honeybook-mcp: Instructions file for Claude Code

CLAUDE.md

honeybook-mcp CLAUDE.md is an instructions file for Claude Code from chrischall/honeybook-mcp. It costs 6,315 tokens per session, scanned A, original, MIT.

A set of instructions for working on honeybook-mcp, an MCP server that lets users view contracts and invoices from multiple HoneyBook vendor portals. It documents commands, architecture, authentication, and testing.

In plain words
What is it for?
Use it when developing, building, testing, or debugging honeybook-mcp, including its session-based portal access and API error handling.
Why use it?
It gives coding agents the project-specific context needed to change the server without breaking its build, authentication flow, or tests.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions .claude-plugin; mentions CLAUDE.md.

This is chrischall/honeybook-mcp's own configuration. It tells Claude Code how to work on honeybook-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything honeybook-mcp configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/chrischall/honeybook-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/chrischall/honeybook-mcp

Made for: Claude Code.

Wrote 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.

agentmods badge for honeybook-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/chrischall/honeybook-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/chrischall/honeybook-mcp/claude-md)
Your own site
<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.

agentmods 80×15 button for honeybook-mcp CLAUDE.md

Your own site · 80×15
<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>
Per session 6,315 This file is loaded in full into every session.
When invoked 6,315 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.06315 $0.06315
Opus 5.5 $0.02526 $0.02526
Sonnet 5.5 $0.01263 $0.01263
Haiku 4.5 $0.00632 $0.00632

Measured yesterday against content hash 220fe76f54a6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 yesterday.

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.

CLAUDE.md · 445 lines

How it starts

The opening of the file, as written. The whole thing — 445 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             # typecheck (src, then src + tests via tsconfig.test.json) + 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, hbApiRequest
                         (on mcp-utils createApiClient, fleet-audit#1380),
                         401 + 404/HBUnauthorizedError, 429, HBWrongAPIVersion,
                         CDN/WAF block page → EdgeBlockedError
                         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
  vendor-secrets.ts      VENDOR_SECRET_KEYS + scrubVendorSecrets (vendor Zoom
                         host link / zak) — applied to every parsed response
                         in hbApiRequest, and again by the feed summarizers
  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 (compact = id/type/brand/last4/
                         expiry/default; billing name+address and Stripe refs
                         only under view:'raw')
    contracts.ts         sign_contract (deep-link fallback + confirm-token gate)
    invoices.ts          pay_invoice (deep-link fallback + confirm-token gate)
    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-
                         token gate + 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)

Read the full file on GitHub · 445 lines

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.

  1. yesterday Changed · +11 lines · +218 tokens per session 220fe76f54a6
  2. 20d ago Changed · +1 lines · +18 tokens per session 1b5512116143
  3. 21d ago Changed · +16 tokens per session ecb7fc01c10b
  4. 28d ago Changed · +3 lines · +53 tokens per session a21e47ff98ef
  5. 1mo ago Changed · +1 lines · +3 tokens per session d785cf4c26d0
  6. 1mo ago Changed · +2 lines · +34 tokens per session 7d0a31f3bb31
  7. 1mo ago Changed · +2 lines · +35 tokens per session dc198378a36a
  8. 1mo ago Changed · +8 lines · +141 tokens per session c08e45525b23
  9. 2mo ago Changed · +12 lines · +214 tokens per session 00f7ff778b7d
  10. 2mo ago First seen · 405 lines · 5,583 tokens per session scan A ece731262e06

Subscribe to this mod's changes

honeybook-mcp CLAUDE.md is an instructions file published in the GitHub repository chrischall/honeybook-mcp (1 stars, last pushed 2d ago), licensed MIT. It adds 6,315 tokens to every session, about $0.0253 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 2026-08-31.

Related

honeybook-mcp CLAUDE.md compared with instructions from other repositories

honeybook-mcp CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
honeybook-mcp CLAUDE.mdchrischall/honeybook-mcpInstructions file12d agoMITA6,315Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode