ciel-quality-guild

ciel-quality-guild is an agent for Claude Code from jxoesneon/Ciel. It costs 30 tokens per session (463 once invoked), scanned A, original, Apache-2.0.

A set of specialist roles and rules for code quality, debugging, refactoring, end-to-end testing, and API checks.

In plain words
What is it for?
Investigating bugs, refactoring legacy code, writing unit or end-to-end tests, checking API contracts, finding memory leaks, profiling performance, and auditing compliance.
Why use it?
It requires fixes and larger testing changes to be reviewed and verified, helping catch regressions and keep surrounding code maintainable.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

Good fit Investigating bugs, refactoring legacy code, writing unit or end-to-end tests, checking API contracts, finding memory leaks, profiling performance, and auditing compliance.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/jxoesneon/ciel/ciel-quality-guild
Install

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.

Clone the repo
git clone --depth 1 https://github.com/jxoesneon/Ciel

Made for: Claude Code.

Wrote 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.

agentmods badge for ciel-quality-guild

README.md
[![agentmods](https://agentmods.dev/badge/agents/jxoesneon/ciel/ciel-quality-guild.svg)](https://agentmods.dev/agents/jxoesneon/ciel/ciel-quality-guild)
Your own site
<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>
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 463 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 7d ago against content hash 5b90fd23ade1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

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.

agents/ciel-quality-guild.md · 40 lines

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

  1. Testing: E2E (Playwright), Unit/Integration (Vitest/Pytest), and Fuzzing.
  2. Refactoring: Tech-debt reduction, modularity improvements, and pattern alignment.
  3. Debugging: Systematic RCA, memory leak detection, and performance profiling.
  4. 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.
Changes

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.

  1. 7d ago First seen · 40 lines · 30 tokens per session scan A 5b90fd23ade1

Subscribe to this mod's changes

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.