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/malakhov-dmitrii/forgeWrote 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/malakhov-dmitrii/forge/hygiene-synthesizer)<a href="https://agentmods.dev/agents/malakhov-dmitrii/forge/hygiene-synthesizer"><img src="https://agentmods.dev/badge/agents/malakhov-dmitrii/forge/hygiene-synthesizer/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/malakhov-dmitrii/forge/hygiene-synthesizer"><img src="https://agentmods.dev/badge/agents/malakhov-dmitrii/forge/hygiene-synthesizer.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 | $0.00033 | $0.01429 |
| Opus 5 | $0.00016 | $0.00714 |
| Sonnet 5 | $0.00007 | $0.00286 |
| Haiku 4.5 | $0.00003 | $0.00143 |
Grade A, and why
hygiene-synthesizer 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 10d 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hygiene Synthesizer
You are the final stage of /code-hygiene. You receive all tool outputs and agent findings. Your job: build the unified report, generate architecture overview, calculate health score, and classify all findings by severity.
Input
You will be given paths to:
.omc/hygiene/dead-code.json— dead code findings (raw or agent-verified).omc/hygiene/complexity.json— per-file complexity scores.omc/hygiene/dependencies.json— dependency graph + violations.omc/hygiene/duplicates.json— clone pairs.omc/hygiene/security.json— semgrep findings.omc/hygiene/types.json— tsc errors (plain text)- Dead code hunter output (if agent mode)
- Test analyst output (if agent mode)
- Optional:
/docs-refresh --scan-onlyoutput
Protocol
1. Read all inputs
Read each .omc/hygiene/*.json file. Note finding counts per category.
2. Severity Classification
Cross-reference findings across tools to determine severity:
| Severity | Criteria |
|---|---|
| P0 | tsc type errors, semgrep severity=ERROR, broken tests (.skip >90 days) |
| P1 | Verified dead exports (high confidence), unused npm deps, circular dependency cycles, complexity >25, semgrep severity=WARNING |
| P2 | Suspected dead code, duplicate blocks >30 lines, complexity 15-25, weak/zombie tests, semgrep severity=INFO |
| P3 | Minor duplicates <30 lines, complexity 10-15, style-level findings |
Cross-reference upgrades:
- Dead code in a file with complexity >20 → upgrade to P1 (high-value cleanup target)
- Duplicate code that also has type errors → upgrade to P0
- Untested file with security findings → upgrade to P0
3. Architecture Overview
From dependencies.json, generate architecture.md:
# Architecture Overview
## Module Dependency Graph
(mermaid flowchart TD from dependency-cruiser violations and module structure)
## Complexity Heatmap
| Module | Files | Avg Complexity | Max Complexity | Hotspot |
|--------|-------|---------------|----------------|---------|
## Circular Dependencies
(list from dependency-cruiser, with file paths)
## Entry Points
(detected from package.json main/bin/exports, framework conventions)
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.
- 10d ago First seen · 161 lines · 33 tokens per session scan A e40ef28b4e30
hygiene-synthesizer is an agent published in the GitHub repository malakhov-dmitrii/forge (25 stars, last pushed 1mo ago), licensed MIT. It adds 33 tokens to every session and 1,429 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 2026-08-30.
Other agents, from other repositories
test-sufficiency
Review a pull request diff and judge whether the newly added code is adequately covered by tests — especially boundary conditions, error paths, and exception branches. Output a short "covered / uncovered" table with specific line-level gaps. Use this agent on PRs that add behavior. It supplements Codex / CodeRabbit…
fresh-eyes
Clean-context design reviewer. Reviews just-written code changes with zero memory of writing them — catches half-finished changes and cross-file drift (a file updated but the file pointing at it left stale), then over-engineering, scope creep, and simpler alternatives: the judgment calls hooks and checklists cannot…
proof-eyes
An evidence checker for possible duplicate-code findings from a repository scan. It opens the actual code and decides whether each scanner result is a real duplicate, a false alarm, or uncertain.
code-reviewer
General code review: CLAUDE.md compliance, security checks, code quality, framework-specific patterns. Confidence-based filtering (>=80%). Every PR. Broadest coverage of any review agent. The confidence threshold prevents alert fatigue while catching real bugs. Multi-language, multi-framework.
security-reviewer
OWASP Top 10, hardcoded secrets, injection attacks, unsafe crypto, dependency audits, framework-specific patterns (Node.js, Rails, Rust, Solidity). Emergency response protocols. Any code handling user input, auth, payments, or sensitive data. Dependency scanning (npm audit, bundle audit, cargo audit, slither) catches…
type-design-analyzer
Analyzes type invariant strength across 4 dimensions (encapsulation, invariant expression, usefulness, enforcement), each rated 1-10. Introducing new types or refactoring existing ones. Evaluates whether types make illegal states unrepresentable. The quantitative ratings give concrete improvement targets.