skill-discovery

skill-discovery is an agent for coding agents from MadAppGang/claude-code. It costs 18 tokens per session (1,804 once invoked), scanned A, original, MIT.

An agent that catalogs Claude Code skills available in a project, including their names, descriptions, locations, and categories.

In plain words
What is it for?
Use it to find project and plugin skill files, read their metadata, and organize the results into a skill catalog.
Why use it?
It helps developers see which reusable instructions are already installed without manually searching every possible skills folder.

Agent

Part of the dev plugin — 47 skills, 12 commands, 14 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 agents/madappgang/claude-code/skill-discovery
Clone the repo
git clone --depth 1 https://github.com/MadAppGang/claude-code

Or install dev, the plugin that ships this one along with the rest of its 47 skills, 12 commands, 14 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 skill-discovery

README.md
[![agentmods](https://agentmods.dev/badge/agents/madappgang/claude-code/skill-discovery.svg)](https://agentmods.dev/agents/madappgang/claude-code/skill-discovery)
Your own site
<a href="https://agentmods.dev/agents/madappgang/claude-code/skill-discovery"><img src="https://agentmods.dev/badge/agents/madappgang/claude-code/skill-discovery.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,804 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 $0.00018 $0.01804
Opus 5 $0.00009 $0.00902
Sonnet 5 $0.00004 $0.00361
Haiku 4.5 $0.00002 $0.00180

Measured yesterday against content hash 86f0cedfa5af, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skill-discovery 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.

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.

plugins/dev/agents/skill-discovery.md · 246 lines

How it starts

The opening of the file, as written. The whole thing — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.

1. **Project-level** (highest priority):
   - .claude/skills/**/SKILL.md

2. **Local plugins** (if .claude-plugin/ exists):
   - .claude-plugin/*/skills/**/SKILL.md

3. **Plugin directories** (workspace plugins):
   - plugins/*/skills/**/SKILL.md

4. **Home directory** (user-wide, lowest priority):
   - ~/.claude/skills/**/SKILL.md

</skill_locations>

<discovery_workflow> Use Glob to find all SKILL.md files: Glob: .claude/skills/**/SKILL.md Glob: .claude-plugin/*/skills/**/SKILL.md Glob: plugins/*/skills/**/SKILL.md

  Note: Skip ~/.claude/skills/ unless explicitly requested
  (user-wide skills may not be relevant to specific project)
</step>

<step number="2" name="Parse Frontmatter">
  For each discovered SKILL.md:

  1. Read the file
  2. Extract YAML frontmatter between --- markers
  3. Parse required fields:
     - name (string, required)
     - description (string, required)
  4. Parse optional fields:
     - keywords (array)
     - category (string)
     - dependencies (array)
</step>

<step number="3" name="Infer Categories">
  If skill doesn't have explicit category, infer from:

  1. **Path analysis**:
     - /testing/ → "testing"
     - /frontend/ → "frontend"
     - /backend/ → "backend"
     - /workflow/ → "workflow"

  2. **Name analysis**:
     - "tdd-*", "*-test" → "testing"
     - "debug-*" → "debugging"
     - "react-*", "vue-*" → "frontend"
     - "api-*", "db-*" → "backend"

  3. **Description keywords**:
     Match against keyword list (see <category_keywords>)
</step>

<step number="4" name="Build Catalog">
  Create structured catalog:
  ```json
  {
    "total_count": 5,
    "by_source": {
      "project": 2,
      "plugin": 3
    },
    "by_category": {
      "testing": ["tdd-workflow", "unit-testing"],
      "frontend": ["react-patterns"],
      "backend": ["api-design", "db-patterns"]
    },
    "skills": [
      {
        "name": "tdd-workflow",
        "description": "Test-driven development workflow",
        "path": ".claude/skills/tdd-workflow/SKILL.md",
        "source": "project",
        "categories": ["testing", "workflow"],
        "keywords": ["tdd", "red-green-refactor"],
        "priority": 1
      }
    ]
  }
  ```
</step>

<step number="5" name="Match to Task">
  If a task description is provided, rank skills by relevance:

  1. **Exact keyword match** (+10 points)
  2. **Category match** (+5 points)
  3. **Description similarity** (+1-3 points)
  4. **Project source bonus** (+2 points)

  Return skills sorted by relevance score.
</step>

</discovery_workflow>

<category_keywords> testing: - test, tdd, spec, coverage, assertion, mock, stub, fixture - jest, vitest, pytest, testing-library, cypress, playwright

debugging:
  - debug, trace, diagnose, log, breakpoint, error, exception
  - stack trace, profiling, performance

frontend:
  - react, vue, svelte, angular, component, ui, ux
  - css, style, layout, responsive, animation, a11y

backend:
  - api, server, endpoint, route, handler, middleware
  - rest, graphql, grpc, websocket

Read the full file on GitHub · 246 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. yesterday First seen · 246 lines · 18 tokens per session scan A 86f0cedfa5af

Subscribe to this mod's changes

skill-discovery is an agent published in the GitHub repository MadAppGang/claude-code (279 stars, last pushed 5mo ago), licensed MIT. It adds 18 tokens to every session and 1,804 once invoked, about $0.0001 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 2026-09-03.