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 docsgit 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/docs)<a href="https://agentmods.dev/skills/agent-field/swe-af/docs"><img src="https://agentmods.dev/badge/skills/agent-field/swe-af/docs/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/docs"><img src="https://agentmods.dev/badge/skills/agent-field/swe-af/docs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, 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 40 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.
- medium Data Exfiltration · line 110 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 | $0.00027 | $0.01585 |
| Opus 5.5 | $0.00011 | $0.00634 |
| Sonnet 5.5 | $0.00005 | $0.00317 |
| Haiku 4.5 | $0.00003 | $0.00159 |
Grade A, and why
swe-af 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 -X POST http://localhost:8080/api/v1/execute/async/swe-planner.build \ How it starts
The opening of the file, as written. The whole thing — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SWE-AF Usage Guide
Autonomous engineering team runtime — one API call spins up coordinated AI agents to scope, build, and ship software.
What It Does
SWE-AF creates a coordinated team of AI agents (planning, coding, review, QA, merge, verification) that execute in parallel based on DAG dependencies. Issues with no dependencies run simultaneously; dependent issues run sequentially.
Installation
python3.12 -m venv .venv
source .venv/bin/activate
pip install -e ".[dev]"
Running
Terminal 1 — Control Plane:
af # starts AgentField on port 8080
Terminal 2 — Register Node:
python -m swe_af # registers the swe-planner node
Triggering a Build
With local repo:
curl -X POST http://localhost:8080/api/v1/execute/async/swe-planner.build \
-H "Content-Type: application/json" \
-d '{
"input": {
"goal": "Add JWT auth to all API endpoints",
"repo_path": "/path/to/your/repo",
"config": {
"runtime": "open_code",
"models": {
"default": "zai-coding-plan/glm-5"
}
}
}
}'
With GitHub repo (clones + creates draft PR):
curl -X POST http://localhost:8080/api/v1/execute/async/swe-planner.build \
-H "Content-Type: application/json" \
-d '{
"input": {
"goal": "Add comprehensive test coverage",
"repo_url": "https://github.com/user/my-project",
"config": {
"runtime": "open_code",
"models": {
"default": "zai-coding-plan/glm-5"
}
}
}
}'
Configuration
| Key | Values | Description |
|---|---|---|
runtime |
"claude_code", "open_code", "codex" |
AI backend to use |
models.default |
model ID string | Default model for all agents |
models.coder |
model ID string | Override for coder role |
models.qa |
model ID string | Override for QA role |
repo_path |
local path | Local workspace (new or existing) |
repo_url |
GitHub URL | Clone + draft PR workflow |
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 191 lines · 27 tokens per session scan A c56a61ab74a2
swe-af 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 27 tokens to every session and 1,585 once invoked, about $0.0001 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.