An autonomous workflow for investigating and fixing GitHub issues, which are reported problems or requested changes in a software repository. It records the agent's debugging steps as an auditable trail.

Use it to resolve bugs or refactoring tasks from GitHub issues through an edit, check, and test cycle.

It gives complex bug fixes a repeatable investigation process and makes the reasoning behind the changes easier to inspect.

How QuBiit0/lmagent configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to QuBiit0/lmagent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/QuBiit0/lmagent/main/.agents/skills/swe-agent/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/QuBiit0/lmagent

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/qubiit0/lmagent/swe-agent/github.svg)](https://agentmods.dev/skills/qubiit0/lmagent/swe-agent)

Your own site

<a href="https://agentmods.dev/skills/qubiit0/lmagent/swe-agent"><img src="https://agentmods.dev/badge/skills/qubiit0/lmagent/swe-agent/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/qubiit0/lmagent/swe-agent"><img src="https://agentmods.dev/badge/skills/qubiit0/lmagent/swe-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,941 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00038	$0.02941
Opus 5.5	$0.00015	$0.01176
Sonnet 5.5	$0.00008	$0.00588
Haiku 4.5	$0.00004	$0.00294

Measured 2mo ago against content hash da615c3f0582, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

swe-agent scanned grade A with 0 findings 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 2mo 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.agents/skills/swe-agent/SKILL.md · 321 lines

How it starts

The opening of the file, as written. The whole thing — 321 lines — stays where its author put it; the contents beside it link to each section on GitHub.

# Activación: Se activa para resolver GitHub Issues de principio a fin sin intervención humana constante.
# Diferenciación:
#   - systematic-debugger → INVESTIGA causas complejas paso a paso con el humano.
#   - backend-engineer → IMPLEMENTA features nuevas (SWE-Agent arregla bugs/refactors).
#   - qa-engineer → VERIFICA que el fix funcione.

SWE-Agent Skill

⚠️ FLEXIBILIDAD DE RESOLUCIÓN AUTÓNOMA: El loop de ejecución (Edit-Lint-Test), el formato de logging (Trajectory) y las fases de resolución de issues son ejemplos de referencia para el desarrollo autónomo. Como agente de SWE, posees la inteligencia y flexibilidad para adaptar tu estrategia de resolución de bugs o features a los pipelines de CI, herramientas de testing o estrategias de versionado particulares del repositorio.

SWE-Agent: Un paradigma de ingeniería de software autónoma donde el agente resuelve issues de forma sistemática, registrando cada paso como una "trajectory" auditable.

🧠 System Prompt

Eres **SWE-Agent**, un ingeniero de software autónomo.
Tu objetivo es **RESOLVER ISSUES PASO A PASO, DE FORMA AUDITABLE Y SEGURA**.
Tu tono es **Metódico, Riguroso, Observable**.

**Principios Core:**
1. **Observe before Act**: Lee y entiende el código antes de modificarlo.
2. **Minimal Changes**: Haz el cambio mínimo necesario. No refactorices lo que no es necesario.
3. **Trajectory is Truth**: Cada paso se registra. Si no está en la trajectory, no pasó.
4. **Test Proves Fix**: El fix no existe hasta que un test lo demuestra.

**Restricciones:**
- NUNCA edites más de lo necesario para resolver el issue.
- SIEMPRE reproduce el bug ANTES de intentar arreglarlo.
- SIEMPRE registra cada paso en formato trajectory.
- NUNCA excedas los límites de costo/iteraciones sin pedir permiso.
- SIEMPRE ejecuta el lint después de cada edición.

🌍 Agnosticismo Tecnológico y Flexibilidad (LMAgent Core Rule)

Eres un experto tecnológicamente agnóstico. NO obligues al usuario a utilizar tecnologías, frameworks o versiones obsoletas a menos que te lo pidan explícitamente. Evalúa el entorno del usuario, respeta su stack actual, y cuando diseñes o propongas soluciones nuevas, recomienda siempre el uso de herramientas modernas, estables y vigentes (Latest Stable), justificando tus decisiones técnica y lógicamente.

Read the full file on GitHub · 321 lines

Files

What ships with it

1 file 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.

references/trajectory-format.md 4.0 KB

Changes

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.

2mo ago First seen · 321 lines · 38 tokens per session scan A da615c3f0582

Subscribe to this mod's changes

swe-agent is a skill published in the GitHub repository QuBiit0/lmagent (2 stars, last pushed 8mo ago), licensed MIT. It adds 38 tokens to every session and 2,941 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Debugging Git and workflow

swe-agent next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
swe-agentQuBiit0/lmagent	Skill	2	8mo ago	MIT	A	38	Claude Code
git-advanced-workflowswshobson/agents	Skill	42k	2d ago	MIT	A	54	Claude Code
agent-merge-conflict-arbiterNousResearch/hermes-agent	Skill	261k	today	MIT	A	19	Claude Code, Codex
enable-check-includes-strictchromium/chromium	Skill	25k	today	BSD-3-Clause	A	70	Claude Code, Codex
resolve-handoffomnigent-ai/omnigent	Skill	11k	today	Apache-2.0	A	23	Claude Code, Codex
reproduce-and-fix-issuesbacknotprop/pstack	Skill	3.8k	yesterday	MIT	A	48	Claude Code, Cursor
cy-orquestrate-issuecompozy/compozy	Skill	2.9k	today	MIT	A	94	Claude Code, Codex

lmagent: Skill for Claude Code