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-pr)<a href="https://agentmods.dev/commands/christopherlouet/claude-base/work-pr"><img src="https://agentmods.dev/badge/commands/christopherlouet/claude-base/work-pr/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-pr"><img src="https://agentmods.dev/badge/commands/christopherlouet/claude-base/work-pr.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 | $0.00330 |
| Opus 5.5 | $0.00000 | $0.00132 |
| Sonnet 5.5 | $0.00000 | $0.00066 |
| Haiku 4.5 | $0.00000 | $0.00033 |
Grade A, and why
work-pr 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-PR Agent
Creates a complete and well-documented Pull Request.
Context
$ARGUMENTS
Goal
Create a clean PR with a clear description, verified tests, and complete documentation.
Title format: type(scope): concise description
Workflow
- Check the repo state and changes (
git status,git diff main...HEAD) - Run quality checks (tests, lint, build)
- Analyze commits since main and determine the type (feature/fix/refactor)
- Self-review: re-read the diff line by line, explicit names, no debug code
- Write the title (Conventional Commits) and the body (description, changes, tests, checklist)
- Push the branch (
git push -u origin <branch>) - Create the PR with
gh pr create(title, body, labels, reviewers)
Expected output
- PR created: PR URL
- Description: Summary of changes and why
- Tests: Verification that everything passes
- Reviewers: Assigned if applicable
Related agents
| Agent | Usage |
|---|---|
/qa:qa-review |
Self-review before PR |
/work:work-commit |
Prepare commits |
/qa:qa-security |
Security review if applicable |
IMPORTANT: One PR = one single concern. If too varied, suggest splitting.
YOU MUST include a clear description of the "why" in the PR.
NEVER create a PR without having verified that tests pass.
Think hard about the clarity of the description for reviewers.
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 · 47 lines · 0 tokens per session scan A 18b3dfb40b69
work-pr 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 330 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.
pull-repos
Pull all repos (parent + marketplace clones + configured project repos).
deploy
Deploy application with pre/post-deploy checks.
autocommit
Toggle auto git commits on/off for this project. Run without args to see status, or with "on"/"off" to set.
review
Unified review orchestrator — detect changes, dispatch reviewers, validate findings, optionally post GitHub inline comments.
commit-message
Generate a conventional commit message from staged changes.