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 agents/actionhero/keryx/pr-preflightgit clone --depth 1 https://github.com/actionhero/keryxWhat 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 | $0.00468 |
| Opus 5 | $0.00000 | $0.00234 |
| Sonnet 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 2d 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.
- 2d ago First seen · 71 lines · 0 tokens per session scan A 1d2d0b51977f
pr-preflight is an agent published in the GitHub repository actionhero/keryx (33 stars, last pushed 10d 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
switchboard
This project uses the Switchboard protocol for cross-IDE agent collaboration.
tool-developer
Builds new UEFN Toolbelt tools autonomously. Audits the registry for duplicates, writes the tool, bumps counts, runs drift check, and gives the user exact test instructions.
verse-deployer
Verse codegen and error-fix loop for UEFN Toolbelt. Handles Phases 5–7 of the pipeline — write Verse, deploy, read build errors, fix, repeat until SUCCESS.
docs-impact
Reviews documentation affected by code changes. Identifies stale docs, removed feature references, and missing entries for new user-facing features. Reports findings with specific fixes. Advisory only - does not modify files.
Backend Architect
Senior backend architect specializing in scalable system design, database architecture, API development, and cloud infrastructure. Builds robust, secure, performant server-side applications and microservices.
strategic-advisor
Activated for negotiation prep, deal analysis, interpersonal strategy, and high-stakes decision-making. Combines game theory with psychological awareness.