Borrowing it
Nothing to install: this file belongs to actionhero/keryx. 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/actionhero/keryx/main/.claude/agents/pr-preflight.mdgit clone --depth 1 https://github.com/actionhero/keryxWrote 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/agents/actionhero/keryx/pr-preflight)<a href="https://agentmods.dev/agents/actionhero/keryx/pr-preflight"><img src="https://agentmods.dev/badge/agents/actionhero/keryx/pr-preflight/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/agents/actionhero/keryx/pr-preflight"><img src="https://agentmods.dev/badge/agents/actionhero/keryx/pr-preflight.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 | $0.00468 |
| Opus 5.5 | $0.00000 | $0.00187 |
| Sonnet 5.5 | $0.00000 | $0.00094 |
| Haiku 4.5 | $0.00000 | $0.00047 |
Grade A, and why
pr-preflight 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 2mo 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
PR Preflight
Run all pre-merge checks for a Keryx pull request. This agent validates that a branch is ready to merge.
Instructions
Run these checks in order. Stop early and report if a blocking issue is found.
1. Version bump check
Read packages/keryx/package.json and compare the "version" field against the main branch:
git diff main -- packages/keryx/package.json
If the version has NOT been bumped, report this as a blocking issue. Every PR must bump the version (patch for bug fixes, minor for new features).
2. Lint check
Run from the repo root:
bun lint
This runs tsc type checking and biome check across all workspaces. Report any failures.
3. Test check
Run the full test suite:
bun tests
Before running, check for stale bun keryx processes:
ps aux | grep "bun keryx" | grep -v grep
Report any test failures with file paths and error details.
4. Test coverage check
Verify that changed code has corresponding test changes:
git diff main --name-only
If source files in packages/keryx/ or example/backend/ were modified but no test files (__tests__/**) were added or changed, flag this as a warning. Every code change should include tests.
5. Docs sync check
Use the docs-sync agent to check whether documentation needs updating based on the code changes in this branch. Report any findings from that agent.
6. Summary
Provide a final summary table:
| Check | Status | Details |
|---|---|---|
| Version bump | pass/fail | current version |
| Lint | pass/fail | error count if any |
| Tests | pass/fail | pass/fail/skip counts |
| Test coverage | pass/warn | list of uncovered files |
| Docs sync | pass/warn | list of stale docs |
Mark the overall result as Ready to merge or Blocked with the specific issues that need fixing.
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.
- 2mo ago First seen · 71 lines · 0 tokens per session scan A 1d2d0b51977f
pr-preflight is an agent published in the GitHub repository actionhero/keryx (46 stars, last pushed 8d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 468 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 agents, from other repositories
cos-compliance
Use this agent before shipping, merging, or deploying changes. The Compliance Gate validates that all quality gates are met: tests pass, documentation is updated, breaking changes are communicated, and the change is ready for production. Context: User wants to merge a feature branch user: "I think this PR is ready to…
git-commit-assistant
A Git commit agent that splits workspace changes into focused commits and writes Chinese Conventional Commit messages in a required dependency order.
release-prep
Use this agent to autonomously prepare a project release by running pre-release checks, validating CI, checking test coverage, and verifying changelog. Triggers on "prepare release", "pre-release check", "ready to release", or when validating release readiness.
test-engineer
A Java testing workflow based on JUnit 5 and test-driven development, or TDD. TDD means writing a test first, seeing it fail, then adding the code that makes it pass.
tl-test-writer
Team-loop test writer for a regulated work package. Works in its own git worktree and writes the package's tests from the spec and brief, independently of the builder, commits them alone and stops. Use at step 5 of the team loop for regulated packages only. Never writes implementation.
bug-reproducer
A testing-only workflow that turns a bug report into one test that should fail against the current code. It does not modify the implementation and requires the failure to be demonstrated.