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/j178/prek/agents-mdgit clone --depth 1 https://github.com/j178/prekWhat 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 | $0.00700 | $0.00700 |
| Opus 5 | $0.00350 | $0.00350 |
| Sonnet 5 | $0.00140 | $0.00140 |
| Haiku 4.5 | $0.00070 | $0.00070 |
Grade A, and why
prek 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 today.
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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Quality
- Write elegant, efficient, and concise code. Prefer simple, clear designs; concise does not mean clever.
- Prefer the smallest coherent change. Reuse existing mechanisms and avoid wrappers or abstractions for speculative or unmeasured gains.
- Prefer direct
iformatchcontrol flow and explicit state types over clever combinators, wrappers, or invalid boolean/Optioncombinations. Prefer plainif/elseto.then()or.then_some(). - Try hard to avoid
panic!,unreachable!,.unwrap(), and.expect(). Encode those constraints in the type system instead. More explicit code or a larger refactor is acceptable when it avoids these calls. - Do not narrate code in comments. Explain invariants and unusual decisions in plain language that makes sense to a first-time reader. Be more verbose when clarity requires it.
- Fix Clippy findings. If suppression is necessary, prefer a narrow
#[expect(...)]with a reason.
Writing Style
- Write natural, direct English that sounds like a human collaborator, not a template or an AI-generated response.
- Avoid canned introductions, generic filler, repetition, and unnecessary summaries.
- Avoid dash-heavy prose, especially em dashes or
-used to join thoughts. Prefer a period, comma, colon, or an explicit conjunction. For example, preferThis is safe because the fallback still validates the state.overThis is safe - the fallback still validates the state.
Build and Tests
-
Linked worktrees must share the primary Cargo target. Before running
cargoor a Cargo-backedmisetask, set:export CARGO_TARGET_DIR="$(dirname "$(git rev-parse --path-format=absolute --git-common-dir)")/target" -
Check existing coverage and nearby style before adding a test. Prefer focused tests; do not run the full integration suite by default.
-
In integration tests, prefer
cmd_snapshot!snapshot coverage over string assertions such ascontains. -
Regenerate
instasnapshots with the relevant test and review them withcargo insta review; do not edit them manually.
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.
- today First seen · 68 lines · 700 tokens per session scan A 08cbcf38626e
prek AGENTS.md is an instructions file published in the GitHub repository j178/prek (8,351 stars, last pushed today), licensed MIT. It adds 700 tokens to every session, about $0.0035 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.
Other instructions, from other repositories
python-uv CLAUDE.md
Instructions for a5chin/python-uv, covering claude.md, project overview, development commands, package management and install dependencies.
pre-commit-hooks copilot-instructions.md
Instructions for duolingo/pre-commit-hooks, covering development rules, architecture, build deploy, root and testing.
totem CLAUDE.md
Instructions for mmnto-ai/totem: The canonical agent instructions for this repository live in AGENTS.md.
know-code AGENTS.md
Instructions for chtnnh/know-code, covering know-code and required agent loop.
Agent-Proof AGENTS.md
AGENTS.md instructions for Heretek-AI/Agent-Proof, covering 🎯 primary directives for ai agents, 🏗️ 3-tier mechanical gate architecture, 📂 repository architecture & key directories, 🛠️ common cli & development commands and build typescript bundles into dist/.
Agent-Proof GEMINI.md
Gemini CLI instructions for Heretek-AI/Agent-Proof, covering gemini.md — google gemini & antigravity assistant guide, 🛠️ project ecosystem & stack, 📋 core development workflows, 1. build and typecheck and build cjs, esm, and .d.ts declarations into dist/.