lmagent: Skill for Claude Code

.agents/skills/swe-agent/SKILL.md

swe-agent is a skill for Claude Code from QuBiit0/lmagent. It costs 38 tokens per session (2,941 once invoked), scanned A, original, MIT.

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.

In plain words
What is it for?
Use it to resolve bugs or refactoring tasks from GitHub issues through an edit, check, and test cycle.
Why use it?
It gives complex bug fixes a repeatable investigation process and makes the reasoning behind the changes easier to inspect.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: mentions Claude Code; installed under .agents/ (shared by several agents); mentions Gemini CLI.

This is QuBiit0/lmagent's own configuration. It tells Claude Code how to work on lmagent itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything lmagent configures →

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.

agentmods badge for swe-agent

README.md
[![agentmods](https://agentmods.dev/badge/skills/qubiit0/lmagent/swe-agent.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.svg" alt="Measured on agentmods" 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00038 $0.02941
Opus 5 $0.00019 $0.01470
Sonnet 5 $0.00008 $0.00588
Haiku 4.5 $0.00004 $0.00294

Measured 8d ago against content hash da615c3f0582, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, 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 8d 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.

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.

  1. 8d 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 6mo ago), licensed MIT. It adds 38 tokens to every session and 2,941 once invoked, about $0.0002 per session on Opus 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.

Related

Other skills, from other repositories

agent-merge-conflict-arbiter

Neutral arbiter for merge conflicts between two agents.

NousResearch/hermes-agent · 19 tokens

git-advanced-workflows

Master advanced Git workflows including rebasing, cherry-picking, bisect, worktrees, and reflog to maintain clean history and recover from any situation. Use when managing complex Git histories, collaborating on feature branches, or troubleshooting repository issues.

wshobson/agents · 54 tokens

bisect

Bisect regressions or broken builds in the Chromium repository using deterministic binary search, checking out midpoint commits, syncing dependencies with gclient sync, compiling the target with autoninja, and querying the user for test results until the culprit commit is isolated.

chromium/chromium · 52 tokens

mantis-critic

Assesses the production viability of findings, filtering out debug-only features and assertion traps. Use when findings have been validated and you need to confirm they are triggerable in production release builds (with assertions disabled). Don't use for writing reproduction scripts or patches.

google/mantis · 55 tokens

hotpath_bump

Bump the hotpath version number across the workspace and related files. Updates crate versions in Cargo.toml files (exact patch version) and version references in the backend middleware, hotpathinit skill, and README (major.minor only). Use when the user wants to bump, bump the version, or release a new hotpath…

pawurb/hotpath-rs · 73 tokens

comet-github-issue-fix

A workflow for fixing a confirmed Comet-related GitHub issue or review blocker within an isolated scope. It covers matching the work to the relevant workflow, testing the change, checking runtime results, and preparing a careful handoff.

rpamis/comet · 71 tokens