Borrowing it
Nothing to install: this file belongs to sns45/dear-claude. 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/sns45/dear-claude/main/CLAUDE.mdgit clone --depth 1 https://github.com/sns45/dear-claudeWrote 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/sns45/dear-claude/claude-md)<a href="https://agentmods.dev/instructions/sns45/dear-claude/claude-md"><img src="https://agentmods.dev/badge/instructions/sns45/dear-claude/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 | $0.01363 | $0.01363 |
| Opus 5 | $0.00681 | $0.00681 |
| Sonnet 5 | $0.00273 | $0.00273 |
| Haiku 4.5 | $0.00136 | $0.00136 |
Grade A, and why
dear-claude CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
dear-claude
MCP server that triggers local Claude Code instances from external platforms (Linear, GitHub, Jira, GitLab, Notion, Obsidian) when "Dear Claude" is mentioned.
Architecture Notes
Data directory (do NOT use process.cwd())
All persistent state resolves through getDataDir() in src/utils/paths.ts:
DEAR_CLAUDE_DATA_DIR(explicit override)$XDG_DATA_HOME/dear-claude~/.local/share/dear-claude(default)
This holds dear-claude.db, workspaces/, contexts/, and api-token.
Never resolve state against process.cwd(). A stdio MCP server inherits the working directory of whatever project the client opened, so a cwd relative path creates a stray data/ folder in every project. That was a real bug, fixed in v1.1.3.
Two transports
The same tool surface is served two ways:
- stdio:
dear-claude start --mcp. Spawned per Claude Code window. - Stateless Streamable HTTP:
POST /mcpon the Hono server, mounted bymountMcpEndpoint()insrc/mcp.ts.
The HTTP endpoint runs stateless (sessionIdGenerator: undefined), building a fresh Server and transport per request, so nothing is shared across requests. Prefer it when running several Claude Code windows: one shared process instead of one per window, which avoids contention on the webhook port.
"dear-claude": {
"type": "http",
"url": "http://127.0.0.1:3334/mcp",
"headers": { "Authorization": "Bearer <dear-claude token>" }
}
stdout is the MCP protocol channel
In --mcp mode, console.log is redirected to stderr at the top of the start action in src/cli.ts. Anything written to stdout that is not JSON-RPC corrupts the framing and the client drops the connection with CONNECTION_CLOSED. Use console.error for any new logging on a code path that can run under stdio.
Auth and binding
/api/* and /mcp require a bearer token (src/utils/auth.ts). These endpoints can spawn Claude with bypassPermissions on this machine, so they must never be open.
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.
- 5d ago First seen · 96 lines · 1,363 tokens per session scan A 63f87b618c42
dear-claude CLAUDE.md is an instructions file published in the GitHub repository sns45/dear-claude (0 stars, last pushed 9d ago), licensed MIT. It adds 1,363 tokens to every session, about $0.0068 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 2026-08-31.
Other instructions, from other repositories
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.
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).
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).
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.
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.