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/docs-plus/docs.plus/claude-mdgit clone --depth 1 https://github.com/docs-plus/docs.plusWrote 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/docs-plus/docs.plus/claude-md)<a href="https://agentmods.dev/instructions/docs-plus/docs.plus/claude-md"><img src="https://agentmods.dev/badge/instructions/docs-plus/docs.plus/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 | $0.02627 | $0.02627 |
| Opus 5 | $0.01314 | $0.01314 |
| Sonnet 5 | $0.00525 | $0.00525 |
| Haiku 4.5 | $0.00263 | $0.00263 |
Grade A, and why
docs.plus 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 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Entry point for Claude Code working on docs.plus. Read AGENTS.md first — it is the durable source of truth for this repo's invariants and maintainer preferences. This file is a thin index, not a second copy.
Read order
- AGENTS.md — durable cross-cutting rules: package manager, git/commit policy, code quality, testing, skills, UI/theme, monorepo toolchain. Treat it as memory: do not deviate without an explicit maintainer instruction. Its §Filed by directory map lists every directory-scoped section and the file that now holds it.
- The per-directory
CLAUDE.mdfor the area you are touching — Claude Code loads it automatically when you work under that path:- apps/webapp/CLAUDE.md — UI systems and document features
- apps/webapp/src/components/TipTap/CLAUDE.md — editor architecture
- apps/webapp/src/components/chatroom/CLAUDE.md — chatroom and messaging
- apps/hocuspocus.server/CLAUDE.md — persistence, HTTP modules, production
- apps/admin-dashboard/CLAUDE.md — admin data path
- packages/supabase/CLAUDE.md — SQL, migrations, RLS, storage
- extensions/CLAUDE.md — extension workflow and per-package rules
- Package-local
AGENTS.mdwhen working inside a package (e.g. extensions/extension-hyperlink/AGENTS.md). Read in addition to the above. - The relevant
.cursor/rules/*.mdcfor the file you are editing (see index below).
Durable memory is at .agents/memory/ (gitignored symlink to the Claude Code store, shared with Cursor); .agents/memory/MEMORY.md is the index. Cursor does not read CLAUDE.md — it gets the same rules through .cursor/rules/agent-rules-and-memory.mdc. Keep that map current when a rule file moves.
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 · 75 lines · 2,627 tokens per session scan A 0a6cf0a2e835
docs.plus CLAUDE.md is an instructions file published in the GitHub repository docs-plus/docs.plus (89 stars, last pushed yesterday), licensed MIT. It adds 2,627 tokens to every session, about $0.0131 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 2026-09-03.
Other instructions, from other repositories
open-pencil AGENTS.md
AGENTS.md instructions for open-pencil/open-pencil, covering openpencil, monorepo, public package exports, editor architecture and settings and credentials.
octo-server AGENTS.md
AGENTS.md instructions for Mininglamp-OSS/octo-server, covering agents.md, project overview, common commands, build and run tests for a module.
liveblocks AGENTS.md
AGENTS.md instructions for liveblocks/liveblocks, covering project structure, bash commands, code style, dependencies and code quality.
miro-mcp-server CLAUDE.md
Claude Code instructions for olgasafonova/miro-mcp-server, covering miro mcp server, project, architecture, key patterns and tool categories (110 total).
open-tag AGENTS.md
Instructions for fancyboi999/open-tag, covering open-tag — guide for ai coding agents, this file is a map, not a manual, conventions, parallel development (worktrees) and isolated dev e2e (on demand).
knowtis-app CLAUDE.md
Claude Code instructions for jovandyaz/knowtis-app, covering claude.md, project overview, important rules, essential commands and development.