Borrowing it
Nothing to install: this file belongs to nirelbaz/promptpit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/nirelbaz/promptpit/main/.claude/commands/pre-pr-check.mdgit clone --depth 1 https://github.com/nirelbaz/promptpitWrote 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/nirelbaz/promptpit/pre-pr-check)<a href="https://agentmods.dev/commands/nirelbaz/promptpit/pre-pr-check"><img src="https://agentmods.dev/badge/commands/nirelbaz/promptpit/pre-pr-check/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/nirelbaz/promptpit/pre-pr-check"><img src="https://agentmods.dev/badge/commands/nirelbaz/promptpit/pre-pr-check.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 | $0.00408 |
| Opus 5.5 | $0.00000 | $0.00163 |
| Sonnet 5.5 | $0.00000 | $0.00082 |
| Haiku 4.5 | $0.00000 | $0.00041 |
Grade A, and why
pre-pr-check 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
Pre-PR quality gate for PromptPit. Run this on your feature branch after implementation is complete, before opening a PR. Chains three checks: code review, adapter correctness verification, and code simplification.
Steps
-
Pre-flight. Verify the branch has changes against main (
git diff origin/main --stat). If no diff, stop. Runnpm test && npm run lint && npm run build— all three must pass before proceeding. If any fail, fix them first. -
Code review. Run
/reviewto do a pre-landing review of the full diff against main. This catches structural issues (SQL safety, race conditions, trust boundaries, enum completeness) and runs the fix-first pipeline. Address all findings before continuing. -
Adapter correctness. Dispatch the AI Stack Expert agent to verify adapter changes against real-world tool behavior. The expert should:
- Read the diff (
git diff origin/main) - For each changed adapter (claude-code, cursor, codex, copilot, standards), verify file paths, field names, and formats match how the tool actually works
- Flag anything that contradicts real tool behavior (wrong config field names, unsupported file locations, incorrect extensions)
- Check MCP config format correctness per-adapter (JSON vs TOML, field names)
- Check rule/skill/agent file naming conventions per-adapter
Skip this step if the diff doesn't touch any files under
src/adapters/,src/commands/install.ts, orsrc/commands/status.ts. - Read the diff (
-
Simplify. Run
/simplifyto review changed code for reuse opportunities, code quality issues, and efficiency problems. This catches duplicated logic, parameter sprawl, and unnecessary work. -
Final verification. Run
npm test && npm run lint && npm run buildone last time to confirm nothing broke during the review fixes. Report the final test count and confirm the branch is ready for PR.
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 · 21 lines · 0 tokens per session scan A 5e2566d9e02d
pre-pr-check is a command published in the GitHub repository nirelbaz/promptpit (6 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 408 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 2026-08-31.
Other commands, from other repositories
commit
A command that examines staged Git changes and proposes a commit message using the Conventional Commits format, such as feat, fix, or docs. Git is a tool for tracking changes to code.
new-sdk-app
Create and setup a new FuXi Agent SDK application.
modernize-transform
Transform one legacy module to the target stack — idiomatic rewrite with behavior-equivalence tests.
setup
Set up Duel Agents routing with your Duel API key.
bump-plugin
Bump changed plugin and marketplace version.
sync
Promote a change's delta specs into the canonical specs, without archiving.