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.
npx agentmods add instructions/systemfsoftware/comment-checker/agents-mdgit clone --depth 1 https://github.com/systemfsoftware/comment-checkerWhat 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 | $0.02265 | $0.02265 |
| Opus 5 | $0.01132 | $0.01132 |
| Sonnet 5 | $0.00453 | $0.00453 |
| Haiku 4.5 | $0.00227 | $0.00227 |
Grade C, and why
comment-checker AGENTS.md scanned grade C with 1 finding 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 yesterday.
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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- Destructive operations (`rm -rf`, dropping databases, deleting migrations). How it starts
The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
A high-quality, mutation-tested Rust implementation of a Claude Code PostToolUse hook that classifies code comments as justified or unnecessary. SOTA engineering: 100% mutation on the core classifier, property-based tests, constitution-aligned, with GitHub releases and npm distribution.
The npm distribution layer uses Effect v4 RC. Never install, import, or pin effect@3.* in the JS side.
Directory map
| Path | What it holds |
|---|---|
crates/ |
Rust core (comment-checker crate) |
npm/packages/comment-checker/ |
JS/npm wrapper (ESM + Effect v4 RC launcher for the Rust binary) |
tests/ |
Integration / F1 tests |
eval/ |
Evaluation corpus |
.github/workflows/ |
CI/release (pnpm + cross-platform Rust) |
Startup Workflow
Before writing code, unconditionally:
- Confirm the working directory (
pwd) and the active task (user or task list). - Read this file — the whole static surface. No other standing reads.
- Run the verification commands below and confirm a healthy baseline; repair failures before adding new scope.
No eager-read mandates: document reads are situational, triggered by the work, never by startup:
README.md— when working in a directory you have not worked in before.ARCHITECTURE.md— when the task changes a module boundary or data flow.- Product/requirements docs — when a decision depends on product intent.
docs/solutions/— when implementing or debugging in an area with documented past solutions.CONCEPTS.md— when orienting to shared domain vocabulary and definitions.
Working Rules
- One task at a time: finish the active task before starting another.
- Verification required: do not claim done without running the verification commands and recording evidence — decisions, bugs, and conventions to the runtime memory system, active work to the task list.
- Stay in scope: do not modify files unrelated to the active task; scope reduction requires explicit user approval.
- Multi-agent: each agent owns a disjoint file set, claims files before editing, never delegates recursively; the root one-shot verification must pass before any agent claims done.
- Git discipline: Master is for releases only and should remain an empty or minimal commit. All work happens on feature branches. Never commit directly to master. Use
git checkout -b feature/...for new work. Rebase or merge only via PRs.
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.
- yesterday First seen · 155 lines · 2,265 tokens per session scan C c1ca2eaf2a6b
comment-checker AGENTS.md is an instructions file published in the GitHub repository systemfsoftware/comment-checker (1 stars, last pushed yesterday), licensed Apache-2.0. It adds 2,265 tokens to every session, about $0.0113 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
navegador CLAUDE.md
Instructions for ConflictHQ/navegador, covering navegador — claude context, what it is, stack, package layout and falkordb connection.
aptu-coder AGENTS.md
AGENTS.md instructions for clouatre-labs/aptu-coder, covering agents.md, project structure, ci runners, commands and observability.
coldstart CLAUDE.md
Instructions for AkashGoenka/coldstart: Lightweight navigation layer for AI agents. Answers one question: which files are relevant to this task? Fast static index over file paths, symbol names, and exports — queried via two operations, find (ranked file paths matched against declared names: filenames, path segments…
codeTree CLAUDE.md
Instructions for ThinkyMiner/codeTree, covering claude.md, what this is, structural analysis tools (13), graph & onboarding tools (10) and supported languages.
aptu-coder src-languages.instructions.md
Instructions for clouatre-labs/aptu-coder, covering languageinfo registration, tree-sitter query strings, handler function signatures, optional fields and kotlin-specific notes.
cc-safe-setup CLAUDE.md
Instructions for yurukusa/cc-safe-setup, covering project rules, safety, code style and git.