SWE-AF is a runtime that coordinates AI agents playing software-development roles such as product manager, architect, coder, reviewer, and tester to produce and ship code. Developers use it to automate work in one repository or coordinate changes across multiple repositories through an API or command-line interface.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Agent-Field/SWE-AF --skill delegate-issuegit clone --depth 1 https://github.com/Agent-Field/SWE-AFWrote 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.
[](https://agentmods.dev/skills/agent-field/swe-af/delegate-issue)<a href="https://agentmods.dev/skills/agent-field/swe-af/delegate-issue"><img src="https://agentmods.dev/badge/skills/agent-field/swe-af/delegate-issue/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.
<a href="https://agentmods.dev/skills/agent-field/swe-af/delegate-issue"><img src="https://agentmods.dev/badge/skills/agent-field/swe-af/delegate-issue.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Data Exfiltration · line 53 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00082 | $0.01182 |
| Opus 5.5 | $0.00033 | $0.00473 |
| Sonnet 5.5 | $0.00016 | $0.00236 |
| Haiku 4.5 | $0.00008 | $0.00118 |
Grade A, and why
delegate-issue scanned grade A with 1 finding 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 1mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s ${AGENTFIELD_SERVER:-http://localhost:8080}/api/v1/nodes | grep -o '"swe-[a-z-]*"' | sort -u How it starts
The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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).
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.
Fire the delegation (async, never sync)
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
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.
- 1mo ago First seen · 117 lines · 82 tokens per session scan A 678bc4256b3e
delegate-issue is a skill published in the GitHub repository Agent-Field/SWE-AF (1,034 stars, last pushed 10d ago), licensed Apache-2.0. It adds 82 tokens to every session and 1,182 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
build-teaql-app
Build or change a TeaQL application in Java, Rust, Go, Swift, Python, C#/.NET, or TypeScript, including Kotlin/JVM applications that consume Java-generated libraries. Mandatory order: first draft and save a complete KSML model, then verify the client and evaluate that saved model, repair it through repeated evaluation…
red-blue-review
An optional adversarial review process for requirement analyses. One agent produces the analysis, while an independent reviewer checks its report, database definitions, alignment records, and requirements for missed issues.
requirement-alignment
A process for analyzing product requirements and turning them into clear technical artifacts such as state machines, sequence diagrams, decision tables, and database definitions. It resolves uncertainty through code evidence, recorded inferences, or explicit human decisions.
using-intent-gate
Use when starting any conversation in a project that has the intent-gate MCP - establishes requirement intent-alignment discipline (never guess on ambiguity), where the analysis playbook lives, and the two optional add-ons (red-blue adversarial review skill, intent-gate-service sister service for DingTalk group…
contract-coding
An extra coding workflow that uses an approved written requirement as the source for implementation. It checks which requirement applies and maps diagrams, rules, and database tables to code.
add-wshcmd
Guide for adding new wsh commands to Wave Terminal. Use when implementing new CLI commands, adding command-line functionality, or extending the wsh command interface.