Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

agent toolingby agent-field

Delegate scoped issues to SWE-AF

agent-field/delegate-issue

Source agent-field/swe-af ↗License Apache-2.0

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.

SkillScore59Maintained

Automatic

AI Engineer pack

Last verified 8/14/2026

What it changes

Passed 9 of 16 test cases with the skill, and 6 of 16 without it.

Without skill36%

With skill59%

Checks it passed that the model alone missed

Rejects immediate verbatim retries of the original payload
Runs git diff main...issue/99-fix-auth to inspect the branch diff
Recommends using a planning skill such as swe-planner.build instead

and 4 more in the full report

6 fixed7 passed either way8 still failing1 broke

Pass-rate lift: +23 pp
Tokens: +21%
Agent turns: 0%
Response time: -53%

Model gemini-3.6-flashMeasured 8/14/2026v113 of 22 cases passed with skill · 16 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/agent-field-delegate-issue/SKILL.md https://app.decimal.ai/s/agent-field-delegate-issue/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add agent-field-delegate-issue, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/agent-field-delegate-issue/ and pins it in .decimal/skills.lock

decimalai skills add agent-field-delegate-issue

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/agent-field-delegate-issue/SKILL.md https://app.decimal.ai/s/agent-field-delegate-issue/SKILL.md

Raw file: /s/agent-field-delegate-issue/SKILL.md ↗ · machine-readable summary at /s/agent-field-delegate-issue.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 6

Prompt

Show a shell command to list distinct available sub-harness node names registered on the default local AgentField control plane.

What was checked, without and with the skill
Checked	Without skill	With skill
Executes a curl request targeting /api/v1/nodes filtered for swe node identifiers	Missed	Passed

case-19 · gemini-3.6-flash · 8/14/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md111 linessingle file

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)

# 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).

Track record

Benchmark

9 / 16

test cases passed, vs 6 / 16 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

agent-field / swe-af

.claude/skills/delegate-issue/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 8/3/2026Version v1

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Delegate scoped issues to SWE-AF

When to delegate (and when not to)

Preflight (once per session)

Compose the issue

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills