
Swe loop
Use when the user has a coding prompt — a feature, bug fix, or refactor — and wants it implemented end to end by a self-checking software lo
- Scripts
- Python
- Platforms
- Claude Code, Codex, Cursor
- GitHub stars
- 183
- Last commit
- 5 months ago
- License
- MIT
- Listing updated
- today
When your agent uses it
Use when the user has a coding prompt — a feature, bug fix, or refactor — and wants it implemented end to end by a self-checking software loop, not a single pass. It refines the prompt into an executable plan (running the plan-loop internally), then executes the plan task by task: an Engineer subagent implements each PR-sized task editing only source, a separate QA subagent authors the tests that prove the task's acceptance criteria (or grades quality only when tests already cover them), runs the task's tests plus the full accumulated regression suite, and grades the code against a strict conciseness/readability/style-match rubric; the Engineer and QA loop on each task until the tests pass and the quality gate holds, then it commits and opens a pull request for the task — stacked PRs (one per task, each based on the prior) by default, or one combined PR — and moves to the next task. Author and critic have disjoint write scopes (Engineer owns source, QA owns tests) so neither can game the gate. Not for produci
From the skill's SKILL.md. Your agent reads this description to decide when to load the skill.
What it can access
- Runs Python scripts(see the files on GitHub)
- No network calls found in its scripts(see the files on GitHub)
- License: MIT(see the files on GitHub)
From a static check of its 8 files (40 KB) on GitHub on 17 November 2026. Nothing was run. Read the files before you install a skill: it can tell your agent to run anything its tools allow.
Install
This skill ships in the agent-loops plugin. In Claude Code, add the marketplace and install the plugin (it may include other skills too):
/plugin marketplace add gaasher/Agent-Loop-Skills
/plugin install agent-loops@agent-loop-skillsOr copy only this skill to ~/.claude/skills/swe-loop:
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/gaasher/Agent-Loop-Skills.git "$tmp" &&
mkdir -p ~/.claude/skills &&
rm -rf ~/.claude/skills/swe-loop &&
cp -R "$tmp/loops/swe-loop" ~/.claude/skills/swe-loop &&
rm -rf "$tmp"For one project only, put the folder in .claude/skills/swe-loop inside it instead.
Copy the skill folder to ~/.agents/skills/swe-loop to use it in every repository:
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/gaasher/Agent-Loop-Skills.git "$tmp" &&
mkdir -p ~/.agents/skills &&
rm -rf ~/.agents/skills/swe-loop &&
cp -R "$tmp/loops/swe-loop" ~/.agents/skills/swe-loop &&
rm -rf "$tmp"For one repository only, put the folder in .agents/skills/swe-loop inside it instead.
Copy the skill folder to ~/.cursor/skills/swe-loop to use it in every project:
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/gaasher/Agent-Loop-Skills.git "$tmp" &&
mkdir -p ~/.cursor/skills &&
rm -rf ~/.cursor/skills/swe-loop &&
cp -R "$tmp/loops/swe-loop" ~/.cursor/skills/swe-loop &&
rm -rf "$tmp"For one project only, put the folder in .cursor/skills/swe-loop inside it instead.
Run in a terminal (add --scope workspace to install it for the current workspace only):
gemini skills install https://github.com/gaasher/Agent-Loop-Skills.git --path loops/swe-loopOr copy the folder to ~/.gemini/skills/swe-loop yourself.
For GitHub Copilot in VS Code, copy the skill folder to ~/.copilot/skills/swe-loop:
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/gaasher/Agent-Loop-Skills.git "$tmp" &&
mkdir -p ~/.copilot/skills &&
rm -rf ~/.copilot/skills/swe-loop &&
cp -R "$tmp/loops/swe-loop" ~/.copilot/skills/swe-loop &&
rm -rf "$tmp"For one project only, put the folder in .github/skills/swe-loop inside it instead.
Get the folder:
git clone --depth 1 https://github.com/gaasher/Agent-Loop-Skills.gitThen copy Agent-Loop-Skills/loops/swe-loop into your agent's skills folder as swe-loop. Agents that support SKILL.md read one folder per skill.
Swe loop FAQ
How do I install Swe loop in Claude Code?
Copy the skill folder from GitHub to ~/.claude/skills/swe-loop to use it in all your projects, or to .claude/skills/swe-loop in one project. Or install the agent-loops plugin, which includes it: /plugin marketplace add gaasher/Agent-Loop-Skills, then /plugin install agent-loops@agent-loop-skills.
Does Swe loop run scripts?
Yes. It runs Python scripts. No network calls were found in its scripts. This comes from a static check of the files on GitHub; nothing was run. Read the files before you install it.
Which AI agents can use Swe loop?
Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf and Goose. Each reads skills in the SKILL.md format from its own folder; the install steps on this page list them.
More from gaasher/Agent-Loop-Skills

Use when the user wants to evolve an ML model/program through population-based search rather than a single sequential refine loop — a genera
- Open source
- 183 GitHub stars

Use when the user has a known, already-observed anomaly in their data — a metric spike or drop, an outlier, an unexpected number — and wants
- Open source
- 183 GitHub stars

Use when the user has concrete failing cases in code or a guardrail/classifier/filter/prompt/API they own — a red-team failure catalogue OR
- Open source
- 183 GitHub stars
- Developer tools

Use when the user has a results draft or a set of data-backed claims and wants each one adversarially verified against the underlying datase
- Open source
- 183 GitHub stars

Use when the user wants an iterative, self-checking exploratory analysis of a dataset — surfacing findings that are each verified by re-runn
- Open source
- 183 GitHub stars
- Analytics and data

Use when the user wants two approaches raced head-to-head on a single shared metric — e.g
- Open source
- 183 GitHub stars