subagent-execution

subagent-execution is a skill for Claude Code, Codex from yimwoo/hotl-plugin. It costs 36 tokens per session (1,981 once invoked), scanned A, original, MIT.

A workflow for delegating eligible development steps to separate coding agents while a main controller manages approvals, checks, budgets, and completion conditions.

In plain words
What is it for?
Running an existing step-by-step development plan when tasks can be delegated one at a time and the main session must retain control of verification and decisions.
Why use it?
It allows independent work to be handed off without losing oversight of what was done, whether it was verified, or whether the workflow should continue.

Skill for Claude CodeCodex

Part of the hotl plugin — 20 skills, 9 commands, 1 agent, 1 hook 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/yimwoo/hotl-plugin/subagent-execution
Any agent
npx skills add yimwoo/hotl-plugin --skill subagent-execution
Clone the repo
git clone --depth 1 https://github.com/yimwoo/hotl-plugin

Made for: Claude Code, Codex.

Or install hotl, the plugin that ships this one along with the rest of its 20 skills, 9 commands, 1 agent, 1 hook.

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-execution

README.md
[![agentmods](https://agentmods.dev/badge/skills/yimwoo/hotl-plugin/subagent-execution.svg)](https://agentmods.dev/skills/yimwoo/hotl-plugin/subagent-execution)
Your own site
<a href="https://agentmods.dev/skills/yimwoo/hotl-plugin/subagent-execution"><img src="https://agentmods.dev/badge/skills/yimwoo/hotl-plugin/subagent-execution.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,981 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 $0.01981
Opus 5 $0.00018 $0.00991
Sonnet 5 $0.00007 $0.00396
Haiku 4.5 $0.00004 $0.00198

Measured 3d ago against content hash 2f1416a66938, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

subagent-execution 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 3d 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.

skills/subagent-execution/SKILL.md · 148 lines

How it starts

The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.

HOTL Subagent Execution

Overview

This is a delegation profile over the HOTL execution state machine defined in skills/loop-execution/SKILL.md. It follows the same resolve → preflight → lint → execute → verify → loop → gate → summarize flow, but eligible steps are delegated to fresh subagents instead of running inline.

When selected by governed-execution, the controller uses the chosen driver for all durable transitions and remains responsible for ownership, action gates and effect outcomes, budgets, verification, receipts, and recovery. Native or background-agent success is never sufficient by itself.

Core principle: delegation is allowed; governance is not delegated.

When to Use

  • The workflow file already exists (canonical docs/plans/YYYY-MM-DD-<slug>-workflow.md preferred; legacy root hotl-workflow-<slug>.md still accepted during migration)
  • Steps are independent enough to hand to one worker at a time
  • You want the controller to stay in this session and keep ownership of gates and verification

Execution

Follow the HOTL Execution State Machine in skills/loop-execution/SKILL.md for the full execution flow (workflow resolution, interrupted run detection, branch/worktree preflight, structural lint, execution state persistence, typed verification, loop rules, gate rules, completion).

The controller owns all hotl-rt runtime calls. It initializes with --require-owner, runs owner claim, retains the one-time token only in HOTL_OWNER_TOKEN, and runs owner heartbeat before dispatch, after a worker returns, and at safe transition boundaries. It calls hotl-rt step N start/verify/retry/block, hotl-rt gate N, sensitive-action lifecycle commands, budget checks, hotl-rt finalize, and hotl-rt finish from the resolved execution_root, pinning every call to the captured run_id (--run-id <run-id> or HOTL_RUN_ID=<run-id>). Subagents never receive the owner token and never call the runtime directly. The runtime-managed .hotl/state/<run-id>.json and .hotl/reports/<run-id>.md are the source of truth; delegated workers do implementation only.

Read the full file on GitHub · 148 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. 3d ago First seen · 148 lines · 36 tokens per session scan A 2f1416a66938

Subscribe to this mod's changes

subagent-execution is a skill published in the GitHub repository yimwoo/hotl-plugin (26 stars, last pushed 1mo ago), licensed MIT. It adds 36 tokens to every session and 1,981 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 skills, from other repositories

first-plan-co-change-analysis

Skill que constrói o Co-change Graph - "quando arquivo X muda, qual outro arquivo geralmente muda junto?". Use durante Discovery e em /fp:cochange. Baseado em git history. Detecta arquivos co-dependentes que devem ser editados juntos para evitar PRs incompletos. v0.3.0+ usa engine nativo Rust quando disponível…

vynazevedo/first-plan · 88 tokens

first-plan-provenance-tracker

Skill que define o schema de proveniência e o sistema de freshness tracking para findings em .first-plan/. Use durante Discovery e refresh para registrar source (file:line@SHA), TTL, confidence inicial e cadeia de supersedeção. Aplica decay de confidence baseado em idade.

vynazevedo/first-plan · 64 tokens

first-plan-git-intelligence

Skill que extrai inteligência do git history - heatmap de atividade, ownership, branches/PRs in-flight. Use durante Discovery e em /fp:hot, /fp:owner, /fp:in-flight. Tudo via comandos git read-only.

vynazevedo/first-plan · 58 tokens

first-plan-protocol

Esta skill DEVE ser carregada em qualquer comando do plugin first-plan. Define o protocolo PLAN-FIRST (Discovery -> Plan -> Approval -> Execution -> Report), as 7 regras invioláveis e o comportamento esperado em cada fase. Ative quando o usuário invocar /fp: ou mencionar "first-plan", "context compilation", "discovery…

vynazevedo/first-plan · 81 tokens

first-plan-reconciliation

Skill que define Spec-Code Reconciliation - matching contínuo entre artefatos de intenção (docs, specs, JIRA, GitHub issues) e implementação (código, testes, PRs). Use durante Discovery e em /fp:check para identificar feature ja implementada, em flight, drifted ou abandonada.

vynazevedo/first-plan · 70 tokens

first-plan-semantic-reuse

Skill que faz busca semantica via BM25 sobre o indice de simbolos do projeto. Substitui grep do reuse-index quando o engine nativo esta disponivel. Encontra "preciso de validacao de email" mesmo se a funcao se chama validateEmailRFC. Use durante /fp:reuse e /fp:plan para identificar componentes reusaveis com matching…

vynazevedo/first-plan · 88 tokens