, commit existing local changes, push them, and open a pull request. Use when submitting current work as a PR.
ce-commit
Create a git commit with a clear, value-communicating message. Use when the user asks to commit/save staged or unstaged changes with a repo-appropriate message.
commit-history
List recent git commits linked to agent sessions, optionally filtered by branch or repo. Use when the user asks "show agent commits", "what has the agent shipped", "list linked commits", or wants commits with their session context.
conventional-commit
Workflow for generating conventional commit messages following the Conventional Commits specification. MUST be invoked every time a commit is created. Guides construction of standardized commit messages with correct type, scope, description, body, and footer.