New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Delegating Work

by mvschwarz in mvschwarz/openrig

Decides who should do a task: do it yourself, spawn a subagent, or route it to an agent that already holds the context, by asking how much a blank slate must read in.

Apache-2.0Auto-check passedAgent Workflows

Install Delegating Work

skills CLI
$ npx skills add mvschwarz/openrig --skill delegating-work -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install mvschwarz/openrig delegating-work --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/mvschwarz/openrig.git skills-src && mkdir -p .claude/skills && cp -r skills-src/packages/daemon/assets/plugins/openrig-core/skills/delegating-work .claude/skills/delegating-work && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
delegating-work
GitHub stars
5.9k
Token cost
~1.2k tokens
SKILL.md length
653 words
Files
1
Skills in repo
49
Repo updated
First seen
Licence
Apache-2.0

At a glance

Decides who should do a task: do it yourself, spawn a subagent, or route it to an agent that already holds the context, by asking how much a blank slate must read in.

  • Deciding whether to spawn a subagent or hand a task to an agent that already has the context
  • SKILL.md covers The core question: context…, The decision, Subagents are underused —… and The failure mode — the part…, plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Delegating research or log scanning that a prompt can fully describe

What it does

The skill reduces delegation to a context question: how much would a blank slate have to read in to do this correctly? A lot means routing the task to a real agent in the team that already holds the context, such as a reviewer, QA or a long-running implementer. A little means spawning a subagent. When unsure, it favors a real agent or doing the work yourself.

It also pushes subagents for self-contained work that a prompt can fully specify, like tracing, research, grounding passes, summarizing, scanning logs, searching, fetching and mechanical extraction with citations. The failure it targets is the blank-slate subagent that returns a plausible but false conclusion because of unknown unknowns, which is worse than no summary. A practical test asks whether a wrong-but-plausible answer would be detectable by the requester; if not, the task belongs with an agent that holds the context. The mechanics of fanning out belong to other skills, dispatching-parallel-agents and subagent-driven-development.

When your agent uses it

  • Deciding whether to spawn a subagent or hand a task to an agent that already has the context
  • Delegating research or log scanning that a prompt can fully describe
  • Avoiding false conclusions from under-briefed subagents

Example prompts

  • “Should I spawn a subagent to review this auth change, or hand it to the reviewer who knows the project?”
  • “Delegate the log scan to a subagent, but first check whether a wrong answer would be detectable.”
  • “Who should investigate the flaky deployment tests: me, a subagent or the QA agent?”

What it can do on your machine

Read from SKILL.md and the folder at commit 1f69831. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Delegating Work loads about 1.2k tokens when it runs. Until then it costs about 133 tokens; SKILL.md has 653 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~133
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from mvschwarz/openrig at commit 1f69831, republished under its Apache-2.0 licence (© mvschwarz). 653 words, ~1,182 tokens.

Download SKILL.mdSave it as .claude/skills/delegating-work/SKILL.md (or your agent's skills folder).
name
delegating-work
description
Use when you have a task and must decide WHO does it — yourself, a spawned subagent, or another agent in the topology that already holds the context. The rule: how much would a blank slate have to read in to do this correctly? A lot → route to a context-holding agent; a little → subagent; unsure → a real agent or yourself. NOT the mechanics of fanning out (that's dispatching-parallel-agents / subagent-driven-development) — this is the who/whether decision, and the failure mode that makes teams abandon subagents.

Delegating work — who should do this task?

The core question: context performance

Getting work done well is a context problem. The agent best suited to a task is the one who already holds the context that task requires. Before you spawn a subagent or grind it out yourself, ask who that is.

The decision

Ask: how much would a blank slate have to read in before it could do this correctly?

  • A lot to read in → route to a real agent in the topology that already holds it. This is what the role structure is FOR — reviewers, QA, implementers who have been on a project over time. An agent that already understands the work produces a better, safer result than any amount of briefing.
  • A little — a prompt plus light grounding is enough → spawn a subagent.
  • Genuinely unsure → err toward a real agent, or do it yourself.

Subagents are underused — reach for them far more

For self-contained work that is fully specifiable in the prompt, spawn a subagent instead of spending your own context: tracing, research, grounding passes, summarizing, scanning log files, searching, fetching, web search, mechanical extraction with citations. This is the common shape and it is under-used.

The failure mode — the part that matters most

Subagents start as blank slates, and you cannot anticipate everything they need to know. Give one a task where there is a lot to understand and it will have blind spots it does not know it has — it will complete the task and return a false conclusion, not from weakness but because it lacked the context to know what "correct" even looked like.

This is the unknown-unknowns problem, and it is the single most common subagent failure: a poorly-contextualized summary is worse than no summary, because it arrives looking like an answer. Overreliance on subagents for context-heavy work causes more problems than it solves — and a team burned by it stops using subagents at all, which is the wrong correction. The fix is not "avoid subagents"; it is "match the task to the context it needs."

The practical test

Before delegating to a blank slate, ask: would a wrong-but-plausible answer here be detectable? If the requester cannot check the result against something they already know — a citation they can open, a count they can re-run — the blind-spot risk is unacceptable, and that task belongs with an agent that holds the context.

Show full SKILL.md (255 more words)Show less

Worked examples

  • GOOD (→ subagent): extract how four apps implement a UI mechanism, with file:line citations and an explicit instruction to report facts, not recommendations. Self-contained; the requester can verify the citations.
  • BAD to delegate blind (→ routed to the context-holder): an independent security re-sweep of a rewritten git branch, where knowing which commit range must stay byte-identical, and that "lightly obfuscated real values" is the thing to hunt, takes a paragraph to explain and one sentence to get wrong. It went to the agent already holding the context.

It generalizes

This is really "route work to whoever holds the context," with subagents as the option for work that needs none. The audience is every agent — implementers and QA seats make this call as much as orchestrators do.

Hand over intent, not instructions

Whoever does the work, give them the goal, why it matters, the context you hold and where to find more, then let them decide how. When you have the requester's own words, pass them on instead of compressing them into a list of steps. A capable agent with the goal builds better than one painting inside a narrow spec, which gets exactly what was written and not what was wanted. Keep exact instructions for the few things that must be exact, and say why.

Once you've decided

  • Decided on subagents for 2+ independent tasks → dispatching-parallel-agents (the fan-out mechanics).
  • Subagents executing a plan's independent tasks → subagent-driven-development.
  • Routing to a real agent you will direct over multiple rounds → directing-partner-agents.
  • The right context-holder is the human → human-in-the-loop.

© mvschwarz, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in packages/daemon/assets/plugins/openrig-core/skills/delegating-work of mvschwarz/openrig.

Open the folder on GitHubat commit 1f69831

Compare with similar skills

Delegating Work next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Delegating Work compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Delegating Work this skillmvschwarz/openrig5.9k—~1.2kAutomated safety check: PassApache-2.0
Paseo Advisor Second Opiniongetpaseo/paseo20k1 repos~756Automated safety check: PassCustom licence
O2 Review Loopopenobserve/openobserve22k—~3.7kAutomated safety check: PassAGPL-3.0
Kimi Code DelegationCherryHQ/cherry-studio52k1 repos~504Automated safety check: PassAGPL-3.0
Harness Agent Team Designerrevfactory/harness9.1k—~4.5kAutomated safety check: PassApache-2.0
ClawTeam Multi-Agent Swarmwin4r/ClawTeam-OpenClaw1.5k1 repos~2.9kAutomated safety check: PassMIT

Similar skills

  • Paseo Advisor Second Opinion

    getpaseo/paseo

    Launches one separate agent through Paseo to give a second opinion on the current task, with a self-contained briefing and no permission to edit files.

    20k GitHub starsUsed in 1 repo~756 tokens
    Agent WorkflowsAuto-check passed

  • O2 Review Loop

    openobserve/openobserve

    Splits a change into planner, coder and independent reviewer roles: you confirm a spec, a subagent implements it, and a separate reviewer checks each round's local WIP commit.

    22k GitHub stars~3.7k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Kimi Code Delegation

    CherryHQ/cherry-studio

    Delegates one bounded repository task to Kimi Code in non-interactive prompt mode and reads back the final result from its JSON event stream.

    52k GitHub starsUsed in 1 repo~504 tokens
    Agent WorkflowsAuto-check passed

  • Harness Agent Team Designer

    revfactory/harness

    Designs a project-specific agent harness: defines specialist agents, writes the skills they follow, picks an execution mode and model for each, and keeps the setup maintained.

    9.1k GitHub stars~4.5k tokensUpdated 10 days ago
    Agent WorkflowsAuto-check passed

  • ClawTeam Multi-Agent Swarm

    win4r/ClawTeam-OpenClaw

    Launches a swarm of specialist Hermes agents in git-worktree-isolated tmux windows with a kanban board and file-based inboxes, using built-in templates like hedge-fund and code-review.

