Borrowing it
Nothing to install: this file belongs to chrischall/honeybook-mcp. 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/chrischall/honeybook-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/chrischall/honeybook-mcpWrote 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/chrischall/honeybook-mcp/claude-md)<a href="https://agentmods.dev/instructions/chrischall/honeybook-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/chrischall/honeybook-mcp/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/chrischall/honeybook-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/chrischall/honeybook-mcp/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 | $0.05797 | $0.05797 |
| Opus 5 | $0.02899 | $0.02899 |
| Sonnet 5 | $0.01159 | $0.01159 |
| Haiku 4.5 | $0.00580 | $0.00580 |
Grade A, and why
honeybook-mcp 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 — 417 lines — stays where its author put it; the contents beside it link to each section on GitHub.
honeybook-mcp
MCP server for the HoneyBook client portal — view contracts & invoices from multiple vendors (each vendor = one captured session), with deep-link fallback for signing and paying.
Commands
npm run build # tsc + esbuild bundle → dist/bundle.js
npm run bundle # esbuild only (no tsc check)
npm test # vitest run
npm run test:watch # vitest in watch mode
npm run dev # node --env-file=.env dist/index.js (requires built dist)
Architecture
src/
index.ts MCP server entry — registers tool modules, stdio transport
client.ts HoneyBookClient — per-session auth headers, fetch wrapper,
401 + 404/HBUnauthorizedError, 429, HBWrongAPIVersion
handling; getActiveClient() resolves
a session from sessionStore and caches a client per origin
auth.ts captureSessionViaFetchproxy() — one-shot @fetchproxy/bootstrap
call that reads localStorage["HONEYBOOK_REACT_CURR_USER"]
out of the user's signed-in portal tab, then closes the
bridge. See "Auth flow" below.
flows.ts Questionnaire ("flow") links: parseFlowLink /
isFlowLinkUrl / flowStorageKey, and the flowStore
(own file, ~/.honeybook-mcp/flows.json)
flow-auth.ts captureFlowCredentialViaFetchproxy() — same lift as
auth.ts, pointed at HONEYBOOK_REACT_WEAK_AUTH_<flowId>
flow-client.ts FlowClient — weak-auth headers over the shared
hbApiRequest; getActiveFlowClient(); plus
fetchFlowMinimal() + flowContextId(), the public
/minimal hop that yields the ctxc a flow read needs
feed.ts Workspace feed (GET /workspaces/<id>/feed): fetch,
message vs activity classification, compact
summarizers, calendar-item compaction (host link
stripped). Shared by messages, meetings tools
pending-tasks.ts runClientPendingTask(): POST /client_pending_task +
poll /client_pending_tasks?task_ids[]= until Finished.
The portal's write protocol (send_message uses it)
sessions.ts Thin adapter over the disk-persisted SessionStore from
@chrischall/mcp-utils/session (this repo was the donor it
was extracted from); re-exports normalizeOrigin and the
configured sessionStore singleton
types.ts HBListEnvelope<T>, ToolResult, CapturedSession, CapturedFlowCredential, FileType
tools/
sessions.ts use_magic_link, list_active_sessions (both kinds)
flows.ts use_flow_link, get_flow
workspace_files.ts list_workspace_files, get_workspace_file (+ section
filtering + heavy-field pruning to keep responses small)
workspaces.ts get_workspace
payment_methods.ts list_payment_methods
contracts.ts sign_contract (deep-link fallback + confirm guard)
invoices.ts pay_invoice (deep-link fallback + confirm guard)
projects.ts list_projects (/client/events), get_project
(/events/<id>/details, trimmed of the vendor account blob)
messages.ts list_messages, get_message, send_message (confirm
guard + pending task), mark_messages_seen
meetings.ts list_meetings — folded out of feed calendar_item activity
tasks.ts list_tasks (/tasks/workspaces/<id> + /counts + /taskgroup)
notes.ts list_notes (/notes/workspace/<id>)
attachments.ts list_attachments (/workspaces/<id>/attachments)
payments.ts list_payments (/workspaces/<id>/payments, per-payment rows)
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 Changed · +12 lines · +214 tokens per session 00f7ff778b7d
- 6d ago Changed · +195 lines · +3,011 tokens per session ece731262e06
- 10d ago First seen · 210 lines · 2,572 tokens per session scan A 6077ca45c5d0
honeybook-mcp CLAUDE.md is an instructions file published in the GitHub repository chrischall/honeybook-mcp (1 stars, last pushed yesterday), licensed MIT. It adds 5,797 tokens to every session, about $0.0290 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).
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.
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.