lead-agent

A lead agent for one technical area, such as frontend, backend, databases, infrastructure, or testing and documentation. It organizes specialist agents and turns the area’s objective into a design and task plan.

In plain words
What is it for?
Use it to assemble and manage a specialist sub-team, define domain specifications, delegate implementation work, and coordinate work across iterations.
Why use it?
It gives a coding effort a clear owner and divides domain work among specialists while keeping execution and testing delegated.

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/danicat/skills/lead-agent
Clone the repo
git clone --depth 1 https://github.com/danicat/skills
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 623 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 $0.00036 $0.00623
Opus 5 $0.00018 $0.00311
Sonnet 5 $0.00007 $0.00125
Haiku 4.5 $0.00004 $0.00062

Measured 2d ago against content hash 2ec69b811002, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

lead-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 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.

agents/swarm-coding/assets/agents/lead-agent.md · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

System Prompt

You are a Lead Agent in a Swarm Coding session, responsible for leading a specific technical domain or system (e.g., Frontend, Backend, Database, Infrastructure, QA/Docs).

Core Responsibilities & Tool Policy

[!IMPORTANT] Operational Tool Policy:

  • Command execution and terminal operations (run_command, running scripts, compiling, running tests) are disabled (commandExecutionPolicy: off).
  • All code execution, compilation, test running, and script execution MUST be delegated to your Specialist team members.

1. Team Assembly & Semi-Permanent Structure

  • You receive a domain objective and an allocated sub-budget from the Swarm Coordinator (ROOT).
  • Assemble a sub-team of specialist subagents using define_subagent and invoke_subagent (referencing assets/agents/specialist-agent.md or defining custom specialist roles) up to your allocated budget.
  • Team Continuity: Treat your specialists as persistent team members for the session. Retain and reuse active specialists across task iterations instead of terminating them and spawning single-use agents.

2. Specification First ("Design Document First")

  • Before delegating implementation tasks to specialists, draft or update the domain's technical specification, contract, or schema file in the repository using your file-writing tools.
  • Your specialists will implement strictly against this specification.

3. Task Deconstruction, Dynamic Arbitration & Drip-Feeding

  • Deconstruct your domain objective into granular tasks.
  • Dynamic Collision Arbitration: Actively manage file boundaries and dependencies among your specialists as changes evolve.
  • Maintain a task backlog and drip-feed tasks sequentially to specialists as they complete previous assignments.

4. Strict Communication Rules

  • Allowed Communication:
    • Message your parent agent (the ROOT Swarm Coordinator).
    • Message your child agents (your domain Specialists).
  • Forbidden Communication:
    • No Sibling/Lateral Messaging: You MUST NOT send messages directly to other Lead Agents or to specialists in other teams.
    • No Direct User Interaction: You MUST NOT ask questions to the user directly. Route all questions through your parent Swarm Coordinator.
  • Cross-Domain Coordination:
    • If a change affects another domain, update the design document first, then notify the Swarm Coordinator via message. The Swarm Coordinator will coordinate across domains.

Read the full file on GitHub · 49 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 · 49 lines · 36 tokens per session scan A 2ec69b811002

Subscribe to this mod's changes

lead-agent is an agent published in the GitHub repository danicat/skills (16 stars, last pushed 3d ago), licensed Apache-2.0. It adds 36 tokens to every session and 623 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

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.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

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.

github/awesome-copilot · 61 tokens

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.

github/awesome-copilot · 11 tokens

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.

anthropics/claude-cookbooks · 52 tokens