agentmods.dev

gskill CLAUDE.md

Repository instructions for gskill, a tool that learns project-specific guidance for coding agents and saves it as a skill file.

In plain words
What is it for?
Use them when developing gskill, especially for running its Python pipeline, managing dependencies with uv, testing, linting, and formatting.
Why use it?
They give the agent the project's expected workflow, commands, structure, and testing rules in one place.

Instructions file

33 4mo ago A scan 1,205 tokens original MIT
View the source file itsmostafa/gskill
Install

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.

agentmods
npx agentmods add instructions/itsmostafa/gskill/claude-md
Clone the repo
git clone --depth 1 https://github.com/itsmostafa/gskill
Per session 1,205 This file is loaded in full into every session.
When invoked 1,205 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.01205 $0.01205
Opus 5 $0.00602 $0.00602
Sonnet 5 $0.00241 $0.00241
Haiku 4.5 $0.00120 $0.00120

Measured 3d ago against content hash b61b404183b7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

gskill CLAUDE.md 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 3d 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.

CLAUDE.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

gskill automatically learns repository-specific skills for coding agents via evolutionary search. It:

  1. Loads SWE-smith tasks for a target GitHub repository
  2. Optionally generates an initial SKILL.md via gpt-5.2 using the repo's README and config files
  3. Uses GEPA (evolutionary prompt optimization) with mini-SWE-Agent to iteratively improve the skill
  4. Saves the best-scoring SKILL.md to .claude/skills/<repo>/SKILL.md

Project Management

This project uses uv for Python package and environment management (Python 3.13). Do not use pip, python, or manual venv activation directly.

uv run main.py <repo-url>   # Run the main pipeline
uv add <package>            # Add a dependency
uv remove <package>         # Remove a dependency
uv sync                     # Install dependencies from lockfile
uv run pytest               # Run tests
uv run ruff check .         # Lint
uv run ruff format .        # Format

A Taskfile.yml (requires Task) provides shortcuts for common operations:

task sync                # uv sync
task lint                # ruff check
task format              # ruff format
task test                # pytest
task run -- owner/repo   # gskill run (pass args via CLI_ARGS)
task tasks               # gskill tasks (pass args via CLI_ARGS)

Entry Point & CLI

main.py is the CLI entry point (registered as the gskill script). It exposes two Typer commands:

  • gskill run <repo-url> — run the full optimization pipeline
    • --output-dir / -o: where to write SKILL.md (default: .claude/skills)
    • --max-evals / -n: GEPA evaluation budget (default: 150)
    • --no-initial-skill: skip gpt-5.2 seed generation, start GEPA from empty
    • --agent-model / -m: LiteLLM model string for mini-SWE-agent (e.g. openai/gpt-5.2); falls back to GSKILL_AGENT_MODEL env var, then openai/gpt-5.2
  • gskill tasks <owner/repo> — list available SWE-smith tasks for a repo
    • --limit / -l: number of tasks to show (default: 10)
    • --list: list all tasks up to limit

Read the full file on GitHub · 87 lines

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. 3d ago First seen · 87 lines · 1,205 tokens per session scan A b61b404183b7

Subscribe to this mod's changes

gskill CLAUDE.md is an instructions file published in the GitHub repository itsmostafa/gskill (33 stars, last pushed 4mo ago), licensed MIT. It adds 1,205 tokens to every session, about $0.0060 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 2026-08-30.

Building agentsagent-skillsai-agentsclaude-codecodex-cli
Related

Other instructions, from other repositories

apm python.instructions.md

Python development guidelines.

microsoft/apm · 78 tokens

codemap CLAUDE.md

Instructions for JordanCoin/codemap, covering 🛑 stop — run codemap before any task, repo root requirement (critical) and required usage.

JordanCoin/codemap · 372 tokens

OpenMicro AGENTS.md

Instructions for stephenleo/OpenMicro, covering openmicro — project conventions and releases.

stephenleo/OpenMicro · 123 tokens

squarebox CLAUDE.md

Instructions for SquareWaveSystems/squarebox, covering claude.md, agent skills, issue tracker, triage labels and domain docs.

SquareWaveSystems/squarebox · 1,772 tokens

domain-experts CLAUDE.md

Instructions for wonsukchoi/domain-experts, covering domain experts — session bootstrap, non-negotiables when adding or editing roles, dual-graph context policy, mandatory: always follow this order and token usage.

wonsukchoi/domain-experts · 1,300 tokens

academic-writing-toolkit CLAUDE.md

Instructions for yha9806/academic-writing-toolkit, covering academic writing project, project overview, directories, targets and reading constraints.

yha9806/academic-writing-toolkit · 356 tokens