how-to-delegate

how-to-delegate is a skill for Claude Code from Jamie-BitFlight/claude_skills. It costs 46 tokens per session (2,276 once invoked), scanned A, original, MIT.

A worksheet for orchestrators—people who coordinate coding agents—to prepare clear task assignments while leaving implementation choices to specialist agents.

In plain words
What is it for?
Use it before assigning work to sub-agents to record observations, success criteria, context, and delegation details.
Why use it?
It helps prevent vague delegations, missing context, wasted agent work, and unclear completion signals.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: mentions subagents.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is [Example: "Validation scripts in ./scripts/ — check README.md" or "Previous fixes documented in .tmp/reports/"].

Part of the agent-orchestration plugin — 4 skills shipped together

Good fit Use it before assigning work to sub-agents to record observations, success criteria, context, and delegation details.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/Jamie-BitFlight/claude_skills
agentmods
npx agentmods add skills/jamie-bitflight/claude_skills/how-to-delegate

Made for: Claude Code.

Or install agent-orchestration, the plugin that ships this one along with the rest of its 4 skills.

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 how-to-delegate

README.md
[![agentmods](https://agentmods.dev/badge/skills/jamie-bitflight/claude_skills/how-to-delegate/github.svg)](https://agentmods.dev/skills/jamie-bitflight/claude_skills/how-to-delegate)
Your own site
<a href="https://agentmods.dev/skills/jamie-bitflight/claude_skills/how-to-delegate"><img src="https://agentmods.dev/badge/skills/jamie-bitflight/claude_skills/how-to-delegate/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for how-to-delegate

Your own site · 80×15
<a href="https://agentmods.dev/skills/jamie-bitflight/claude_skills/how-to-delegate"><img src="https://agentmods.dev/badge/skills/jamie-bitflight/claude_skills/how-to-delegate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,276 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00046 $0.02276
Opus 5 $0.00023 $0.01138
Sonnet 5 $0.00009 $0.00455
Haiku 4.5 $0.00005 $0.00228

Measured 7d ago against content hash 65418fde5d25, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

how-to-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 7d 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.

plugins/agent-orchestration/skills/how-to-delegate/SKILL.md · 299 lines

How it starts

The opening of the file, as written. The whole thing — 299 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Delegation Preparation Worksheet

Workflow Reference: See the agent-orchestration skill for the complete delegation flow, DONE/BLOCKED signaling protocol, and agent selection guide.

CRITICAL: You are an orchestrator. Complete ALL steps before invoking the Agent tool. Incomplete preparation causes failed delegations, wasted agent context, and poor outcomes.

<user_instructions>$ARGUMENTS</user_instructions>


Conditional Execution

flowchart TD
    START[Skill loaded] --> CHECK{user_instructions content?}
    CHECK -->|Empty or literal $ARGUMENTS| WAIT[Complete Step 1 only\nState: 'Delegation framework loaded. Awaiting task.'\nSTOP — wait for user task]
    CHECK -->|Contains a task| FULL[Complete ALL steps 1–10\nFill every section with actual content\nDo NOT skip or summarize steps]

Core Delegation Principles

Your role as orchestrator — apply these throughout every step below:

  • Route observations and context between user and agents
  • Define measurable success criteria
  • Enable comprehensive agent discovery
  • NEVER pre-gather data agents will collect themselves
  • NEVER prescribe HOW agents should work (tools, steps, implementation)
  • ALWAYS state WHAT must be achieved and WHY it matters

Reason: Agents have 200k context windows and specialized expertise. Pre-gathering causes context rot and duplicates work. Prescribing HOW limits agents from discovering better solutions.


Step 1: Load Framework

ACTION: Activate the agent-orchestration skill NOW:

Skill(skill: "agent-orchestration:agent-orchestration")

Then load domain-specific skills based on task type:

flowchart TD
    START[Task Received] --> ORCH[Load agent-orchestration]
    ORCH --> CHECK{Task domain?}

    CHECK -->|Python code| PY[python3-development]
    CHECK -->|Linting/code quality| LINT[holistic-linting]
    CHECK -->|GitLab CI| GL[gitlab-skill]
    CHECK -->|Git commits| CC[conventional-commits]
    CHECK -->|Package management| UV[uv]
    CHECK -->|Documentation| DOCS[mkdocs]
    CHECK -->|Pre-commit hooks| PRE[pre-commit]
    CHECK -->|Other domain| OTHER[Search available_skills list]

    PY & LINT & GL & CC & UV & DOCS & PRE & OTHER --> PROCEED[Proceed to Step 2]

Read the full file on GitHub · 299 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. 7d ago First seen · 299 lines · 46 tokens per session scan A 65418fde5d25

Subscribe to this mod's changes

how-to-delegate is a skill published in the GitHub repository Jamie-BitFlight/claude_skills (66 stars, last pushed yesterday), licensed MIT. It adds 46 tokens to every session and 2,276 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 2026-09-03.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens