Borrowing it
Nothing to install: this file belongs to jhaizhou-ops/pinrule. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jhaizhou-ops/pinrule/main/CLAUDE.mdgit clone --depth 1 https://github.com/jhaizhou-ops/pinruleWrote 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/jhaizhou-ops/pinrule/claude-md)<a href="https://agentmods.dev/instructions/jhaizhou-ops/pinrule/claude-md"><img src="https://agentmods.dev/badge/instructions/jhaizhou-ops/pinrule/claude-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 5.1 | $0.01004 | $0.01004 |
| Opus 5 | $0.00502 | $0.00502 |
| Sonnet 5 | $0.00201 | $0.00201 |
| Haiku 4.5 | $0.00100 | $0.00100 |
Grade A, and why
pinrule 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 8d 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pinrule — Project collaboration charter
One-line positioning
pinrule keeps the user's most-valued directions from being lost in long Agent tasks.
Strict boundaries (non-negotiable)
These boundaries come from v1's lessons (see karma-v1/ARCHIVE.md). Each one closes off a path that proved costly:
Things we don't do
- ❌ No auto-distilling new rules — User manually maintains directions; LLM distillation produces noise and misalignment
- ❌ No retrieval / cosine / scene routing — 5-10 rules are all always-on; selection layer not needed
- ❌ Don't compete with memory systems — "Facts about the user" belong in the client's built-in memory
- ❌ No LLM dependency — pure engineering (keywords / regex / counting); decision is firm, not just for v0
- ❌ No reward / RL / scoring — behavioral reminders aren't reward functions; scoring rules makes the model optimize the score, not the behavior
Working principles
1. Don't cheat the current user
pinrule is validated by author self-use. To keep that signal honest, never do these for short-term comfort:
- Hardcode author-specific rules into default templates
- Hardcode author's empirically-found violation phrases into hooks
- Train anything on author's session data
pinrule's defaults have to be cross-user reasonable — at CLAUDE.md / Anthropic best-practice level of universality.
2. Always design from "I am the user" perspective
For every change, ask:
- Can a first-time pinrule user get started in 5 minutes?
- Is the yaml config self-explanatory, or do they need to read docs to understand it?
- Does the first violation detection make them say "ah, I see"?
If a feature only works for the author → cut it.
3. Validation beats accuracy numbers
pinrule v1 fixated on accuracy numbers (67% precision, etc.) and that fixation pulled optimization off-target.
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.
- 8d ago First seen · 104 lines · 1,004 tokens per session scan A f2cd1b3eebbc
pinrule CLAUDE.md is an instructions file published in the GitHub repository jhaizhou-ops/pinrule (47 stars, last pushed 3mo ago), licensed MIT. It adds 1,004 tokens to every session, about $0.0050 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
repobrain copilot-instructions.md
Copilot instructions for study8677/repobrain, covering github copilot bootstrap instructions and hard rule — query the repobrain hub first.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.