Borrowing it
Nothing to install: this file belongs to PrismorSec/prismor. 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/PrismorSec/prismor/main/CLAUDE.mdgit clone --depth 1 https://github.com/PrismorSec/prismorWrote 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/prismorsec/prismor/claude-md)<a href="https://agentmods.dev/instructions/prismorsec/prismor/claude-md"><img src="https://agentmods.dev/badge/instructions/prismorsec/prismor/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.
<a href="https://agentmods.dev/instructions/prismorsec/prismor/claude-md"><img src="https://agentmods.dev/badge/instructions/prismorsec/prismor/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00692 | $0.00692 |
| Opus 5.5 | $0.00277 | $0.00277 |
| Sonnet 5.5 | $0.00138 | $0.00138 |
| Haiku 4.5 | $0.00069 | $0.00069 |
Grade A, and why
prismor 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 11d 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 — 29 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prismor Security — CLAUDE.md
This project is the Prismor security package for AI coding agents.
Prismor Runtime Protection
This repo has Prismor hooks enabled. The hook dispatcher at prismor/runtime/cli.py monitors tool calls and blocks dangerous actions in real time.
Agent sessions in this repo are screened by the working tree, not the installed release (dogfooding, #495). The committed .claude/settings.json, .codex/hooks.json, .cursor/hooks.json and .github/hooks/prismor.json route every hook through scripts/dev-hook.py in observe mode (scripts/dev-hook.cmd on Windows).
- Never run
prismor install-hooks --scope project(orprismor setupat project scope) inside this repo. It rewrites those files with the installed-binary form and silently stops the dogfooding.tests/test_dogfood_configs.pyfails if that happens. - After changing an installer's events or matchers, regenerate with
python tests/test_dogfood_configs.py --write. - Needs a python that can
import yaml(python3/python, orpyon Windows); point elsewhere withPRISMOR_DEV_PYTHON=/path/to/python.PRISMOR_DOGFOOD=0turns the dogfood hooks off. - If the working tree stops importing, shell and web tool calls are blocked with a message saying why; prompts, reads and edits still go through, so the agent can fix it.
- Windows: Claude Code needs Git Bash (its default hook shell); Codex and Copilot use the
.cmdlauncher. Codex resolves agit worktreeto the main checkout, so in a worktree its dogfood hooks are not loaded.
Cloaking (secret prevention)
The prismor/runtime/cloaking/ subsystem is Prismor's prevention layer for secret leaks. Real secret values live under ~/.prismor/secrets/ and are referenced in tool calls as @@SECRET:<name>@@. When editing this subsystem, treat it as security-sensitive code and never print, log, or narrate real secret values — use the placeholder form in all examples and prose. See prismor/runtime/cloaking/README.md for the full design and AGENTS.md for editing guidelines.
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.
- 11d ago Changed · +20 tokens per session 552fa107e562
- 1mo ago Changed · +8 lines · +313 tokens per session c47026d7978a
- 1mo ago First seen · 21 lines · 359 tokens per session scan A e81b7150182c
prismor CLAUDE.md is an instructions file published in the GitHub repository PrismorSec/prismor (448 stars, last pushed today), licensed Apache-2.0. It adds 692 tokens to every session, about $0.0028 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 2026-08-30.
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).
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.
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).
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.
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).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.