corpus: Instructions file for Claude Code

CLAUDE.md

corpus CLAUDE.md is an instructions file for Claude Code from monahand1023/corpus. It costs 499 tokens per session, scanned A, original, MIT.

Instructions for developing corpus, a reusable retrieval-augmented generation engine. RAG is a way for an AI system to find relevant documents and use them when answering questions.

In plain words
What is it for?
Use them when changing corpus code, tests, documentation, commits, or other repository content that might accidentally reveal private sources or data.
Why use it?
They prevent private data from entering a public code repository and define how domain-specific copies of the engine should be kept separate.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is monahand1023/corpus's own configuration. It tells Claude Code how to work on corpus itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything corpus configures →

Reuse

Borrowing it

Nothing to install: this file belongs to monahand1023/corpus. 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/monahand1023/corpus/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/monahand1023/corpus

Made for: Claude Code.

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.

agentmods badge for corpus CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/monahand1023/corpus/claude-md/github.svg)](https://agentmods.dev/instructions/monahand1023/corpus/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/monahand1023/corpus/claude-md"><img src="https://agentmods.dev/badge/instructions/monahand1023/corpus/claude-md/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.

agentmods 80×15 button for corpus CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/monahand1023/corpus/claude-md"><img src="https://agentmods.dev/badge/instructions/monahand1023/corpus/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 499 This file is loaded in full into every session.
When invoked 499 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00499 $0.00499
Opus 5.5 $0.00200 $0.00200
Sonnet 5 $0.00100 $0.00100
Haiku 4.5 $0.00050 $0.00050

Measured 2d ago against content hash db2173bc3f5f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-27, from the pricing page.

Security

Grade A, and why

corpus 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 2d 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 · 45 lines

How it starts

The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.

corpus

corpus is the generic RAG engine (the class). Separate per-domain repos elsewhere on this machine are instances of it: they install corpus editable, add their own config/connectors, and hold their own data.

HARD RULE: this repository is PUBLIC. No private data, ever.

No exceptions, for any reason, including "just a test" or "it's only in a commit message".

Never put anything from a private instance into this repo — not in files, tests, fixtures, docs, CHANGELOG, commit messages, branch or tag names, or PR/issue text. That includes:

  • the names of private instance repos, or of the organisations whose data they hold
  • document content, titles, subjects, source keys, file paths, ticket keys, people's names, hostnames
  • eval queries, golden sets, scores, chunk counts, or any per-source stats measured on a private archive
  • anything about the owner's personal reasons for this work

Use neutral placeholders instead (TICKET-123, example.com, Alice). Engineering lessons may be described generically, where they explain code.

How it is enforced — keep these working, never bypass them:

  • .githooks/ (pre-commit, commit-msg, pre-push; install with scripts/install-hooks.sh). The pre-push hook reads its denylist from .git/private-name-patterns, which lives inside .git/ so the denylist itself is never published. If it is missing, pushes are blocked on purpose.
  • tests/test_repo_hygiene.py — no database files, no real corpus.toml, no private ticket-key shapes, no names embedded in the hooks. Its checks are pattern-based on purpose: a literal denylist here would itself be the leak.
  • Never use --no-verify. Never open GitHub PRs for this repo (PR refs cannot be deleted); work on main or local branches.

A rewrite + force-push does NOT remove a leaked commit from GitHub — it stays fetchable by SHA until GitHub Support purges it. Prevention is the only cheap fix.

Instance-specific notes (which repos, where they live) belong in the gitignored CLAUDE.local.md, never in this file.

Read the full file on GitHub · 45 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. 2d ago First seen · 45 lines · 499 tokens per session scan A db2173bc3f5f

Subscribe to this mod's changes

corpus CLAUDE.md is an instructions file published in the GitHub repository monahand1023/corpus (0 stars, last pushed yesterday), licensed MIT. It adds 499 tokens to every session, about $0.0020 per session on Opus 5.5. 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 2026-09-25.

Related

Other instructions, from other repositories

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).

microsoft/vscode · 9,406 tokens

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.

vercel/next.js · 6,985 tokens

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.

openai/codex · 5,153 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

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.

langchain-ai/langchain · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,494 tokens