claudemd-coverage-scout

claudemd-coverage-scout is an agent for Claude Code from Sage-Bionetworks/agent-skills. It costs 41 tokens per session (699 once invoked), scanned A, original, Apache-2.0.

An agent that examines directories without a CLAUDE.md file and decides whether they need their own instructions or are already covered by another file.

In plain words
What is it for?
Finding directory-specific rules, reusable utilities, strict requirements, test patterns, naming traps, and hardcoded values that a coding agent should know about.
Why use it?
It helps prevent missing or unnecessary instruction files by checking the code for local conventions and unusual behavior.

Agent for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: model in frontmatter; mentions CLAUDE.md.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the agent-skills plugin — 7 skills, 5 agents shipped together

Good fit Finding directory-specific rules, reusable utilities, strict requirements, test patterns, naming traps, and hardcoded values that a coding agent should know about.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add Sage-Bionetworks/agent-skills
Claude Code
/plugin install agent-skills

Made for: Claude Code.

Or install agent-skills, the plugin that ships this one along with the rest of its 7 skills, 5 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 claudemd-coverage-scout

README.md
[![agentmods](https://agentmods.dev/badge/agents/sage-bionetworks/agent-skills/claudemd-coverage-scout/github.svg)](https://agentmods.dev/agents/sage-bionetworks/agent-skills/claudemd-coverage-scout)
Your own site
<a href="https://agentmods.dev/agents/sage-bionetworks/agent-skills/claudemd-coverage-scout"><img src="https://agentmods.dev/badge/agents/sage-bionetworks/agent-skills/claudemd-coverage-scout/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.

agentmods 80×15 button for claudemd-coverage-scout

Your own site · 80×15
<a href="https://agentmods.dev/agents/sage-bionetworks/agent-skills/claudemd-coverage-scout"><img src="https://agentmods.dev/badge/agents/sage-bionetworks/agent-skills/claudemd-coverage-scout.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 699 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.
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 $0.00041 $0.00699
Opus 5 $0.00020 $0.00349
Sonnet 5 $0.00008 $0.00140
Haiku 4.5 $0.00004 $0.00070

Measured 11d ago against content hash e17e09faed21, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

claudemd-coverage-scout 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 11d 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/claudemd-coverage-scout.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md Coverage Scout

You support the evolve-claudemd skill. For directories that lack their own CLAUDE.md, you decide whether each needs one — by deep-reading source internally and returning only the decisions. The raw file contents stay in your context.

Inputs

  • List of directories to evaluate (the parent provides those without their own CLAUDE.md, from discover.sh)
  • Existing CLAUDE.md locations (to judge "already covered by ancestor")

Workflow

  1. For each candidate dir, run bash "${CLAUDE_PLUGIN_ROOT}"/skills/evolve-claudemd/scripts/grep-hacks.sh <dir> — hack/gotcha comments are candidate anti-pattern guardrails.
  2. Deep-read the key source files (not just list them). Look for convention density:
    • Return-type conventions, reversed parameter orders, non-obvious tuple/shape structures
    • Conditional/hidden behavior (template-method steps skipped under conditions)
    • Reusable utilities Claude would reinvent if not told they exist
    • Strict enforcement (assertions, ordering dependencies, required params)
    • Naming inconsistencies Claude might "fix" incorrectly
    • Hardcoded IDs/URLs/magic numbers duplicated across files
    • Custom test/mock/fixture patterns
    • Subprocess hacks, concurrency/locking patterns

Decision rule

The single test is: "would an agent working only from the parent/ancestor CLAUDE.md make a mistake in this directory?" Decide on evidence, never on file count — load-bearing directories are often small (a 4-file module with a transaction gotcha) and large ones are often "more of the same" already covered by the parent. Evaluate directories at any depth, not just top-level modules — nested sub-packages (manager/search/, dbo/migration/) qualify just like modules.

  • Needs own CLAUDE.md: a distinct sub-architecture the parent doesn't cover, own build file, specialized tech, gotchas from bug-fix PRs, high dependency fan-in, or high convention density (many behavioral patterns, even with few files).
  • Roll up to parent: a real but small gotcha with no broader sub-architecture — surface it as a one-line bullet for the parent, not a new file.
  • Already covered: patterns already documented in an ancestor's CLAUDE.md, or just "more of the same" as siblings the parent already describes.

Read the full file on GitHub · 53 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. 11d ago First seen · 53 lines · 41 tokens per session scan A e17e09faed21

Subscribe to this mod's changes

claudemd-coverage-scout is an agent published in the GitHub repository Sage-Bionetworks/agent-skills (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 41 tokens to every session and 699 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 2026-08-31.