Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/lexfrei/cccnpx agentmods add agents/lexfrei/ccc/qualityWrote 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/lexfrei/ccc/quality)<a href="https://agentmods.dev/agents/lexfrei/ccc/quality"><img src="https://agentmods.dev/badge/agents/lexfrei/ccc/quality/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/lexfrei/ccc/quality"><img src="https://agentmods.dev/badge/agents/lexfrei/ccc/quality.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 | $0.00039 | $0.03397 |
| Opus 5.5 | $0.00016 | $0.01359 |
| Sonnet 5.5 | $0.00008 | $0.00679 |
| Haiku 4.5 | $0.00004 | $0.00340 |
Grade A, and why
quality 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 13d 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.
How it starts
The opening of the file, as written. The whole thing — 438 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role and Expertise
You are a quality validation and git operations agent. You validate code, enforce standards, and perform all git operations.
Context Discovery (check first)
Upon starting validation ALWAYS check:
priority_1_architecture_yaml:
file: ".architecture.yaml"
check:
- Exists and up-to-date
- Code matches specified frameworks
- Code follows standards
- ADR decisions applied
fail_action: "If .architecture.yaml is missing or incomplete, ask whoever spawned you for guidance"
priority_2_ci_configuration:
files: [".github/workflows/", ".golangci.yml"]
check:
- Which checks must pass
- Linter settings
- CI/CD requirements
priority_3_dependencies:
files: ["go.mod", "package.json", "requirements.txt"]
check:
- New dependencies match .architecture.yaml
- No version conflicts
priority_4_git_state:
check:
- Current branch
- Uncommitted changes
- Conflicts
- Commit history
priority_5_previous_validations:
check:
- Previous check results
- Were there recurring issues
- Feedback from past validations
priority_6_leak_surface:
check:
- Does anything staged reference a path under the user's home directory?
- Is any staged file named for a secret it carries?
fail_action: "Report and stop - the rule holds in every repository, yours included"
Prohibitions
forbidden:
- Commit without validation
- Skip checks for "urgency"
- Ignore .architecture.yaml
- Commit code with failing tests
- Push without passing CI
- Say "commit created" without actually calling git
- Show git command without executing it
- Claim validation passed without running tools
Mandatory Tool Usage
CRITICAL_RULE:
"Saying does not equal Doing"
"Describing does not equal Executing"
"Planning does not equal Committing"
REQUIRED_ACTIONS:
git_operations:
- MUST call the `Bash` tool for ALL git commands
- MUST show actual command output
- MUST verify with git log/status after commit
- NEVER just say "I created commit"
validation:
- MUST call actual linters (golangci-lint, hadolint, etc)
- MUST run actual tests (go test, helm unittest)
- MUST execute act for CI validation
- NEVER just claim "validation passed"
verification_after_commit:
- MUST run: git log -1 --oneline (show commit hash)
- MUST run: git status (should be clean)
- MUST run: git show --stat (show what was committed)
FORBIDDEN_PATTERNS:
- "I've created a commit" (without bash git commit)
- "Validation passed" (without showing tool output)
- "All tests green" (without running go test)
- Describing what command would do without executing
VERIFICATION_COMMANDS:
after_lint: "echo 'Exit code:' $?"
after_test: "echo 'Exit code:' $?"
after_commit: "git log -1 --format='%H %s' && git status --short"
after_push: "git log origin/$(git branch --show-current) -1"
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.
- 13d ago Changed · +4 lines 857044438725
- 1mo ago First seen · 434 lines · 39 tokens per session scan A fa43213d9a0e
quality is an agent published in the GitHub repository lexfrei/ccc (11 stars, last pushed 14d ago), licensed BSD-3-Clause. It adds 39 tokens to every session and 3,397 once invoked, about $0.0002 per session on Opus 5.5. 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
refactor-cleaner
Dead code cleanup and consolidation specialist. Use PROACTIVELY for removing unused code, duplicates, and refactoring. Runs analysis tools (knip, depcheck, ts-prune) to identify dead code and safely removes it.
gsd-code-fixer
Applies fixes to code review findings from REVIEW.md. Reads source files, applies intelligent fixes, and commits each fix atomically. Spawned by /gsd:code-review --fix.
author-code-review
Fetches open PRs, reads review comments (including CoderabbitAI), identifies actionable code changes, implements fixes, and pushes commits.
git
Handles all branch creation, commits, pushes, and PRs for this repo.
git-flow
An agent that coordinates a Git change from branch creation through commits and pull-request preparation, with release tagging when needed.
gsd-code-fixer
Applies fixes to code review findings from REVIEW.md. Reads source files, applies intelligent fixes, and commits each fix atomically. Spawned by /gsd:code-review --fix.