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.
git clone --depth 1 https://github.com/christopherlouet/claude-baseWrote 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/commands/christopherlouet/claude-base/work-commit)<a href="https://agentmods.dev/commands/christopherlouet/claude-base/work-commit"><img src="https://agentmods.dev/badge/commands/christopherlouet/claude-base/work-commit/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/commands/christopherlouet/claude-base/work-commit"><img src="https://agentmods.dev/badge/commands/christopherlouet/claude-base/work-commit.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 | $0.00000 | $0.00394 |
| Opus 5.5 | $0.00000 | $0.00158 |
| Sonnet 5.5 | $0.00000 | $0.00079 |
| Haiku 4.5 | $0.00000 | $0.00039 |
Grade A, and why
work-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 1mo 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.
What it actually says
WORK-COMMIT Agent
Prepare and perform a clean commit following conventions.
Context
$ARGUMENTS
Goal
Create an atomic, well-documented commit compliant with Conventional Commits. The commit is the last step of the workflow: EXPLORE -> (BRAINSTORM) -> SPECIFY -> PLAN -> TDD -> AUDIT -> COMMIT
Workflow
- Check the repo state (
git status,git diff,git diff --staged) - Run quality checks (tests, lint, typecheck, build)
- Check the consistency of changes (a single subject per commit)
- Check for the absence of sensitive files (.env, credentials, secrets)
- Check for the absence of debug console.log and useless commented-out code
- Determine the type: feat, fix, refactor, test, docs, style, perf, chore
- Write the message:
type(scope): description(< 50 chars, imperative, no period) - Add the relevant files (
git add <files>, check before) - Commit with explanatory body if necessary
Expected output
- Verification: Quality checklist (tests, lint, types)
- Commit: Conventional Commits message with relevant scope
- Confirmation:
git log --oneline -1to verify
Related agents
| Agent | Usage |
|---|---|
/work:work-pr |
Create a PR after commit |
/qa:qa-review |
Review before commit |
/doc:doc-changelog |
Update the changelog |
IMPORTANT: Always check tests and lint before committing.
YOU MUST create atomic commits - one commit = one concern.
NEVER commit sensitive files (.env, credentials, secrets).
NEVER use git add . without checking git status first.
Think hard about the commit message - it will be read by other developers.
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.
- 1mo ago First seen · 50 lines · 0 tokens per session scan A 1ebd031745ee
work-commit is a command published in the GitHub repository christopherlouet/claude-base (5 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 394 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 2026-09-03.
Other commands, from other repositories
cp
Stage, commit, and push the current branch following git governance rules.
undo-commit
Soft-undo the last commit. Restores its changes as staged, leaves working tree intact. Refuses if HEAD is already pushed to a tracked remote.
pull-repos
Pull all repos (parent + marketplace clones + configured project repos).
changelog
Generate a changelog entry from git commits since the last tag using conventional commit format.
deploy
Deploy application with pre/post-deploy checks.
commit
Stage, commit, and optionally ship further. Pass an escalation token (push, pr, merge, squash, squash merge) to skip the prompt. With no token, commits then asks how far to ship. Delegates message format to the atomic-git-discipline skill.