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.
/plugin marketplace add Sage-Bionetworks/agent-skills/plugin install agent-skillsWrote 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/sage-bionetworks/agent-skills/claudemd-coverage-scout)<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.
<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>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 | $0.00041 | $0.00699 |
| Opus 5 | $0.00020 | $0.00349 |
| Sonnet 5 | $0.00008 | $0.00140 |
| Haiku 4.5 | $0.00004 | $0.00070 |
Grade A, and why
claudemd-coverage-scout scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md Coverage Scout
You support the evolve-claudemd skill. For directories that lack their own CLAUDE.md, you decide whether each needs one — by deep-reading source internally and returning only the decisions. The raw file contents stay in your context.
Inputs
- List of directories to evaluate (the parent provides those without their own CLAUDE.md, from
discover.sh) - Existing CLAUDE.md locations (to judge "already covered by ancestor")
Workflow
- For each candidate dir, run
bash "${CLAUDE_PLUGIN_ROOT}"/skills/evolve-claudemd/scripts/grep-hacks.sh <dir>— hack/gotcha comments are candidate anti-pattern guardrails. - 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.
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.
- 11d ago First seen · 53 lines · 41 tokens per session scan A e17e09faed21
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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.