A workflow that scans a GitHub repository for failing tests, applies a code fix through an automated loop, checks the result, and opens a pull request on a separate branch. It currently describes pytest-based scanning and a LoopForge API.

Use it to investigate and fix repository bugs, extend the workflow's workspace or Git support, or debug the /api/repo-fix endpoint. It is configured to create branches named loopforge/fix-{id} and can create a GitHub pull request.

It structures bug fixing from repository setup through quality checks and review, while keeping changes off the main branch. The resulting pull request includes run and test information.

How vpeetla-ai/react-agent-pattern configures Cursor

Reuse

Borrowing it

Nothing to install: this file belongs to vpeetla-ai/react-agent-pattern. 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/vpeetla-ai/react-agent-pattern/main/.cursor/skills/repo-fix-pr/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/vpeetla-ai/react-agent-pattern

Made for: Cursor.

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/vpeetla-ai/react-agent-pattern/repo-fix-pr/github.svg)](https://agentmods.dev/skills/vpeetla-ai/react-agent-pattern/repo-fix-pr)

Your own site

<a href="https://agentmods.dev/skills/vpeetla-ai/react-agent-pattern/repo-fix-pr"><img src="https://agentmods.dev/badge/skills/vpeetla-ai/react-agent-pattern/repo-fix-pr/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/vpeetla-ai/react-agent-pattern/repo-fix-pr"><img src="https://agentmods.dev/badge/skills/vpeetla-ai/react-agent-pattern/repo-fix-pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 343 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.

Origin 100% copy Near-identical to another mod 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	$0.00063	$0.00343
Opus 5.5	$0.00025	$0.00137
Sonnet 5.5	$0.00013	$0.00069
Haiku 4.5	$0.00006	$0.00034

Measured 2mo ago against content hash 257c58ab5887, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

repo-fix-pr 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 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -X POST https://loopforge-api.onrender.com/api/repo-fix \

Origin

This is a copy

100% identical to repo-fix-pr — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.cursor/skills/repo-fix-pr/SKILL.md · 47 lines

What it actually says

Repo Fix → PR Workflow

Flow

clone → scan (pytest) → orchestrate → code → review → quality
  → git checkout -b loopforge/fix-{run_id} → commit → push branch → GitHub PR

API

curl -X POST https://loopforge-api.onrender.com/api/repo-fix \
  -H "Content-Type: application/json" \
  -d '{"repo_url":"https://github.com/org/repo.git","task":"Fix failing tests","create_pr":true}'

Env (Render)

GROQ_API_KEY — live LLM
GITHUB_TOKEN — fine-grained PAT: Contents + Pull requests write

Rules

Never push to main
Branch: loopforge/fix-{run_id[:12]}
PR body includes run_id, review score, test status

Extending

src/loop_engine/workspace/git_ops.py — clone, branch, PR API
src/loop_engine/graph/repo_nodes.py — patch parse, quality gate
Add project detectors (npm, cargo) beside pytest

Demo

https://demo-omega-taupe.vercel.app

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 · 47 lines · 63 tokens per session scan A 257c58ab5887

Subscribe to this mod's changes

repo-fix-pr is a skill published in the GitHub repository vpeetla-ai/react-agent-pattern (2 stars, last pushed 2mo ago), licensed MIT. It adds 63 tokens to every session and 343 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). It is 100% identical to repo-fix-pr, differing in 0 lines, and is treated as a copy.

Debugging Git and workflow Python Testing ai-agents langgraph react-agent tutorial

repo-fix-pr next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
repo-fix-prvpeetla-ai/react-agent-pattern	Skill	2	2mo ago	MIT	A	63	Cursor
mem0-test-integrationmem0ai/mem0	Skill	68k	2d ago	Apache-2.0	A	207	Claude Code, Codex
mem0-integratemem0ai/mem0	Skill	68k	2d ago	Apache-2.0	A	188	Claude Code, Codex
safetylangchain-ai/deepagents	Skill	31k	yesterday	MIT	A	48	Claude Code, Codex
code-reviewlangchain-ai/deepagents	Skill	31k	yesterday	MIT	A	23	Claude Code, Codex
credit-note-fixeropenai/openai-agents-python	Skill	31k	today	MIT	A	21	Claude Code, Codex
verify-changeComposioHQ/composio	Skill	31k	yesterday	MIT	A	57	Claude Code, Codex

react-agent-pattern: Skill for Cursor