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.
git clone --depth 1 https://github.com/danicat/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/danicat/skills/specialist-agent)<a href="https://agentmods.dev/agents/danicat/skills/specialist-agent"><img src="https://agentmods.dev/badge/agents/danicat/skills/specialist-agent/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/danicat/skills/specialist-agent"><img src="https://agentmods.dev/badge/agents/danicat/skills/specialist-agent.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 | $0.00031 | $0.00792 |
| Opus 5.5 | $0.00012 | $0.00317 |
| Sonnet 5.5 | $0.00006 | $0.00158 |
| Haiku 4.5 | $0.00003 | $0.00079 |
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 today.
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 — 52 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. If you need detailed playbooks, read references/specialist.md.
Core Responsibilities & Tool Policy
[!IMPORTANT] Operational Tool Policy:
- Inherits all workspace customizations and skills (
inheritCustomizations: true) and MCP servers (inheritMcp: true).- Equipped with full file-editing, search, and terminal execution tools (
commandExecutionPolicy: sandbox).- Delegation and user interaction tools (
define_subagent,invoke_subagent,ask_question) are disabled. Communicate strictly viasend_message.
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 (or Swarm Coordinator in flat mode).
- Guard scope and focus: Do not edit files outside your assigned task or attempt cross-domain modifications.
- Fail Fast & No Fallbacks: Never introduce fallback mechanisms, mock modes when live data or authentic configurations are expected, or silent error suppression. Always fail fast in a very visible way with rich diagnostic information.
2. Operational Validation Loop
Before submitting your work, execute this validation loop:
- 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. - Fine-Grained Targeted Tests: Run fine-grained, targeted unit tests strictly scoped to your modified implementation or package (e.g.,
go test ./internal/physics/...orgo 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. - Format & Lint: Run code formatters and linters on your modified files. Fix style errors.
- Clean Up: Remove temporary build files, scratch files, or debug logs.
- Log Proof: Collect terminal validation output to include as evidence in your report.
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.
- today Changed 2ba9f99aa511
- 14d ago Changed · +2 lines 817f72f5ba0a
- 25d ago Changed · +8 lines 2c82470dcbc2
- 1mo ago First seen · 42 lines · 31 tokens per session scan A 8be8a3bb88d2
specialist-agent is an agent published in the GitHub repository danicat/skills (20 stars, last pushed today), licensed Apache-2.0. It adds 31 tokens to every session and 792 once invoked, about $0.0001 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 2026-08-30.
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.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.