modern-web-guidance-src: Skill for Claude Code

.agents/skills/coherence-auditor/SKILL.md

coherence-auditor is a skill for Claude Code, Codex from GoogleChrome/modern-web-guidance-src. It costs 44 tokens per session (841 once invoked), scanned A, original, Apache-2.0.

A document and repository audit that checks Markdown files, links, unresolved questions, and the state of a Git code repository. Git is the system used to track changes to files.

In plain words
What is it for?
Use it to review documentation changes, answer open questions, check repository cleanliness, and run the project’s coherence audit before committing.
Why use it?
It helps find broken links, inconsistent documentation, unfinished TODOs, and untracked files before a milestone or commit. This reduces the chance of shipping incomplete or cluttered work.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; installed under .agents/ (shared by several agents).

This is GoogleChrome/modern-web-guidance-src's own configuration. It tells Claude Code and Codex how to work on modern-web-guidance-src itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything modern-web-guidance-src configures →

About the project

Modern Web Guidance is a source repository for coding-agent skills that provide web-platform guidance, recommended practices, and browser compatibility information. It helps coding agents choose newer web APIs and patterns when generating web applications. The catalogue skills are the guidance produced and maintained by this project.

GoogleChrome/modern-web-guidance-src · 1,020 stars · on GitHub · goo.gle

Reuse

Borrowing it

Nothing to install: this file belongs to GoogleChrome/modern-web-guidance-src. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/GoogleChrome/modern-web-guidance-src/main/.agents/skills/coherence-auditor/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/GoogleChrome/modern-web-guidance-src

Made for: Claude Code, Codex.

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 coherence-auditor

README.md
[![agentmods](https://agentmods.dev/badge/skills/googlechrome/modern-web-guidance-src/coherence-auditor.svg)](https://agentmods.dev/skills/googlechrome/modern-web-guidance-src/coherence-auditor)
Your own site
<a href="https://agentmods.dev/skills/googlechrome/modern-web-guidance-src/coherence-auditor"><img src="https://agentmods.dev/badge/skills/googlechrome/modern-web-guidance-src/coherence-auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 841 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00044 $0.00841
Opus 5 $0.00022 $0.00420
Sonnet 5 $0.00009 $0.00168
Haiku 4.5 $0.00004 $0.00084

Measured 8d ago against content hash 2574eecf8a5a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

coherence-auditor 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 8d 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.

.agents/skills/coherence-auditor/SKILL.md · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Document Coherence & Repository Auditor Skill

This skill allows you to run a comprehensive audit of the repository's documentation coherence, link integrity, and git status. It is designed to be run on-demand to catch broken links, out-of-sync mappings, untracked clutter, and unresolved TODOs.

Workflow Instructions

  1. Spawn the document-coherence-auditor Subagent: Define and invoke the subagent using define_subagent and invoke_subagent.

Subagent Definition:

  • Name: document-coherence-auditor

  • Description: Audits documentation coherence, link integrity, and git working-tree health.

  • System Prompt: You are a meticulous Document Coherence, Quality, and Git Repository Auditor subagent for this project.

    When invoked, you will run the audit script to check the state of the workspace and documentation.

    You should run the following command to execute the audit:

    node --experimental-strip-types scripts/coherence-audit.ts
    

    This script performs the following checks:

    1. Git State Check: Verifies if the working tree is clean and warns if you are working directly on the main branch.
    2. Root Clutter Check: Identifies untracked or non-canonical markdown files in the root directory that should be cleaned up.
    3. Link Integrity Check: Scans all markdown files (excluding dist/ and node_modules/) and verifies that all relative markdown links point to existing files.
    4. Feature Map Sync Check: Verifies that guides/features-and-use-cases.md is in sync with the actual guides in the repository.
    5. TODO/TBD Scan: Scans canonical docs and source guides for TODO, TBD, FIXME, or other unresolved markers.
    6. Skills Configuration Check: Warns if any skill in skills-src/ is not configured in lib/skills-config.ts.
    7. Coherence between CONTEXT.md and Project Skills: Lists CONTEXT.md and all project-* prefixed skills in .agents/skills/ to prompt a semantic coherence check.
    8. Guides Integrity Check: Runs the automated test suite guides/guides-integrity.test.ts to validate guide frontmatter, markdown soundness, and macro usage.

Read the full file on GitHub · 57 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. 8d ago First seen · 57 lines · 44 tokens per session scan A 2574eecf8a5a

Subscribe to this mod's changes

coherence-auditor is a skill published in the GitHub repository GoogleChrome/modern-web-guidance-src (1,020 stars, last pushed today), licensed Apache-2.0. It adds 44 tokens to every session and 841 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.

Related

Other skills, from other repositories

prowler-commit

Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.

prowler-cloud/prowler · 33 tokens

gh-auth-isolation

Safely manage multiple GitHub identities (EMU + personal) in agent workflows.

github/gh-aw · 20 tokens

comet-github

A routing guide for Comet-related GitHub work. It directs requests about pull requests, issues, CI failures, ideas, and fixes to the appropriate review or implementation process.

rpamis/comet · 72 tokens

github-skill

Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.

zeenie-ai/OpenCompany · 51 tokens

codex-autoresearch

Run autonomous, measurable experiments in a Git repository: change one hypothesis, verify a numeric metric, keep improvements, and revert failures. Use when the user wants Codex to keep iterating toward a numeric target in the foreground or as a detached background run. Do not use for ordinary one-shot coding…

leo-lilinxiao/codex-autoresearch · 80 tokens

changelog-composer

Generates structured changelogs and release notes from git history and PRs, classifying breaking changes, features, fixes, performance, docs. Triggers on: "generate changelog", "write release notes", "what changed since", "prepare release", "release notes for", "diff since tag".

Mathews-Tom/armory · 67 tokens