nested-agents

nested-agents is a skill for Claude Code, Codex from bostonaholic/team. It costs 60 tokens per session (3,069 once invoked), scanned A, original, MIT.

A set of rules for coding agents that are allowed to start one level of helper agents. A helper agent is a separate worker used for a small part of a larger task.

In plain words
What is it for?
Use it in multi-agent research, implementation, code review, or security review workflows that may delegate sub-tasks.
Why use it?
It prevents nested helpers from becoming a required dependency and gives a fallback when the feature is unavailable or fails. It also limits nesting to supported versions and one level.

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the team plugin — 42 skills, 13 agents, 2 hooks shipped together

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 skills/bostonaholic/team/nested-agents
Any agent
npx skills add bostonaholic/team --skill nested-agents
Clone the repo
git clone --depth 1 https://github.com/bostonaholic/team

Made for: Claude Code, Codex.

Or install team, the plugin that ships this one along with the rest of its 42 skills, 13 agents, 2 hooks.

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 nested-agents

README.md
[![agentmods](https://agentmods.dev/badge/skills/bostonaholic/team/nested-agents.svg)](https://agentmods.dev/skills/bostonaholic/team/nested-agents)
Your own site
<a href="https://agentmods.dev/skills/bostonaholic/team/nested-agents"><img src="https://agentmods.dev/badge/skills/bostonaholic/team/nested-agents.svg" alt="Measured on agentmods" height="20"></a>
Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,069 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 $0.00060 $0.03069
Opus 5 $0.00030 $0.01535
Sonnet 5 $0.00012 $0.00614
Haiku 4.5 $0.00006 $0.00307

Measured today against content hash 63fb0e1fca67, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

nested-agents 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.

The scan reads SKILL.md. This mod also ships 1 executable file (supports-nesting.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/nested-agents/SKILL.md · 250 lines

How it starts

The opening of the file, as written. The whole thing — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Nested Sub-Agents — Guardrails

You are a Team pipeline agent that has been granted the Agent tool. The orchestrator (the main session) dispatched you. You may dispatch helpers one level further down. These rules are non-negotiable.

Optimization, never a dependency

Nested spawning is new (Claude Code >= 2.1.172) and may be absent or capped differently in the user's version. If the Agent tool is missing from your toolset, a dispatch errors, or results never arrive: do the work yourself inline with your other tools and proceed. Never report failure solely because nesting was unavailable — it is an optimization, never a dependency (skills/principle-optimization-never-dependency/SKILL.md).

Version gate — confirm before the first nested dispatch

Nested dispatch requires Claude Code >= 2.1.172. Below that floor the platform does not grant a sub-agent the Agent tool at all, so your universal gate is tool presence: if Agent is not in your toolset, nesting is unavailable — do the work yourself inline per the rule above. This gate needs no command and holds for every agent, including read-only ones that have no Bash tool.

When you also hold the Bash tool, make sure of the running version with the bundled deterministic check. It pins the exact floor, rather than trust tool presence alone:

node "${CLAUDE_PLUGIN_ROOT}/skills/nested-agents/supports-nesting.mjs" "$(claude --version)"

It prints supported and exits 0 at or above the floor, or unsupported and exits non-zero otherwise. The check is fail-closed: an older release, unrecognizable version output, or an environment where you cannot run the check all count as unsupported. On any non-zero result — i.e. whenever the version is less than 2.1.172 or undeterminable — do not spawn helpers. Do the work yourself inline. Run the gate once. A supported result holds for the rest of your turn. Unknown counts as unsupported (skills/principle-fail-closed/SKILL.md).

Read the full file on GitHub · 250 lines

Files

What ships with it

3 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. today Changed · +20 lines 63fb0e1fca67
  2. 3d ago First seen · 230 lines · 60 tokens per session scan A 0eb0420b5626

Subscribe to this mod's changes

nested-agents is a skill published in the GitHub repository bostonaholic/team (11 stars, last pushed today), licensed MIT. It adds 60 tokens to every session and 3,069 once invoked, about $0.0003 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 skills, from other repositories

tutti-app-release

Set up, review, run, or debug external repositories that publish a Tutti workspace app through the reusable Tutti App Release GitHub Actions workflow. Use for caller workflows, tutti.app.json manifests, @tutti-os/app-release-tools, S3/CloudFront release hosting, latest.json, versions.json, catalog.json, catalog-only…

tutti-os/tutti · 80 tokens

analyze-performance-traces

Analyze Chrome, Chromium, Electron, React DevTools, or Perfetto-compatible JSON traces and audit user-reported profiling findings without loading large artifacts into context; prove trigger-to-render/layout chains, separate measured facts from source inference, find exact code choke points, classify forced layout and…

tutti-os/tutti · 127 tokens

tutti-test-audit

Audit, design, write, materially revise, or remove Tutti tests. Use whenever Codex changes or reviews unit, component, conformance, integration, regression, platform, or repository tests; enforce a protected product contract, credible failure, correct owning boundary, negative-control evidence, overlap review…

tutti-os/tutti · 74 tokens

tutti-agent-workspace-app

Build or evolve a complex agent-enabled Tutti workspace app repository. Use for Tutti apps with web/server/shared monorepos, @tutti-os/agent-acp-kit local agent runtimes, kit-owned TUTTICLI agent/composer discovery, dynamic agent catalogs, run-scoped MCP tool gateways, app-owned package builders, web-first debugging…

tutti-os/tutti · 106 tokens

assimilate-popular-workflows

This skill should be used when the user asks to "find skills in the wild", "assimilate popular workflows", "discover SKILL.md files in repos", "research external skills", "find workflow patterns", "survey the skill landscape", "what skills exist out there", or wants to investigate public repositories for extractable…

a5c-ai/babysitter · 110 tokens

process-builder

Scaffold new babysitter process definitions following SDK patterns, proper structure, and best practices. Guides the 3-phase workflow from research to implementation.

a5c-ai/babysitter · 32 tokens