audit-comments

audit-comments is a skill for Claude Code, Codex from JHostalek/dotclaude. It costs 55 tokens per session (2,169 once invoked), scanned A, original, CC0-1.0.

A code-review guide for checking comments, docstrings, and other explanatory text written alongside code. It keeps explanations that record important rules the code cannot show clearly and removes misleading or unnecessary prose.

In plain words
What is it for?
Use it to review comments, API notes, annotations, and documentation directives in a selected part of a codebase. It is useful when cleaning up, updating, or deciding which embedded explanations should remain.
Why use it?
It helps prevent stale comments from confusing maintainers or hiding the system's real behavior. It also avoids leaving useful explanations out simply to make the code shorter.

Skill for Claude CodeCodex

Part of the jhostalek-skills plugin — 32 skills, 12 agents shipped together

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 skills/jhostalek/dotclaude/audit-comments
Any agent
npx skills add JHostalek/dotclaude --skill audit-comments
Clone the repo
git clone --depth 1 https://github.com/JHostalek/dotclaude

Made for: Claude Code, Codex.

Or install jhostalek-skills, the plugin that ships this one along with the rest of its 32 skills, 12 agents.

Wrote 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.

agentmods badge for audit-comments

README.md
[![agentmods](https://agentmods.dev/badge/skills/jhostalek/dotclaude/audit-comments.svg)](https://agentmods.dev/skills/jhostalek/dotclaude/audit-comments)
Your own site
<a href="https://agentmods.dev/skills/jhostalek/dotclaude/audit-comments"><img src="https://agentmods.dev/badge/skills/jhostalek/dotclaude/audit-comments.svg" alt="Measured on agentmods" height="20"></a>
Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,169 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 $0.00055 $0.02169
Opus 5 $0.00028 $0.01085
Sonnet 5 $0.00011 $0.00434
Haiku 4.5 $0.00006 $0.00217

Measured 4d ago against content hash 11162ea20120, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

audit-comments 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 4d 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/audit-comments/SKILL.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

!cat "${CLAUDE_SKILL_DIR}/../shared/audit-workflow.md"

Run as the comments dimension. Comments run last because preceding structure, behavior, and naming edits can invalidate them.

Judge whether comments, docstrings, API documentation embedded beside code, annotations carrying prose, and documentation-only directives preserve the system's intended behavior or obscure it. The desired state is not maximal deletion: code states what it can express clearly; retained prose records consequential information that code and types cannot make reliable enough on their own.

Work top-down

Reconstruct the system before judging individual prose:

  1. Identify components, public and internal boundaries, data/control flows, lifecycle transitions, operational environments, generated surfaces, and the audiences who rely on embedded documentation: maintainers, API consumers, operators, integrators, auditors, or tooling.
  2. Derive the documentation invariants whose loss or distortion could cause wrong behavior: protocol and schema semantics, units and ranges, ordering and concurrency constraints, ownership and cleanup, state transitions, compatibility commitments, safety/security rationale, platform or third-party quirks, irreversible operations, and tool-enforced directives. Add system-specific invariants.
  3. Trace those invariants through declarations, implementations, callers, tests, configuration, schemas, generated output, and primary specifications. Review architecture-wide contradictions and lifecycle drift before local wording.
  4. Find candidates widely across every applicable baseline area, then apply the shared workflow's noise filter. A terse or familiar-looking construct is not proof that its prose is redundant; a detailed comment is not proof that it is valuable.

Do not infer accuracy from naming, types, a framework, helper abstraction, nearby tests, repeated wording, an authoritative tone, or a comment surviving for years. Verify each material claim in its exact call path, version, configuration, lifecycle phase, and audience context. Conversely, do not remove a comment merely because the implementation currently agrees with it: the prose may carry a constraint the implementation alone cannot preserve through future change.

Read the full file on GitHub · 120 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. 4d ago First seen · 120 lines · 55 tokens per session scan A 11162ea20120

Subscribe to this mod's changes

audit-comments is a skill published in the GitHub repository JHostalek/dotclaude (11 stars, last pushed 1mo ago), licensed CC0-1.0. It adds 55 tokens to every session and 2,169 once invoked, about $0.0003 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.