agent-fanout

agent-fanout is a skill for Claude Code from neuromechanist/research-skills. It costs 113 tokens per session (2,889 once invoked), scanned A, original, BSD-3-Clause.

A workflow for coordinating multiple coding agents or subagents on one larger task. It helps decide when work can be split, how agents should be assigned, and how their results should be combined and reviewed.

In plain words
What is it for?
Use it to explore separate areas in parallel, assign one agent to each independent issue, organize implementation teams, or review and validate a completed change.
Why use it?
It reduces the need to manage parallel investigations, implementations, and reviews manually when the work contains independent parts.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents; mentions Claude Code; mentions Codex.

Part of the project plugin — 15 skills, 5 commands, 3 agents shipped together

Good fit Use it to explore separate areas in parallel, assign one agent to each independent issue, organize implementation teams, or review and validate a completed change.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/neuromechanist/research-skills/agent-fanout
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.

Any agent
npx skills add neuromechanist/research-skills --skill agent-fanout
Clone the repo
git clone --depth 1 https://github.com/neuromechanist/research-skills

Made for: Claude Code.

Or install project, the plugin that ships this one along with the rest of its 15 skills, 5 commands, 3 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 agent-fanout

README.md
[![agentmods](https://agentmods.dev/badge/skills/neuromechanist/research-skills/agent-fanout/github.svg)](https://agentmods.dev/skills/neuromechanist/research-skills/agent-fanout)
Your own site
<a href="https://agentmods.dev/skills/neuromechanist/research-skills/agent-fanout"><img src="https://agentmods.dev/badge/skills/neuromechanist/research-skills/agent-fanout/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.

agentmods 80×15 button for agent-fanout

Your own site · 80×15
<a href="https://agentmods.dev/skills/neuromechanist/research-skills/agent-fanout"><img src="https://agentmods.dev/badge/skills/neuromechanist/research-skills/agent-fanout.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 113 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,889 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Privilege Escalation · line 134
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
How audits are shown
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 $0.00113 $0.02889
Opus 5 $0.00056 $0.01444
Sonnet 5 $0.00023 $0.00578
Haiku 4.5 $0.00011 $0.00289

Measured 12d ago against content hash e17114b3d3f7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

agent-fanout 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 12d 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/project/skills/agent-fanout/SKILL.md · 210 lines

How it starts

The opening of the file, as written. The whole thing — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Fan-Out and Teams

Orchestrate multiple subagents or teammates to explore, implement, review, and validate in parallel. This skill makes every judgment call explicit: when to fan out, how many agents, which model, what to put in each prompt, how to supervise, and how to combine results.

When to fan out (decision table)

Situation Action
Single bounded question ("where is X defined?") No fan-out. Search directly or use one read-only explorer.
Open-ended audit/review of a system with 2+ independent subsystems One read-only explorer per subsystem, in parallel.
Multiple root-caused issues, each fixable independently One implementer per issue, each in its own git worktree.
One pull request (PR) ready for review One review panel (2-5 reviewers, see Review panels below).
Sequential work where step N needs step N-1's output Do NOT parallelize. Run one agent at a time or do it inline.
Task needs secrets, deploy rights, or user-only credentials Do NOT delegate. Keep it in the main session (mark the task "owner: lead").

Do not fan out for work you can finish inline in a few minutes; a subagent costs setup, supervision, and synthesis time.

Hard limits (compute BEFORE launching)

  1. Before any fan-out, compute the worst case: finders x max findings per finder x verifiers per finding + implementers + reviewers. Write the number down in your plan.
  2. Budget: 10-20 agents per run for routine work; hard cap 40. If the math exceeds the routine budget, say so and justify it; if it exceeds 40, cut scope before launching: fewer lenses, findings capped per agent (maxItems-style limits in the prompt), one verification vote instead of three. Going past 40 requires explicit user approval in the same conversation. If the user's own configuration states a stricter cap, the stricter number wins.
  3. Prefer waves of 10 or fewer concurrent agents. Finish and synthesize a wave before launching the next.
  4. Every phase plan states its own agent budget and routing up front (for example "Sol lead + Terra phase planner + Luna implementer/reviewer, ~4 agents total").
  5. If you hit a rate limit: stop spawning, schedule one backoff wait, resume staggered. Narrate as a status update, not a question.

Read the full file on GitHub · 210 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 12d ago First seen · 210 lines · 113 tokens per session scan A e17114b3d3f7

Subscribe to this mod's changes

agent-fanout is a skill published in the GitHub repository neuromechanist/research-skills (45 stars, last pushed 9d ago), licensed BSD-3-Clause. It adds 113 tokens to every session and 2,889 once invoked, about $0.0006 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.