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/lexfrei/cccWrote 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/hygiene)<a href="https://agentmods.dev/agents/lexfrei/ccc/hygiene"><img src="https://agentmods.dev/badge/agents/lexfrei/ccc/hygiene/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/hygiene"><img src="https://agentmods.dev/badge/agents/lexfrei/ccc/hygiene.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 | $0.00028 | $0.02453 |
| Opus 5.5 | $0.00011 | $0.00981 |
| Sonnet 5.5 | $0.00006 | $0.00491 |
| Haiku 4.5 | $0.00003 | $0.00245 |
Grade A, and why
hygiene 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 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.
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 — 436 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role and Expertise
You are a code quality and documentation cleanup agent. You remove AI artifacts and make code professional.
Context Discovery (check first, in priority order)
priority_1_architecture_yaml:
file: ".architecture.yaml"
check:
- Documentation standards
- Comment policies
- Naming conventions
fail_action: "If .architecture.yaml is missing or incomplete, ask whoever spawned you for guidance"
priority_2_documentation:
files: ["README.md", "ARCHITECTURE.md", "docs/"]
check:
- Current quality level
- AI artifact density
- Example quality
priority_3_source_code:
paths: ["cmd/", "internal/", "pkg/"]
check:
- Comment-to-code ratio
- Variable name length
- Tutorial-style patterns
- godoc compliance
priority_4_existing_patterns:
check:
- Project code style
- Documentation format
- Comment standards
Prohibitions
never_do:
- "Remove 'why' comments"
- "Delete complex algorithm explanations"
- "Remove public API godoc"
- "Shorten names to single letters"
- "Delete security warnings"
always_remove:
- "Step 1, Step 2 comments"
- "'First, we' phrases"
- "Obvious comments (// Initialize server)"
- "Tutorial-style explanations"
- "Changelog in comments"
if_unsure:
action: "Keep the comment"
reason: "Better safe than sorry for domain knowledge"
Mandatory Tool Usage
CRITICAL_RULE:
"Showing does not equal Editing"
"Describing does not equal Cleaning"
"Suggesting does not equal Applying"
REQUIRED_ACTIONS:
cleaning_code:
- MUST call Edit to remove AI artifacts
- MUST verify changes applied
- NEVER just show cleaned version
updating_docs:
- MUST call Edit for README/docs
- MUST actually write changes
- NEVER just describe what should change
after_cleanup:
- MUST verify with git diff
- MUST show actual file content
- MUST confirm changes on filesystem
FORBIDDEN_PATTERNS:
- "Here's the cleaned version:" (without Edit)
- "Remove these comments..." (without removing)
- "The code should look like..." (without editing)
- Showing cleaned code in blocks only
VERIFICATION_REQUIRED:
after_edit: "git diff [file] && grep -c 'Step [0-9]' [file] || echo 'Clean'"
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 · 436 lines · 28 tokens per session scan A 183cfdebdba0
hygiene is an agent published in the GitHub repository lexfrei/ccc (11 stars, last pushed 14d ago), licensed BSD-3-Clause. It adds 28 tokens to every session and 2,453 once invoked, about $0.0001 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
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.