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 commands/utensils/claudette/commit-changesgit clone --depth 1 https://github.com/utensils/claudetteWhat 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 | $0.00000 | $0.00634 |
| Opus 5 | $0.00000 | $0.00317 |
| Sonnet 5 | $0.00000 | $0.00127 |
| Haiku 4.5 | $0.00000 | $0.00063 |
Grade A, and why
commit-changes 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review all uncommitted changes and create a well-structured commit using conventional commit format.
Steps
-
Pre-flight checks — Ensure the code is ready to commit:
- Detect the project's toolchain from config files (e.g.,
package.json,Makefile,mix.exs,Cargo.toml,pyproject.toml) - Run the project's format command (e.g.,
prettier,mix format,cargo fmt,ruff format) - Run the project's lint command (e.g.,
eslint,mix credo,cargo clippy,ruff check) - Run the project's typecheck command if applicable (e.g.,
tsc --noEmit,mypy,mix dialyzer) - Run the project's test command (e.g.,
jest,mix test,cargo test,pytest) - If any check fails, fix the issues before proceeding
- Detect the project's toolchain from config files (e.g.,
-
Review changes — Understand what's being committed:
- Run
git statusto see all modified/untracked files - Run
git diffto review unstaged changes - Run
git diff --cachedto review already-staged changes - Run
git log --oneline -5to see recent commit style for context
- Run
-
Stage files — Add relevant files to staging:
- Stage files by name (avoid
git add -Aorgit add .) - Do NOT stage files that contain secrets (
.env, credentials, etc.) - If there are unrelated changes, group them into separate logical commits
- Stage files by name (avoid
-
Draft commit message — Use conventional commit format:
- Format:
<type>(<scope>): <description> - Types:
feat,fix,refactor,chore,docs,test,style,perf,ci,build - Scope: the domain or area affected (e.g.,
orders,shipments,auth,api) - Description: concise summary of the "why", not the "what"
- Add a body paragraph if the change is non-trivial, explaining motivation or trade-offs
- Reference GitHub issues when applicable (e.g.,
Closes #123)
- Format:
-
Create the commit — Use a HEREDOC for the message to preserve formatting:
git commit -m "$(cat <<'EOF' type(scope): description Optional body with more context. EOF )" -
Verify — Run
git statusafter committing to confirm success.
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 First seen · 62 lines · 0 tokens per session scan A 27aa0e7e7152
commit-changes is a command published in the GitHub repository utensils/claudette (75 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 634 tokens. 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 commands, from other repositories
test-feature
Test a React Native feature on the running simulator/emulator. Verifies UI, user flows, and internal state. Generates a persistent Maestro test file.
dispatcher
Pick the next-best repo to work on across the portfolio — rank free repos, recommend one, claim its lease atomically, and route to the entry command.
journey-audit
Outside-in product audit as a deep session — 7 read-only roles check what the site promises against what the code does, what a user experiences, what arrives by mail, and what the data says is used. Writes a dossier; needs a per-repo journey-manifest.
brain-stats
Show claudectl brain learning metrics — accuracy, correction rate, and effectiveness.
cost-tracker
Track session costs, understand token spend, and get optimization tips.
mach12:gh-pr-read
Read a GitHub pull request's title, body, and all top-level PR conversation comments; optionally locate an HTML-marker comment.