Borrowing it
Nothing to install: this file belongs to CaseyRo/mcp-readwise. 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/CaseyRo/mcp-readwise/main/CLAUDE.mdgit clone --depth 1 https://github.com/CaseyRo/mcp-readwiseWrote 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/caseyro/mcp-readwise/claude-md)<a href="https://agentmods.dev/instructions/caseyro/mcp-readwise/claude-md"><img src="https://agentmods.dev/badge/instructions/caseyro/mcp-readwise/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/caseyro/mcp-readwise/claude-md"><img src="https://agentmods.dev/badge/instructions/caseyro/mcp-readwise/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 | $0.00370 | $0.00370 |
| Opus 5.5 | $0.00148 | $0.00148 |
| Sonnet 5.5 | $0.00074 | $0.00074 |
| Haiku 4.5 | $0.00037 | $0.00037 |
Grade A, and why
mcp-readwise 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 1mo 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.
What it actually says
CLAUDE.md
Project overview, structure and conventions: see AGENTS.md and README.md.
uv sync && uv run pytest && uv run ruff check .
Scope: what this server adds over the official connector
The official claude.ai Readwise connector (mcp__claude_ai_readwise_MCP__…) covers Reader search/list/create/move/tags, highlight CRUD and highlight tags, highlight vector search and daily review. This server keeps only the gap: EPUB delivery (save_markdown_as_epub, verify_epub_received), branded save_markdown, engagement-scored reading_status / writing_material, update_progress, reader_get_by_url (exact URL lookup) and v2 tags (list_tags for ids, create_tag, delete_tag). Don't re-add tools the connector already has.
fastmcp 4 idioms
- Tools are plain async functions registered in
server.pywithmcp.tool(fn, title=..., annotations=...); output models must stay additive-only (tests/test_output_schema_contract.py). - Raise
fastmcp.exceptions.ToolErrorfor caller mistakes. - Test over the wire with the in-memory
fastmcp.Client(mcp)(tests/test_mcp_protocol.py); see themcp-testingskill. - Releases are tag-only: after a merge,
release.ymlpushes the nextv*tag; no version-bump commits. Deploys rebuild from source.mainis protected (PR +testcheck). See thecdit-release-pipelineskill. - Behind an MCP portal, the portal's tool catalog needs a manual sync after tool-surface 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.
- 1mo ago Changed · +6 tokens per session 52be9e2f9502
- 1mo ago First seen · 20 lines · 364 tokens per session scan A 6afc790a8546
mcp-readwise CLAUDE.md is an instructions file published in the GitHub repository CaseyRo/mcp-readwise (1 stars, last pushed 8d ago), licensed MIT. It adds 370 tokens to every session, about $0.0015 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 2026-09-29.
mcp-readwise CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mcp-readwise CLAUDE.mdCaseyRo/mcp-readwise | Instructions file | 1 | 8d ago | MIT | A | 370 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |