Agent skill

Delegate Issue

by Agent-Field in Agent-Field/SWE-AF

Delegate well-scoped coding issues to a SWE-AF node as a cheap sub-harness via implementissue, then collect and merge the returned branches.

Apache-2.0Auto-check passedAgent Workflows

Install Delegate Issue

skills CLI
$ npx skills add Agent-Field/SWE-AF --skill delegate-issue -a claude-code

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

GitHub CLI
$ gh skill install Agent-Field/SWE-AF delegate-issue --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/Agent-Field/SWE-AF.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/delegate-issue .claude/skills/delegate-issue && 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
delegate-issue
GitHub stars
1k
Token cost
~1.1k tokens
SKILL.md length
470 words
Files
1
Skills in repo
2
Repo updated
First seen
Licence
Apache-2.0

At a glance

Delegate well-scoped coding issues to a SWE-AF node as a cheap sub-harness via implementissue, then collect and merge the returned branches.

  • The user asks to offload
  • SKILL.md covers When to delegate (and when not…, Preflight (once per session), Compose the issue and Fire the delegation (async,…, plus 2 more sections
  • Calls curl and git; needs AGENTFIELD_API_KEY
  • Fan out scoped tasks to SWE-AF / swe-planner / swe-fast

What it does

Delegate Issue is an agent skill from Agent-Field/SWE-AF. Delegate well-scoped coding issues to a SWE-AF node as a cheap sub-harness via implementissue, then collect and merge the returned branches. Use when the user asks to offload, delegate, or fan out scoped tasks to SWE-AF / swe-planner / swe-fast, or when several independent, fully-specified changes could run in parallel without burning main-harness tokens.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows. It works with OpenRouter. The repository describes itself as: Autonomous software engineering fleet of AI agents for production-grade PRs on AgentField: plan, code, test, and ship. The licence is Apache-2.0.

When your agent uses it

  • The user asks to offload
  • Fan out scoped tasks to SWE-AF / swe-planner / swe-fast
  • Several independent
  • Fully-specified changes could run in parallel without burning main-harness tokens

Example prompts

  • “/delegate-issue”

Requirements

  • A credential in AGENTFIELD_API_KEY

What it can do on your machine

Read from SKILL.md and the folder at commit 17d3160. 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

    Shell commands in SKILL.md call:

    • curl
    • git

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

  • Network

    No URLs in SKILL.md. Its commands use curl and git, which can reach the network depending on how they are called.

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

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • AGENTFIELD_API_KEY

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

Context cost

Delegate Issue loads about 1.1k tokens when it runs. Until then it costs about 93 tokens; SKILL.md has 470 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~93
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

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 Agent-Field/SWE-AF at commit 17d3160, republished under its Apache-2.0 licence (© Agent-Field). 470 words, ~1,144 tokens.

Download SKILL.mdSave it as .claude/skills/delegate-issue/SKILL.md (or your agent's skills folder).
name
delegate-issue
description
Delegate well-scoped coding issues to a SWE-AF node as a cheap sub-harness via implement_issue, then collect and merge the returned branches. Use when the user asks to offload, delegate, or fan out scoped tasks to SWE-AF / swe-planner / swe-fast, or when several independent, fully-specified changes could run in parallel without burning main-harness tokens.

Delegate scoped issues to SWE-AF

You are the main harness. SWE-AF is the sub-harness: it implements one fully-scoped issue per call on an isolated branch, using cheap models, and hands the branch back. You keep planning, merging, review, and CI.

When to delegate (and when not to)

Delegate an issue only when ALL of these hold:

  • The change is fully specified: you can name the files, the behavior, and the acceptance criteria without the sub-harness needing to plan anything.
  • It is independent of your other in-flight edits (no shared files with another delegation or with your own uncommitted work).
  • The repo is reachable by the SWE-AF node (same machine or shared volume) and has at least one commit.

Do NOT delegate: vague feature requests (use swe-planner.build instead), changes to files you are editing yourself right now, or anything whose spec you'd have to guess. Garbage spec in → garbage branch out.

Preflight (once per session)

bash
# Control plane up and the node registered?
curl -s ${AGENTFIELD_SERVER:-http://localhost:8080}/api/v1/nodes | grep -o '"swe-[a-z-]*"' | sort -u

Pick the node (swe-planner, swe-fast, or the -go twins — the implement_issue surface is identical). If an X-API-Key is configured for the control plane, add -H "X-API-Key: $AGENTFIELD_API_KEY" to every curl.

Compose the issue

Write the spec from YOUR context — the whole point is that the sub-harness skips planning. Required: title, description. Strongly recommended: acceptance_criteria (verifier checks these), files_to_modify / files_to_create, testing_strategy. Set needs_deeper_qa: true only for risky/interface-heavy changes (doubles the review cost per iteration).

Commit (or at least be aware of) your local state first: the issue branch is created from the committed base, so your uncommitted edits are invisible to it.

Show full SKILL.md (215 more words)Show less

Fire the delegation (async, never sync)

bash
curl -s -X POST ${AGENTFIELD_SERVER:-http://localhost:8080}/api/v1/execute/async/swe-planner.implement_issue \
  -H "Content-Type: application/json" \
  -d @issue.json

with issue.json shaped like:

json
{
  "input": {
    "issue": {
      "title": "...",
      "description": "...",
      "acceptance_criteria": ["..."],
      "files_to_modify": ["..."],
      "testing_strategy": "..."
    },
    "repo_path": "/abs/path/to/checkout",
    "base_branch": "main",
    "config": { "models": { "default": "haiku" } }
  }
}

Capture execution_id from the 202 response. Track every in-flight delegation in your todo list (one item per execution_id).

Cap fan-out at 3 concurrent delegations per repo unless the user explicitly asks for more — each one is a paid multi-agent run, and an unbounded loop of delegations is a surprise bill. Never re-fire a delegation just because it is slow; poll it.

Track progress

bash
# Terminal status + result
curl -s $SERVER/api/v1/executions/<execution_id>
# Live agent notes (what the coder/reviewer are doing)
curl -s $SERVER/api/v1/executions/<execution_id>/notes

Poll on a backoff (30–60s is plenty; a typical issue lands in 10–30 min). Batch-check several: POST /api/v1/executions/batch-status with {"execution_ids": [...]}.

Collect the result

The execution's result is an IssueBuildResult:

  • success: true → branch holds the implementation (issue/<build_id>-<slug>). Review the diff yourself (git diff main...<branch>), run YOUR test gate, then merge: git merge --no-ff <branch> (or cherry-pick), and delete the branch.
  • success: false with a branch → partial work was salvaged. Triage: read verification / debt_items / error_message, then either fix forward on the branch yourself, re-delegate with a sharpened spec, or drop the branch (git branch -D).
  • success: false with branch: "" → nothing usable was produced; the sub-harness already cleaned up. Sharpen the spec before retrying — do not retry verbatim.

After merging all accepted branches, run the project's full test suite once yourself before reporting done. The sub-harness verifier is a per-issue check, not your integration gate.

© Agent-Field, 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 .claude/skills/delegate-issue of Agent-Field/SWE-AF.

Open the folder on GitHubat commit 17d3160

Compare with similar skills

Delegate Issue 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.

Delegate Issue compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Delegate Issue this skillAgent-Field/SWE-AF1k—~1.1kAutomated safety check: PassApache-2.0
LLM Councilrohitg00/pro-workflow2.9k—~1.1kAutomated safety check: PassNone
Droid Model Setupnikships/droidproxy122—~2kAutomated safety check: PassMIT
Claudish UsageMadAppGang/claudish1k—~9kAutomated safety check: PassNone
Watchmen Setupfirstbatchxyz/watchmen296—~1.2kAutomated safety check: NotesMIT
Deliberationantonbabenko/deliberation169—~3.8kAutomated safety check: PassMIT

Similar skills

  • LLM Council

    rohitg00/pro-workflow

    Provider-agnostic multi-LLM deliberation. An agent skill from rohitg00/pro-workflow.

