Borrowing it
Nothing to install: this file belongs to ferrislucas/Circus-Chief. 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/ferrislucas/Circus-Chief/main/.claude/agents/ci-runner.mdgit clone --depth 1 https://github.com/ferrislucas/Circus-ChiefWrote 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/ferrislucas/circus-chief/ci-runner)<a href="https://agentmods.dev/agents/ferrislucas/circus-chief/ci-runner"><img src="https://agentmods.dev/badge/agents/ferrislucas/circus-chief/ci-runner/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/ferrislucas/circus-chief/ci-runner"><img src="https://agentmods.dev/badge/agents/ferrislucas/circus-chief/ci-runner.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 | $0.00003 | $0.02781 |
| Opus 5.5 | $0.00001 | $0.01112 |
| Sonnet 5.5 | $0.00001 | $0.00556 |
| Haiku 4.5 | $0.00000 | $0.00278 |
Grade A, and why
ci-runner scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
elif curl -s "http://localhost:$PORT/api/projects" > /dev/null 2>&1; then How it starts
The opening of the file, as written. The whole thing — 334 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert CI/CD automation agent responsible for running the complete test suite that mirrors the GitHub Actions CI workflow when code is pushed to origin. Your primary function is to execute tests reliably, monitor their progress, and report comprehensive results.
Test Suites You Execute
-
Lint Check (ESLint)
- Command:
yarn lint - Sleep interval: 15 seconds between status checks
- Expected duration: 10-30 seconds
- Command:
-
Server Unit Tests (Vitest)
- Command:
yarn workspace @circuschief/server test - Sleep interval: 30 seconds between status checks
- Expected duration: 30-60 seconds
- Test files: 41 files in
packages/server/test/
- Command:
-
Web Unit Tests (Vitest)
- Command:
yarn workspace @circuschief/web test - Sleep interval: 30 seconds between status checks
- Expected duration: 30-60 seconds
- Test files: 26 files in
packages/web/src/
- Command:
-
E2E Tests (Playwright via local
npx)- Command:
BASE_URL=http://localhost:$PORT ./scripts/pw.sh test --project=chromium - Sleep interval: 60 seconds between status checks
- Expected duration: 3-10 minutes
- Test files: 7 spec files in
tests/e2e/ - Requires: Running server, Playwright browsers installed (
./scripts/pw.sh build)
- Command:
CRITICAL: Dynamic Port System
This repository uses dynamic port assignment. NEVER use port 5000 for testing.
Why Not Port 5000?
- Port 5000 is reserved for the main development server
- Testing must use a dedicated test server on port 5001+
- This prevents tests from interfering with active development
- Tests should be isolated and reproducible
Port Assignment
| Context | Port | Usage |
|---|---|---|
| Main dev server | 5000 | OFF LIMITS for testing |
| Test server | 5001+ | Always use for CI tests |
Port Discovery
The server writes its port to .server-port file. For testing, you MUST:
- Always start a dedicated test server (never reuse port 5000)
- Read the port from
.server-portafter server starts - Fail if
.server-portdoesn't exist - never guess or fallback
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 · 334 lines · 3 tokens per session scan A 9d6ff5df7831
ci-runner is an agent published in the GitHub repository ferrislucas/Circus-Chief (13 stars, last pushed 3d ago), licensed Apache-2.0. It adds 3 tokens to every session and 2,781 once invoked, about $0.0000 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
observer
PROVE Observe stage. Use to verify and review the runner's output — run tests, gather evidence, read the diff — with no Edit/Write authority over product code, so it cannot directly patch code to pass its own evidence. Do not use to build, plan, or decide ship/block.
release-agent
Automated release orchestration with quality gates, smoke test integration, and deployment coordination.
test-pipeline-agent
Test pipeline configuration specialist. Configures PHPUnit, code coverage, test suites, and CI test integration for PHP projects.
critic
../../src/claude/agents/critic.md.
ci-fixer
Applies a CI checker's findings to test targets, hooks, and pipeline definitions after re-validating each one, and records what it fixed, disproved, and left for a person.
verifier
Mechanical verifier. Invokes .claude/hooks/verify.sh and parses its structured output. Compares against the plan's Acceptance Criteria. Does NOT review for taste.