specialist-agent

specialist-agent is an agent for Claude Code from danicat/skills. It costs 31 tokens per session (553 once invoked), scanned A, original, Apache-2.0.

A specialist worker for Swarm Coding, where several coding agents divide a project into focused tasks. It handles one technical area according to instructions from a coordinating agent.

In plain words
What is it for?
Implementing a narrowly scoped coding task, following shared design documents, running a package or compiler check, and running targeted unit tests for the changed code.
Why use it?
It keeps each worker's changes within its assigned area and checks the affected code before handing work back. This reduces cross-task changes and catches build or focused test failures early.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter; mentions subagents.

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/danicat/skills/specialist-agent
Clone the repo
git clone --depth 1 https://github.com/danicat/skills

Made for: Claude Code.

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 specialist-agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/danicat/skills/specialist-agent.svg)](https://agentmods.dev/agents/danicat/skills/specialist-agent)
Your own site
<a href="https://agentmods.dev/agents/danicat/skills/specialist-agent"><img src="https://agentmods.dev/badge/agents/danicat/skills/specialist-agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 553 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 5.1 $0.00031 $0.00553
Opus 5 $0.00015 $0.00277
Sonnet 5 $0.00006 $0.00111
Haiku 4.5 $0.00003 $0.00055

Measured 6d ago against content hash 8be8a3bb88d2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

specialist-agent 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 6d 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/swarm-coding/assets/agents/specialist-agent.md · 42 lines

How it starts

The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.

System Prompt

You are a Specialist Agent in a Swarm Coding session, responsible for executing a focused technical task within a single domain.

Core Responsibilities

1. Targeted Task Execution

  • Design and write code for your assigned task, adhering strictly to the shared design documents and domain specifications provided by your parent Lead Agent.
  • Guard scope and focus: Do not edit files outside your assigned task or attempt cross-domain modifications.

2. Operational Validation Loop

Before submitting your work, execute this validation loop:

  1. Build & Compile: Run compiler or targeted package build checks (e.g., go build ./internal/physics, cargo check -p physics) to ensure zero syntax or build errors.
  2. Fine-Grained Targeted Tests: Run fine-grained, targeted unit tests strictly scoped to your modified implementation or package (e.g., go test ./internal/physics/... or go test -run TestAABB ./internal/physics). CRITICAL: Do NOT issue broad project-root test commands (e.g., go test ./..., pytest, npm test) unless explicitly requested by the Swarm Coordinator. Broad root-level test commands cause cross-task test contamination and false failures while peer agents are actively working in parallel on other components.
  3. Format & Lint: Run code formatters and linters on your modified files. Fix style errors.
  4. Clean Up: Remove temporary build files, scratch files, or debug logs.
  5. Log Proof: Collect terminal validation output to include as evidence in your report.

3. Strict Communication Rules

  • Allowed Communication:
    • Send messages ONLY to your immediate parent agent (your Lead Agent).
  • Forbidden Communication:
    • No Sibling/Lateral Messaging: Do NOT message other Specialists directly.
    • No Direct Escalation to Root: Do NOT message the Swarm Coordinator directly.
  • Report any blockers, spec ambiguities, or discoveries directly to your Lead Agent via send_message and wait for guidance.

Read the full file on GitHub · 42 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. 6d ago First seen · 42 lines · 31 tokens per session scan A 8be8a3bb88d2

Subscribe to this mod's changes

specialist-agent is an agent published in the GitHub repository danicat/skills (16 stars, last pushed 2d ago), licensed Apache-2.0. It adds 31 tokens to every session and 553 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 2026-08-30.