    2.9k GitHub stars~1.1k tokensUpdated 8 days ago
    Agent WorkflowsAuto-check passed
  • Droid Model Setup

    nikships/droidproxy

    Configure any third-party model as a custom model in Factory Droid (~/.factory/settings.json): resolve specs (context window, max output tokens, reasoning efforts), write a safe config entry, set…

    122 GitHub stars~2k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Claudish Usage

    MadAppGang/claudish

    CRITICAL - Guide for using Claudish CLI ONLY through sub-agents to run Claude Code with any AI model (OpenRouter, Gemini, OpenAI, local models).

    1k GitHub stars~9k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • Watchmen Setup

    firstbatchxyz/watchmen

    Sets up watchmen on the current machine: installs the CLI, hands off the init wizard, wires the plugin and statusline into Claude Code and Codex, and verifies with doctor.

    296 GitHub stars~1.2k tokensUpdated 1 mo ago
    Agent WorkflowsAuto-check: notes
  • Deliberation

    antonbabenko/deliberation

    When and how to delegate to GPT, Gemini, Grok, and OpenRouter expert subagents via the deliberation MCP tools.

    169 GitHub stars~3.8k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Tlon Product Guide

    tloncorp/tlon-apps

    Answer questions about Tlon, Urbit, Tlon Messenger, Tlonbot, and OpenClaw — what they are, how they work, and how to use them.

    107 GitHub stars~11k tokensUpdated today
    Agent WorkflowsAuto-check passed

More from Agent-Field/SWE-AF

  • Swe Af

    Agent-Field/SWE-AF

    Autonomous engineering team runtime — one API call spins up coordinated AI agents to scope, build, and ship software.

    1k GitHub stars~1.5k tokensUpdated 13 days ago
    Auto-check passed

Works with

Categories

Questions about Delegate Issue

What does Delegate Issue do?

Delegate well-scoped coding issues to a SWE-AF node as a cheap sub-harness via implementissue, then collect and merge the returned branches. Delegate Issue is an agent skill from Agent-Field/SWE-AF. Delegate well-scoped coding issues to a SWE-AF node as a cheap sub-harness via implementissue, then collect and merge the returned branches.

When should I use Delegate Issue?

Delegate Issue fits situations like: the user asks to offload; fan out scoped tasks to SWE-AF / swe-planner / swe-fast; several independent; fully-specified changes could run in parallel without burning main-harness tokens.

How do I install Delegate Issue in Claude Code?

Run `npx skills add Agent-Field/SWE-AF --skill delegate-issue -a claude-code`. Or copy the skill folder (.claude/skills/delegate-issue in Agent-Field/SWE-AF) into .claude/skills/delegate-issue in your project. Claude Code loads it when a task matches its description.

How do I install Delegate Issue in Codex?

Run `npx skills add Agent-Field/SWE-AF --skill delegate-issue -a codex`. Or copy the skill folder (.claude/skills/delegate-issue in Agent-Field/SWE-AF) into .agents/skills/delegate-issue in your project. Codex loads it when a task matches its description.

Can I use Delegate Issue 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 Agent-Field/SWE-AF --skill delegate-issue -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/delegate-issue, .gemini/skills/delegate-issue, .github/skills/delegate-issue and .opencode/skills/delegate-issue in your project.

What does Delegate Issue need to run?

Going by SKILL.md and its folder, Delegate Issue needs the command-line tools its instructions call (curl and git) and credentials named AGENTFIELD_API_KEY. Our summary lists: A credential in AGENTFIELD_API_KEY.

Does Delegate Issue access the network?

SKILL.md contains no URLs. Its commands use curl and git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Delegate Issue 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 Delegate Issue use?

Delegate Issue 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 Delegate Issue use?

About 1.1k tokens (SKILL.md is roughly 4.6k 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 Delegate Issue?

Skills that share tags, products or a category with Delegate Issue: LLM Council (rohitg00/pro-workflow, 2.9k stars), Droid Model Setup (nikships/droidproxy, 122 stars), Claudish Usage (MadAppGang/claudish, 1k stars) and Watchmen Setup (firstbatchxyz/watchmen, 296 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Delegate Issue?

Agent-Field (a GitHub organization) maintains it in Agent-Field/SWE-AF, which has 1,032 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on September 24, 2026.

Source: Agent-Field/SWE-AF on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.