hygiene

A code-cleanup agent for comments, documentation, and names that appear machine-generated. It preserves explanations of complex logic, public API documentation, and security warnings.

In plain words
What is it for?
Use it to review and clean README files, architecture documents, source comments, and identifiers without deleting important explanations.
Why use it?
AI-written code can contain narration, obvious comments, or overly tutorial-like wording that makes a codebase harder to maintain. The agent removes those artifacts while keeping useful documentation.

Agent

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.

agentmods
npx agentmods add agents/lexfrei/ccc/hygiene
Clone the repo
git clone --depth 1 https://github.com/lexfrei/ccc
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,453 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00028 $0.02453
Opus 5 $0.00014 $0.01226
Sonnet 5 $0.00006 $0.00491
Haiku 4.5 $0.00003 $0.00245

Measured 2d ago against content hash 183cfdebdba0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 2d 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.

skills/become/agents/hygiene.md · 436 lines

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'"

Read the full file on GitHub · 436 lines

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. 2d ago First seen · 436 lines · 28 tokens per session scan A 183cfdebdba0

Subscribe to this mod's changes

hygiene is an agent published in the GitHub repository lexfrei/ccc (9 stars, last pushed 2d 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. 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.