agentmods.dev

crow-diagnose

crow-diagnose is a skill for Claude Code, Codex from corveil/crow. It costs 168 tokens per session (8,191 once invoked), scanned A, original, Apache-2.0.

A software-work triage workflow that turns an observation into a well-defined ticket, a larger epic, or a decision not to file work. An epic is a large piece of work that may contain several tickets.

In plain words
What is it for?
Use it to examine an observation, check for duplicates, choose the affected repositories, and draft or file the appropriate backlog item.
Why use it?
It keeps raw comments or meeting notes from becoming vague or duplicate backlog items. It investigates the code and records where the decision came from, but does not start the work.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

not rated 21repo +1 changed yesterday A scan 168 tokens original Apache-2.0

Good fit Use it to examine an observation, check for duplicates, choose the affected repositories, and draft or file the appropriate backlog item.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/corveil/crow/crow-diagnose
View source ↗ corveil/crow
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.

Any agent
npx skills add corveil/crow --skill crow-diagnose
Clone the repo
git clone --depth 1 https://github.com/corveil/crow

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 crow-diagnose

README.md
[![agentmods](https://agentmods.dev/badge/skills/corveil/crow/crow-diagnose/github.svg)](https://agentmods.dev/skills/corveil/crow/crow-diagnose)
Your own site
<a href="https://agentmods.dev/skills/corveil/crow/crow-diagnose"><img src="https://agentmods.dev/badge/skills/corveil/crow/crow-diagnose/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 crow-diagnose

Your own site · 80×15
<a href="https://agentmods.dev/skills/corveil/crow/crow-diagnose"><img src="https://agentmods.dev/badge/skills/corveil/crow/crow-diagnose.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 168 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 8,191 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 $0.00168 $0.08191
Opus 5.5 $0.00067 $0.03276
Sonnet 5.5 $0.00034 $0.01638
Haiku 4.5 $0.00017 $0.00819

Measured yesterday against content hash 0db5b6de0589, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

crow-diagnose 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 yesterday.

The scan reads SKILL.md. This mod also ships 2 executable files (diagnose_test.sh, diagnose.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/crow-diagnose/SKILL.md · 395 lines

How it starts

The opening of the file, as written. The whole thing — 395 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Crow Diagnose Skill

Purpose

An observation stays raw at its source: a meeting remark captured as a Corveil FollowUp, a Slack thread, a Scratch item. This skill is the step between capture and the backlog. A Manager that can read the code diagnoses one observation. It either files a ticket or epic that meets the ticket standard, or reports one of the outcomes that aren't tickets. ADR 0031 records why.

One run:

  1. Resolve the source and read it in full.
  2. Gate: is it engineering work?
  3. Choose the repos.
  4. Investigate the code at origin/main.
  5. Check for duplicates.
  6. Decide the shape: nothing, a comment, one ticket, or an epic.
  7. Draft, check and file.
  8. Write the provenance back to the source.
  9. Report.

It never starts the work. Prioritising is /crow-backlog-brief, and working is /crow-workspace or /crow-cascade-epic.

Requirements

  • A Crow Manager, which can read every repo in its workspace. gh authenticated for the workspace's repos, jq 1.6 or newer, and git.
  • For a FollowUp or a meeting: the corveil CLI with an API key. To write a FollowUp's ticket_url back: the Corveil MCP server's ontology_update_entity tool.
  • For a Slack permalink: a Slack MCP tool that reads a thread, or the Corveil MCP server (Corveil's Slack sensor records threads).
  • A GitHub workspace for the helper. repos, checkout, dupes and file refuse a GitLab workspace. There, do those steps with glab by hand. For a Jira task_provider, file into Jira with the jira MCP the way /crow-create-ticket does. The gate, the standard and the plan stay the same.

Harnesses

Manager How to run it What differs
Claude Code /crow-diagnose <observation> [flags] Can fan the investigation out to Agent subagents (Step 4).
Cursor, Codex, OpenCode If the harness doesn't load .claude/skills/ as slash commands, ask it to "read .claude/skills/crow-diagnose/SKILL.md and follow it for <observation>". No subagents: investigate one repo at a time. The FollowUp write-back needs the Corveil MCP server in that harness. Without it, Step 8 reports the pending write instead.

Read the full file on GitHub · 395 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. yesterday Changed 0db5b6de0589
  2. 3d ago First seen · 395 lines · 168 tokens per session scan A 1dced4c4b297

Subscribe to this mod's changes

crow-diagnose is a skill published in the GitHub repository corveil/crow (21 stars, last pushed today), licensed Apache-2.0. It adds 168 tokens to every session and 8,191 once invoked, about $0.0007 per session on Opus 5.5. 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 2026-11-10.

Claude CodePlanningProject managementaideveloper-toolsgit-worktreeswiftterminal
Related

crow-diagnose compared with skills from other repositories

crow-diagnose next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
crow-diagnosecorveil/crowSkill21todayApache-2.0A168Claude Code, Codex
liney-clieverettjf/lineySkill150todayApache-2.0B195Claude Code, Codex
focus-colorbrianharms/dispatchSkill55mo agoMITA19Claude Code, Codex
test-warp-uiwarpdotdev/warpSkill66ktodayAGPL-3.0A55Claude Code
modify-settingswarpdotdev/warpSkill66ktodayAGPL-3.0A16Claude Code, Codex
mulmoterminal-keysreceptron/mulmoterminalSkill2682d agoMITA310Claude Code, Codex
tui-migrate-setupwarpdotdev/warpSkill66ktodayAGPL-3.0B75Claude Code, Codex