subagent

subagent is a skill for Claude Code, Codex from alessiomarcone/agent-fieldbook. It costs 76 tokens per session (558 once invoked), scanned A, original, MIT.

A guide for deciding when to delegate work to subagents—separate AI workers—and for defining exactly how they should work. It covers Claude Code, Anthropic Managed Agents, and Codex separately.

In plain words
What is it for?
Use it to plan delegated tasks, set their inputs, limits, tools, permissions, expected results, and tests, or troubleshoot subagent setups.
Why use it?
It prevents unnecessary delegation and unclear handoffs. It also avoids mixing configuration or permission rules between different products.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present. Also seen: mentions subagents; mentions Claude Code; mentions Codex.

Part of the knowledge-pack plugin — 10 skills shipped together

Good fit Use it to plan delegated tasks, set their inputs, limits, tools, permissions, expected results, and tests, or troubleshoot subagent setups.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/alessiomarcone/agent-fieldbook/subagent
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 alessiomarcone/agent-fieldbook --skill subagent
Clone the repo
git clone --depth 1 https://github.com/alessiomarcone/agent-fieldbook

Made for: Claude Code, Codex.

Or install knowledge-pack, the plugin that ships this one along with the rest of its 10 skills.

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 subagent

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/alessiomarcone/agent-fieldbook/subagent"><img src="https://agentmods.dev/badge/skills/alessiomarcone/agent-fieldbook/subagent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 558 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.
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 $0.00076 $0.00558
Opus 5 $0.00038 $0.00279
Sonnet 5 $0.00015 $0.00112
Haiku 4.5 $0.00008 $0.00056

Measured 8d ago against content hash 00853e9af6c6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

subagent 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 8d 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/knowledge-pack/skills/subagent/SKILL.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Subagent

Design the smallest delegated unit that can return a decision-ready handoff.

References

Resolve the product first, then read only its branch:

  • Claude Code: references/claude-code-subagents.md.
  • Anthropic Managed Agents: also read references/managed-agents.md.
  • Codex: references/codex-subagents.md.

Never transfer fields, commands, models, tools, or permission semantics between branches. For a cross-product migration, read both the source and target official references, map intent and constraints, and never map fields by analogy.

Decision gate

Use a subagent only when at least one is true:

  • independent work can proceed in parallel;
  • a separate context prevents noise or context pollution;
  • a specialist needs a different model, tool, or sandbox boundary;
  • the parent needs a compact result rather than the full exploration.

Otherwise return only Verdict and Simpler route, then stop.

Procedure

  1. Identify the exact surface and current supported configuration format.
  2. Define objective, inputs, exclusions, allowed tools, authority, deliverable, and success test.
  3. Default investigations to read-only. Require explicit authority for edits, external messages, publication, or destructive effects.
  4. State what context the child receives, must discover, and must not assume.
  5. Prefer read-heavy parallelism; coordinate agents that share writable state.
  6. Require a handoff with evidence, changes, unresolved risks, and a concise conclusion.
  7. When implementation is requested, verify time-sensitive configuration against current official documentation and validate the file.

Output contract

When the verdict is yes, return:

  1. Verdict — why delegation is warranted.
  2. Contract — objective, inputs, exclusions, tools, and authority.
  3. Prompt/configuration — ready to use for the selected product.
  4. Handoff — exact required return shape.
  5. Tests — normal, boundary, and failure case.

Boundaries

  • Do not invent configuration fields or availability.
  • Do not activate for an open comparison such as “custom agent or skill?”; route mechanism comparisons to navigate.
  • Do not accept “research this” without a decision-ready deliverable.
  • Do not permit silent external side effects.
  • Answer in the user's language.

Read the full file on GitHub · 60 lines

Files

What ships with it

4 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. 8d ago First seen · 60 lines · 76 tokens per session scan A 00853e9af6c6

Subscribe to this mod's changes

subagent is a skill published in the GitHub repository alessiomarcone/agent-fieldbook (5 stars, last pushed yesterday), licensed MIT. It adds 76 tokens to every session and 558 once invoked, about $0.0004 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 2026-08-31.

Related

Other skills, from other repositories

agent-memory-mcp

A hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).

lingxling/awesome-skills-cn · 26 tokens

create-agent-skills

Expert guidance for creating, writing, building, and refining Claude Code Skills. Use when working with SKILL.md files, authoring new skills, improving existing skills, or understanding skill structure and best practices.

glittercowboy/taches-cc-resources · 46 tokens

customer-support-expert

Build comprehensive customer support systems including ticketing, knowledge management, SLA tracking, and customer satisfaction analytics. Use when the user mentions helpdesk or service desk, ticketing, SLA targets, knowledge bases, escalation workflows, CSAT/NPS, or customer success operations.

personamanagmentlayer/pcl · 58 tokens

software-in-worten

Übersetzt zwischen Benutzeroberfläche und Text — in beide Richtungen. Aus einer beschriebenen Oberfläche wird ein Skill; aus einem Skill wird eine Oberfläche. Nutzen, wenn eine Anwendung entworfen wird und der Ablauf noch unklar ist, wenn ein bestehendes Werkzeug als Skill verfügbar gemacht werden soll, wenn…

ellmos-ai/skills · 87 tokens

decision-board

Render an interactive HTML board for the user to pick among multiple comparable options side-by-side at once — engineering trade-offs, copy audits, action-item triage, architecture decisions, policy calls. Returns the picks (and optional hold/note flags) as a JSON file the agent can apply.

2ykwang/agent-skills · 61 tokens

instruction-eval

Change one condition an agent runs under (instruction text, the reference material instructions point at, MCP tools and permissions, hooks, skill files), then run the same prompts before and after, several times each, to see what actually changes. Produces an HTML report showing both arms' answers side by side. Use…

2ykwang/agent-skills · 179 tokens