    1.5k GitHub starsUsed in 1 repo~2.9k tokens
    Agent WorkflowsAuto-check passed

  • Sub-Agent Delegation

    codewhale-hq/Codewhale

    Guides when and how to split multi-step coding, research or verification work into focused sub-agent runs while the parent keeps integration and final checks.

    41k GitHub stars~790 tokensUpdated today
    Agent WorkflowsAuto-check passed

More from mvschwarz/openrig

All 49 skills in this repo

  • OpenRig Upgrade Procedure

    mvschwarz/openrig

    Walks an agent through upgrading the OpenRig CLI and daemon one observed step at a time, keeping live seats alive and reconciling managed plugin files.

    5.9k GitHub starsUsed in 1 repo~2.9k tokens
    Auto-check passed

  • Agent Refocusing

    mvschwarz/openrig

    Re-grounds a long-running agent in the current product outcome by running a path-based trace to the root of its topology and work trees.

    5.9k GitHub stars~864 tokensUpdated today
    Auto-check passed

  • OpenRig Software Factory

    mvschwarz/openrig

    Helps set up a continuing agent software team for a real repository with OpenRig, choosing between manual work, queue handoffs and an explicit Workflow.

    5.9k GitHub stars~2.6k tokensUpdated today
    Auto-check passed

  • Addressable Markdown Loader

    mvschwarz/openrig

    Loads one section of a Markdown file by its path#h2-slug address with a bundled resolver script, for use outside OpenRig's context library.

    5.9k GitHub starsUsed in 1 repo~341 tokens
    Auto-check passed

  • Seat Continuity and Handover

    mvschwarz/openrig

    Separates a stable agent seat's identity from its changing occupant, and records honest, two-part provenance whenever one occupant replaces another.

    5.9k GitHub stars~2.1k tokensUpdated today
    Auto-check passed

  • Cross Host Rig Commands

    mvschwarz/openrig

    A skill your agent uses when addressing a registered remote OpenRig host, choosing its transport, or interpreting a cross-host result.

    5.9k GitHub starsUsed in 1 repo~1.3k tokens
    Auto-check passed

Categories

Questions about Delegating Work

What does Delegating Work do?

Decides who should do a task: do it yourself, spawn a subagent, or route it to an agent that already holds the context, by asking how much a blank slate must read in. The skill reduces delegation to a context question: how much would a blank slate have to read in to do this correctly? A lot means routing the task to a real agent in the team that already holds the context, such as a reviewer, QA or a long-running implementer.

When should I use Delegating Work?

Delegating Work fits situations like: deciding whether to spawn a subagent or hand a task to an agent that already has the context; delegating research or log scanning that a prompt can fully describe; avoiding false conclusions from under-briefed subagents.

How do I install Delegating Work in Claude Code?

Run `npx skills add mvschwarz/openrig --skill delegating-work -a claude-code`. Or copy the skill folder (packages/daemon/assets/plugins/openrig-core/skills/delegating-work in mvschwarz/openrig) into .claude/skills/delegating-work in your project. Claude Code loads it when a task matches its description.

How do I install Delegating Work in Codex?

Run `npx skills add mvschwarz/openrig --skill delegating-work -a codex`. Or copy the skill folder (packages/daemon/assets/plugins/openrig-core/skills/delegating-work in mvschwarz/openrig) into .agents/skills/delegating-work in your project. Codex loads it when a task matches its description.

Can I use Delegating Work in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add mvschwarz/openrig --skill delegating-work -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/delegating-work, .gemini/skills/delegating-work, .github/skills/delegating-work and .opencode/skills/delegating-work in your project.

What does Delegating Work need to run?

SKILL.md names no scripts, command-line tools or credentials: Delegating Work is instructions for the agent only.

Does Delegating Work access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Delegating Work safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Delegating Work use?

Delegating Work is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Delegating Work use?

About 1.2k tokens (SKILL.md is roughly 4.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Delegating Work?

Skills that share tags, products or a category with Delegating Work: Paseo Advisor Second Opinion (getpaseo/paseo, 20k stars), O2 Review Loop (openobserve/openobserve, 22k stars), Kimi Code Delegation (CherryHQ/cherry-studio, 52k stars) and Harness Agent Team Designer (revfactory/harness, 9.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Delegating Work?

mvschwarz (a GitHub user) maintains it in mvschwarz/openrig, which has 5,854 GitHub stars. The repository holds 49 skills in this directory. The repository was last updated on October 8, 2026.

Source: mvschwarz/openrig on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.