compose:subagent

compose:subagent is a skill for Claude Code, Codex from sergezuber/FABULA-LLM-5. It costs 17 tokens per session (3,530 once invoked), scanned A, a copy of compose:subagent, MIT.

A method for carrying out an implementation plan by giving each independent task to a fresh specialized coding agent, followed by two reviews.

In plain words
What is it for?
Use it to execute multi-step plans involving independent coding tasks, with specification and code-quality reviews after each task.
Why use it?
It keeps separate tasks focused and checks both whether the requested behavior was implemented and whether the code is well made.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

Good fit Use it to execute multi-step plans involving independent coding tasks, with specification and code-quality reviews after each task.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sergezuber/fabula-llm-5/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 sergezuber/FABULA-LLM-5 --skill subagent
Clone the repo
git clone --depth 1 https://github.com/sergezuber/FABULA-LLM-5

Made for: Claude Code, Codex.

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 compose:subagent

README.md
[![agentmods](https://agentmods.dev/badge/skills/sergezuber/fabula-llm-5/subagent.svg)](https://agentmods.dev/skills/sergezuber/fabula-llm-5/subagent)
Your own site
<a href="https://agentmods.dev/skills/sergezuber/fabula-llm-5/subagent"><img src="https://agentmods.dev/badge/skills/sergezuber/fabula-llm-5/subagent.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,530 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 86% copy Near-identical to another mod 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 $0.00017 $0.03530
Opus 5 $0.00009 $0.01765
Sonnet 5 $0.00003 $0.00706
Haiku 4.5 $0.00002 $0.00353

Measured 8d ago against content hash e0998da43c9a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

compose: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.

Origin

This is a copy

86% identical to compose:subagent — 7 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

engine/packages/opencode/src/skill/compose/.bundle/subagent/SKILL.md · 326 lines

How it starts

The opening of the file, as written. The whole thing — 326 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Subagent-Driven Development

Execute plan by dispatching fresh subagent per task, with two-stage review after each: spec compliance review first, then code quality review.

Why subagents: You delegate tasks to specialized agents with isolated context. By precisely crafting their instructions and context, you ensure they stay focused and succeed at their task. They should never inherit your session's context or history — you construct exactly what they need. This also preserves your own context for coordination work.

Core principle: Fresh subagent per task + two-stage review (spec then quality) = high quality, fast iteration

Continuous execution: Do not pause to check in with your human partner between tasks. Execute all tasks from the plan without stopping. The only reasons to stop are: BLOCKED status you cannot resolve, ambiguity that genuinely prevents progress, or all tasks complete. "Should I continue?" prompts and progress summaries waste their time — they asked you to execute the plan, so execute it. When you must stop for ambiguity or a blocker, use compose:ask to present the situation with structured options. If no user is available, resolve it with your best judgment and continue.

When to Use

  1. Have implementation plan? — No → brainstorm first or manual execution
  2. Tasks mostly independent? — No (tightly coupled) → brainstorm first or manual execution
  3. Stay in this session? — Yes → compose:subagent / No → compose:execute (parallel session)

vs. Executing Plans (parallel session):

  • Same session (no context switch)
  • Fresh subagent per task (no context pollution)
  • Two-stage review after each task: spec compliance first, then code quality
  • Faster iteration (no human-in-loop between tasks)

The Process

Setup: Read plan → extract all tasks with full text → note context → create a task per plan task (task create)

Per Task:

  • Dispatch implementer — create+bind task (--task <TID>, auto-starts), inject covered spec as Intent, dispatch (./implementer-prompt.md)
  • Implementer asks questions? — Yes → answer, provide context, re-dispatch implementer
  • Implementer implements — tests, commits, self-reviews
  • Spec review phase 1 — dispatch with spec + diff only, no report
  • Phase 1 flagged anything? — Yes → dispatch phase 2 (report explains flags, downgrade-only)
  • Spec gate: all in-scope claims pass with evidence? — No → implementer fixes → back to spec review phase 1
  • Code quality review — dispatch reviewer (./code-quality-reviewer-prompt.md)
  • Quality approved? — No → implementer fixes → back to code quality review
  • Mark task donetask done <TID>

Read the full file on GitHub · 326 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. 8d ago First seen · 326 lines · 17 tokens per session scan A e0998da43c9a

Subscribe to this mod's changes

compose:subagent is a skill published in the GitHub repository sergezuber/FABULA-LLM-5 (83 stars, last pushed 7d ago), licensed MIT. It adds 17 tokens to every session and 3,530 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to compose:subagent, differing in 7 lines, and is treated as a copy.

Related

Other skills, from other repositories

architecture-audit

Systematic architecture audit and refactoring methodology for Rust + TypeScript codebases. Use when performing refactoring, cleanup, unification, code review, dead code removal, module reorganization, or tech debt elimination. Ensures no naming confusion, semantic overloading, hidden defaults, duplicate logic, or…

org2AI/ORG2 · 70 tokens

e2e-testing

ORGII keeps two separate E2E surfaces. Do not use one as proof for the other.

org2AI/ORG2 · 0 tokens

dual-instance-verification

Dual-instance (双机) real-machine verification protocol for ORG2 cloud sync and session sharing. Use before declaring any sharing/sync/collab feature or fix "verified": share/unshare, push/retract, fork/import, comments, member-floor, replay, continuation, or anything touching Org2CloudSyncEngine, collab engines, or the…

org2AI/ORG2 · 0 tokens

org2-performance-guard

Prevent CPU, RAM, I/O, background-work, and false-green lifecycle regressions in ORG2. Use when adding or reviewing polling, timers, Realtime subscriptions, event listeners, workers, streaming paths, caches, pagination, provider-owned transcript ingestion or identity/dedupe, external-history scans, cloud sync…

org2AI/ORG2 · 112 tokens

react-best-practices

ORGII-specific React 19 performance review and implementation guidance, adapted from Vercel Engineering. Use for React performance, re-render, async waterfall, bundle, heavy dependency, virtualization, high-frequency event, Context/provider, or store-subscription work. Do not trigger for styling, copy changes, or…

org2AI/ORG2 · 77 tokens

create-orgii-agent

Create or modify a custom ORGII agent definition (and the org it belongs to). Use when the user wants to create, configure, retune, rename, or delete an agent, define an agent's soul / capabilities / tools, organise agents into an org, or asks about agent-definitions.json.

org2AI/ORG2 · 67 tokens