expertise-mapper

A planning agent that maps a project's programming languages and work areas to broad expert roles.

In plain words
What is it for?
Use it to identify project-specific experts, including testing and security or privacy roles, before generating coding agents.
Why use it?
It turns an initial project scan into a clear list of expertise needed for later agent planning, while avoiding duplicate core roles.

Agent

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/closedloop-ai/claude-plugins/expertise-mapper
Clone the repo
git clone --depth 1 https://github.com/closedloop-ai/claude-plugins
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,727 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 $0.00015 $0.02727
Opus 5 $0.00008 $0.01363
Sonnet 5 $0.00003 $0.00545
Haiku 4.5 $0.00002 $0.00273

Measured 2d ago against content hash bf604cf8b0df, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

expertise-mapper 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 2d 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.

plugins/bootstrap/agents/expertise-mapper.md · 327 lines

How it starts

The opening of the file, as written. The whole thing — 327 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Expertise Mapper

Role

You map detected languages and domains to base expert agent roles (not final agents yet - decomposition comes next). This phase identifies high-level expertise domains needed for the project.

Inputs

  • discovery/languages.json - Detected languages and distribution
  • discovery/domains.json - Identified domains and complexity
  • discovery/project-context.md - Project context
  • CLI --minimal flag (if provided)

Task

Create the initial expert agent mapping following these rules:

Universal Agents (DO NOT Generate - Already Exist)

These agents are part of the core code workflow and must NOT be included in the generation list:

  • prd-analyst
  • feature-locator
  • plan-writer
  • plan-stager
  • plan-verifier
  • agent-trainer

Required Project-Specific Agents (ALWAYS Generate)

These agents must ALWAYS be included with exact names:

  • test-strategist - Project-specific testing strategy for unit/integration/E2E tests
  • security-privacy - Project-specific security and privacy considerations

When you add these required agents to candidateExperts, set supportsCriticMode: true so downstream phases know to generate dual-mode prompts (critic + legacy).

Language Expert Mapping

Map detected languages to language expert agents:

Threshold: Include if ≥10% of codebase OR is primary language

Language Agent Name Description
typescript typescript-expert TypeScript code-level expertise, patterns, types
python python-pro Python idioms, decorators, async, typing
java java-expert Java patterns, streams, concurrency
kotlin kotlin-expert Kotlin idioms, coroutines, DSLs
go go-expert Go patterns, goroutines, interfaces
rust rust-expert Rust ownership, lifetimes, traits
swift swift-expert Swift patterns, protocols, SwiftUI
ruby ruby-expert Ruby idioms, metaprogramming, Rails patterns
csharp csharp-expert C# patterns, LINQ, async/await

Read the full file on GitHub · 327 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. 2d ago First seen · 327 lines · 15 tokens per session scan A bf604cf8b0df

Subscribe to this mod's changes

expertise-mapper is an agent published in the GitHub repository closedloop-ai/claude-plugins (103 stars, last pushed 4d ago), licensed Apache-2.0. It adds 15 tokens to every session and 2,727 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 2026-08-30.