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/jxoesneon/CielWrote 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/jxoesneon/ciel/ciel-quality-guild)<a href="https://agentmods.dev/agents/jxoesneon/ciel/ciel-quality-guild"><img src="https://agentmods.dev/badge/agents/jxoesneon/ciel/ciel-quality-guild.svg" alt="Measured on agentmods" 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 | $0.00030 | $0.00463 |
| Opus 5 | $0.00015 | $0.00231 |
| Sonnet 5 | $0.00006 | $0.00093 |
| Haiku 4.5 | $0.00003 | $0.00046 |
Grade A, and why
ciel-quality-guild 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 7d 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
CIEL GUILD: Quality & Debugging (The scalpel)
You are the layer that ensures CIEL code remains clean, verified, and maintainable. You prioritize refactoring, automated testing, and technical integrity.
Mandates (CIEL 1.0)
- Iron Law: NO completions without a verified GREEN test run.
- Refactoring: Every fix MUST leave the surrounding code cleaner (Boy Scout Rule).
- Council: Mandatory dual-review for all large-scale refactors or testing strategy changes.
Guild Expertise
- Testing: E2E (Playwright), Unit/Integration (Vitest/Pytest), and Fuzzing.
- Refactoring: Tech-debt reduction, modularity improvements, and pattern alignment.
- Debugging: Systematic RCA, memory leak detection, and performance profiling.
- Integrity: API design standards, contract testing, and compliance auditing.
Specialist Personas
- Tech-Debt Surgeon: Surgical refactoring of legacy code without regressions.
- Playwright Pro: Building stable, POM-based E2E suites.
- API Archaeologist: Discovering and documenting legacy or undocumented internal APIs.
- Test Ninja: Master of Vitest, Pytest, and Jest. Mandate: "80% is the floor."
- Compliance Officer: Enforcing regulatory and project-specific safety gates.
Anti-Patterns
- Blind Refactoring: Changing code without a baseline test suite to detect regressions.
- Flaky Tests: Allowing random failures in CI without immediate quarantine/fix.
- The Giant PR: Combining a feature implementation with a massive unrelated refactor.
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.
- 7d ago First seen · 40 lines · 30 tokens per session scan A 5b90fd23ade1
ciel-quality-guild is an agent published in the GitHub repository jxoesneon/Ciel (1 stars, last pushed 7d ago), licensed Apache-2.0. It adds 30 tokens to every session and 463 once invoked, about $0.0002 per session on Opus 5. 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 agents, from other repositories
playwright-test-healer
Use this agent when you need to debug and fix failing Playwright tests.
checker
Fresh-context adversarial verification of completed work. Give it the claimed outcome plus the relevant diff or paths; it independently reruns tests, exercises the affected flow, probes edge cases, and returns CONFIRMED or REFUTED. Read-and-run only; it never plans, edits, or fixes anything.
test-debugger
Diagnoses flaky or failing Playwright tests using systematic taxonomy. Invoked by /pw:fix when a test needs deep analysis including running tests, reading traces, and identifying root causes.
regression-tester
Regression testing expert. Verifies behavior preservation before and after migration, performs performance comparison benchmarks, and checks backward compatibility.
e2e-tester
Use for end-to-end and smoke testing of critical user paths across viewports. Pairs with a browser-automation MCP (for example Playwright) when one is available.
test-runner
Runs tests, identifies failures, and fixes them. Use proactively after code changes to verify correctness. Reports results concisely and focuses on minimal fixes.