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/mohammadmaso/kherad/claude-mdgit clone --depth 1 https://github.com/mohammadmaso/kheradWrote 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/mohammadmaso/kherad/claude-md)<a href="https://agentmods.dev/instructions/mohammadmaso/kherad/claude-md"><img src="https://agentmods.dev/badge/instructions/mohammadmaso/kherad/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 | $0.02633 | $0.02633 |
| Opus 5 | $0.01316 | $0.01316 |
| Sonnet 5 | $0.00527 | $0.00527 |
| Haiku 4.5 | $0.00263 | $0.00263 |
Grade A, and why
kherad 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 6d 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 — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What this is
Kherad is an internal, git-backed wiki. Non-technical authors edit pages through a Lexical
block editor that feels like Notion, but every save is a real git commit under the hood, and
every published change goes through a merge-request review/approve step. See PRD.md for the
full product/technical spec (roles, data model, workflows) — read it when a task touches
permissions, the git/branching model, or the review workflow, since this file only covers
what's needed to navigate and run the code.
Commands
This is a pnpm + Turborepo monorepo ([email protected], Node >=20). Run from repo root unless noted.
pnpm dev # turbo run dev — starts apps/api (tsx watch) and apps/web (next dev) together
pnpm build # turbo run build
pnpm lint # turbo run lint
pnpm check-types # turbo run check-types (tsc --noEmit in every package)
pnpm test # turbo run test (currently only packages/core has tests)
pnpm format # prettier --write across the repo
Scope any of the above to one workspace with pnpm --filter <name> <script> (package names:
api, web, @kherad/core, @kherad/db, @kherad/ui).
Tests live only in packages/core (Vitest). Run them from that package:
cd packages/core
pnpm test # vitest run — all tests
pnpm vitest run src/git/engine.test.ts # single file
pnpm vitest run -t "some test name" # single test by name
Database (packages/db), via drizzle-kit, run from packages/db after cp .env.example .env:
pnpm db:generate # write a new migration from src/schema.ts
pnpm db:migrate # apply pending migrations
pnpm db:push # push schema directly, no migration file (prototyping only)
pnpm db:studio # Drizzle Studio against DATABASE_URL
pnpm db:seed # idempotent: one admin user + one public "welcome" bundle
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.
- 6d ago First seen · 182 lines · 2,633 tokens per session scan A a47c38d002ca
kherad CLAUDE.md is an instructions file published in the GitHub repository mohammadmaso/kherad (46 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 2,633 tokens to every session, about $0.0132 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
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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.
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 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).