delegate

A task-delegation workflow that starts a separate child coding agent with its own working context and a defined task envelope.

In plain words
What is it for?
Use it to split work across agents, run parallel investigations, or assign a task that needs a different skill or verification approach.
Why use it?
It lets large or isolated tasks be worked on independently and checked separately.

Skill for Claude CodeCodex

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/usefulmove/enso/delegate
Any agent
npx skills add usefulmove/enso --skill delegate
Clone the repo
git clone --depth 1 https://github.com/usefulmove/enso

Made for: Claude Code, Codex.

Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 359 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 $0.00042 $0.00359
Opus 5 $0.00021 $0.00179
Sonnet 5 $0.00008 $0.00072
Haiku 4.5 $0.00004 $0.00036

Measured yesterday against content hash 7eb22ecb99ce, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

delegate 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 yesterday.

The scan reads SKILL.md. This mod also ships 1 executable file (delegate.sh), 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/delegate/SKILL.md · 40 lines

What it actually says

Delegate

Spawn a child pi agent from within a running harness. The child runs in its own context directory and returns through an explicit return path.

Interface (the contract)

Parameter Description
context_dir The child's working directory. Inherits parent .pi/skills/ unless overridden.
prompt The task envelope: goal, acceptance criteria, and any loaded skills.
return_path stdout, <context_dir>/.pi/return.md, or a named tmux session.
name Optional tmux session name for re-attachment.

Canonical invocation

pi -p --cwd ./runs/<task-id> <<< "$PROMPT"

Or wrapped:

./delegate.sh <context-dir> <prompt-file> [session-name]

Patterns

  • Fan-out: Spawn multiple agents against sibling directories; collect return.md files.
  • Pipeline: Child stdout piped into next child stdin, or into parent post-processor.
  • Supervisor: Named tmux session for long-running work. Re-attach with tmux attach -t <name>.

Why This Skill Exists

The harness is self-composing. An agent that can invoke pi via bash is a Lisp eval. Without a documented envelope every spawn is bespoke. This skill provides the minimal contract so that recursive delegation remains inspectable and portable across enso instances.

Files

What ships with it

1 file 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. yesterday First seen · 40 lines · 42 tokens per session scan A 7eb22ecb99ce

Subscribe to this mod's changes

delegate is a skill published in the GitHub repository usefulmove/enso (2 stars, last pushed 2mo ago), licensed MIT. It adds 42 tokens to every session and 359 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 2026-08-31.

Related

Other skills, from other repositories

harness-creator

Build, audit, and improve harnesses that make AI coding agents reliable: AGENTS.md/CLAUDE.md instruction files, feature/state tracking, verification gates, scope boundaries, session handoff, memory persistence, context budgets, tool-permission safety, and multi-agent coordination. Use this whenever a coding agent is…

walkinglabs/learn-harness-engineering · 142 tokens

harness

하네스를 구성합니다. 전문 에이전트를 정의하며, 해당 에이전트가 사용할 스킬을 생성하는 메타 스킬. (1) '하네스 구성해줘', '하네스 구축해줘' 요청 시, (2) '하네스 설계', '하네스 엔지니어링' 요청 시, (3) 새로운 도메인/프로젝트에 대한 하네스 기반 자동화 체계를 구축할 때, (4) 하네스 구성을 재구성하거나 확장할 때, (5) '하네스 점검', '하네스 감사', '하네스 현황', '에이전트/스킬 동기화' 등 기존 하네스 운영/유지보수 요청 시 사용.

revfactory/harness · 170 tokens

pr-review

Review a GitHub pull request and post a verdict comment. Stateful — if a previous review comment exists, review only the new commits since the last review and track whether prior findings were addressed. Focus on code cleanliness, duplication, and docs sync. Use when user says "review this PR", "check the PR", "leave…

lee-to/aif-handoff · 83 tokens

new-plugin

Factory line for adding a new HAR verification plugin (like playwright or rocketsim) for any framework — research the framework docs, build the template under src/templates/plugins/, register it everywhere, validate on a real repository, and open a PR. Use when asked to add/create a plugin, plugin template, or…

os-factory/har · 89 tokens

cc10x-router

THE ONLY ENTRY POINT FOR CC10X. Activate this skill for build, debug, review, and plan requests. Use when the user asks to implement, fix, review, plan, test, refactor, or continue code work. Trigger keywords: build, implement, create, write, add, review, audit, debug, fix, error, bug, broken, plan, design, architect…

romiluz13/cc10x · 125 tokens

building

Implementation skill for writing production code with TDD. Covers the RED-GREEN-REFACTOR cycle, false-RED detection, vertical slicing, scope escalation, test process discipline, and code generation patterns. Loaded by component-builder and bug-investigator.

romiluz13/cc10x · 53 tokens