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.
npx agentmods add instructions/cheolwanpark/snippets/agents-mdgit clone --depth 1 https://github.com/cheolwanpark/snippetsWrote 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.
[](https://agentmods.dev/instructions/cheolwanpark/snippets/agents-md)<a href="https://agentmods.dev/instructions/cheolwanpark/snippets/agents-md"><img src="https://agentmods.dev/badge/instructions/cheolwanpark/snippets/agents-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00564 | $0.00564 |
| Opus 5 | $0.00282 | $0.00282 |
| Sonnet 5 | $0.00113 | $0.00113 |
| Haiku 4.5 | $0.00056 | $0.00056 |
Grade A, and why
snippets AGENTS.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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 24 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
Python 3.12 project with runtime code in src/. Agents that talk to Claude now live in src/agent/ (snippet_extractor.py, prompt.py), shared storage helpers in src/snippet/, and IO/utilities in src/utils/. main.py wires everything into a CLI. Keep new modules under the closest matching package; add integration demos or fixtures under samples/, not in src/.
Environment & Configuration
Install dependencies with uv sync (or pip install -e .) from the repo root. Export CLAUDE_CODE_OAUTH_TOKEN before running the extractor; fail fast if it is missing. Respect the default 1 MB file cap and exclude test fixtures unless --include-tests is passed.
Build, Test, and Development Commands
uv run python main.py <path>— scan a file or directory and stream snippets to stdout (snippet limits are auto-calculated per file).uv run python main.py samples --output snippets.txt— write formatted snippets to a file (helpful for manual QA).uv run python -m pytest— placeholder; add tests here when atests/package exists. Wrap long runs withCLAUDE_CODE_OAUTH_TOKEN=... uv run ...when scripting.
Coding Style & Naming Conventions
Follow standard Black-compatible formatting (4-space indent, double quotes for docstrings). Type hints are expected on public call surfaces. Loggers use logging.getLogger("snippet_extractor"); reuse it for new components. Class names are PascalCase, functions snake_case, constants UPPER_SNAKE. Prefer dataclasses or NamedTuple for structured payloads.
Testing Guidelines
There is no test suite yet; seed tests/ with pytest modules mirroring the package layout (tests/utils/test_file_loader.py). Name async fixtures with the _event_loop fixture when needed. Target high-value behaviors: file filtering edge cases, storage serialization, and concurrency guard rails. Keep sample fixtures under samples/ to avoid polluting the CLI path.
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.
- 4d ago First seen · 24 lines · 564 tokens per session scan A 6c8fd5f62532
snippets AGENTS.md is an instructions file published in the GitHub repository cheolwanpark/snippets (58 stars, last pushed 10mo ago), licensed MIT. It adds 564 tokens to every session, about $0.0028 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.
Other instructions, from other repositories
cocoindex-code CLAUDE.md
Instructions for cocoindex-io/cocoindex-code, covering claude.md, build and test commands, architecture, process model and key layers.
devo AGENTS.md
AGENTS.md instructions for 7df-lab/devo, covering agents.md, rust, tests, test assertions and protocol and session settings.
repobrain copilot-instructions.md
Copilot instructions for study8677/repobrain, covering github copilot bootstrap instructions and hard rule — query the repobrain hub first.
codesage AGENTS.md
Instructions for iliaal/codesage, covering codesage, build, sanity check before pushing, crate map and search pipeline.
amp-acp AGENTS.md
Instructions for tao12345666333/amp-acp, covering agents.md, commands, architecture and code style.
roamcode AGENTS.md
AGENTS.md instructions for burakgon/roamcode, covering repository instructions for coding agents, public-repository safety, stable release and ota contract, releasing a stable version and ota changes.