Home / yeisonrestrepo / code-conductor · skills/agent-delegation/SKILL.md · GitHub

agent-delegation skillA

agent-delegation is agent-read markdown (skill) from yeisonrestrepo/code-conductor: Rules for when and how to spawn sub-agents: Explore for 3+ file reads, parallel agents for independent tasks, summaries only — raw output never enters main context.

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

What the file says

# Agent Delegation

Keep the main context clean. Raw file contents, grep output, and intermediate data never enter the main context. Sub-agents process data and return summaries only.

## When to Spawn

### Explore Sub-Agent
**Condition:** Task requires reading 3+ files to answer one question, or codebase exploration precedes implementation.

```javascript
// Use the Agent tool with these parameters:
Agent({
  subagent_type: "Explore",
  description: "<10-word description of the lookup>",
  prompt: "<question>. Search across relevant files. Return a summary of ≤200 words. Do not include raw file contents."
})
```

### Parallel Agents
**Condition:** 2+ implementation tasks with no shared state, each describable independently.

Send both Agent calls in a single message so they run in parallel:

```javascript
// Use the Agent tool twice in the same message — they run in parallel:
Agent({ description: "Task A", prompt: "... Return a summary of ≤200 words." })
Agent({ description: "Task B", prompt: "... Return a summary of ≤200 words." })
```

## Output Contract
- Every sub-agent returns ≤200 words to the main context.
- The main context acts only on summaries, not raw data.
…

Read the whole file at its exact version.

How to install

Latest version
mdr add yeisonrestrepo/code-conductor/agent-delegation@git:20260922.8fd811c
Exact content
mdr add yeisonrestrepo/code-conductor/agent-delegation@sha256:4f781a26adc91596

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_gwyeccu6bf5ovb6n.svg)](https://markdownregistry.com/a/art_gwyeccu6bf5ovb6n)

1 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260922.8fd811c latest2026-09-22 8fd811c 1,696 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (1696 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

yeisonrestrepo/code-conductor · 7 stars · license MIT · pushed 2026-09-22 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_gwyeccu6bf5ovb6n
GET https://markdownregistry.com/api/v1/resolve?ref=yeisonrestrepo/code-conductor/agent-delegation
GET https://markdownregistry.com/api/v1/blob/4f781a26adc91596ca3fa9ef8ae8d3b38da6802e985e77ea278d78f3692da3f2

Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

More from yeisonrestrepo/code-conductor

CLAUDE.md claude
yeisonrestrepo/code-conductor · CLAUDE.md
git:20260623.46b26a5 · audit A · 7 stars
CLAUDE.md@global claude
yeisonrestrepo/code-conductor · global/CLAUDE.md
git:20260922.8fd811c · audit A · 7 stars
CLAUDE.md@project-template claude
yeisonrestrepo/code-conductor · project-template/CLAUDE.md
git:20260922.8fd811c · audit A · 7 stars
code-simplifier skill
yeisonrestrepo/code-conductor · skills/code-simplifier/SKILL.md · Always-active simplicity rules: no speculative abstractions, one job per function, max 30 lines, flat over nested with…
git:20260922.8fd811c · audit A · 7 stars
critical-review skill
yeisonrestrepo/code-conductor · skills/critical-review/SKILL.md · 4-phase adversarial review protocol: pre-flight analysis, adversarial execution check, self-correction loop, and…
git:20260922.8fd811c · audit A · 7 stars
memory-first skill
yeisonrestrepo/code-conductor · skills/memory-first/SKILL.md · Lookup chain enforced before any file read or search: project memory, code graph, grep/glob, Explore sub-agent…
git:20260922.8fd811c · audit A · 7 stars
verbosity skill
yeisonrestrepo/code-conductor · skills/verbosity/SKILL.md · Response verbosity protocol: reads the level from ~/.claude/memory/verbosity.md and applies the MIN, INFO or VERBOSE…
git:20260922.8fd811c · audit A · 7 stars

Every file in yeisonrestrepo/code-conductor

Other files named agent-delegation

agent-delegation skill
qwenlm/qwen-code · packages/core/src/skills/bundled/agent-delegation/SKILL.md · Reference for briefing a subagent or a fork — what to put in the prompt, what not to delegate, and a worked example…
git:20260922.c650a3e · audit A · 28,110 stars

Browse by kind, by grade A, or by owner.