node-huckleberry-mcp: Instructions file for Claude Code

CLAUDE.md

node-huckleberry-mcp CLAUDE.md is an instructions file for Claude Code from KenLSM/node-huckleberry-mcp. It costs 553 tokens per session, scanned A, original, MIT.

Repository instructions for contributors to a TypeScript project called node-huckleberry-mcp. They point developers to the project’s architecture, task roadmap, conventions, security guidance, and required checks.

In plain words
What is it for?
Use them when starting a task, choosing work from the roadmap, checking the Firebase and Firestore setup, or preparing a branch and pull request.
Why use it?
They provide one place to learn how the repository works and how changes should be made safely. They also clarify which build, lint, formatting, and test commands must pass.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

This is KenLSM/node-huckleberry-mcp's own configuration. It tells Claude Code how to work on node-huckleberry-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 node-huckleberry-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to KenLSM/node-huckleberry-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/KenLSM/node-huckleberry-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/KenLSM/node-huckleberry-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 node-huckleberry-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/kenlsm/node-huckleberry-mcp/claude-md.svg)](https://agentmods.dev/instructions/kenlsm/node-huckleberry-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/kenlsm/node-huckleberry-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/kenlsm/node-huckleberry-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 553 This file is loaded in full into every session.
When invoked 553 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 $0.00553 $0.00553
Opus 5 $0.00277 $0.00277
Sonnet 5 $0.00111 $0.00111
Haiku 4.5 $0.00055 $0.00055

Measured 7d ago against content hash 4d25165ca505, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

node-huckleberry-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 7d 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.

CLAUDE.md · 43 lines

How it starts

The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

See AGENTS.md — the canonical contributor guide for this repo (architecture, conventions, how to pick up tasks, secrets/safety).

Quick orientation:

  • TASKS.md — the roadmap and source of truth for what to build, in what order, and which model tier to use per task.
  • docs/architecture.md — the verified auth/data mechanism, live Firebase config, Firestore schema, and the T0.2 decision (use the Firebase JS SDK).

Toolchain: TypeScript + oxc (oxlint + oxfmt) + Vitest — not ESLint/Prettier/Jest. Before committing run npm run build, npm run lint, npm run format, and npm test (all must pass). See AGENTS.md → Toolchain for details.

Branch hygiene: one concern per branch, one branch per PR — start each task from a fresh branch off main, and never bundle unverified work with verified work. See AGENTS.md → Git → Branch hygiene.

Note — we deviate from the Python reference; verify features ourselves

The Python projects (Woyken/py-huckleberry-api, bckenstler/py-huckleberry-mcp) are a reference for leads, not a spec to copy. They are themselves reverse-engineered and can be wrong, incomplete, or stale, and we have intentionally diverged (oxc/Vitest toolchain, lenient read models, a different tool surface, no active-session timers).

For any new feature, verify the real Huckleberry/Firestore behavior ourselves before trusting it — don't port a write shape or field name on the Python project's word. The loop:

  1. Do the action in the official Huckleberry app.
  2. Inspect the resulting Firestore document(s) — npm run inspect:schema.
  3. Build the Zod model + op to the observed shape (not the Python one).
  4. Prove it with a gated live round-trip (HUCKLEBERRY_ALLOW_WRITES=1).

Where the real backend disagrees with the Python port, follow the backend. See docs/discovery-plan.md for how we map the full API/Firestore surface, and TASKS.md → B5 for a known live-confirmed deviation (solids food tracking: the Python log_solids stores foods/reactions and a different custom-food doc shape than we currently write).

Read the full file on GitHub · 43 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. 7d ago First seen · 43 lines · 553 tokens per session scan A 4d25165ca505

Subscribe to this mod's changes

node-huckleberry-mcp CLAUDE.md is an instructions file published in the GitHub repository KenLSM/node-huckleberry-mcp (1 stars, last pushed 18d ago), licensed MIT. It adds 553 tokens to every session, about $0.0028 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.

Related

Other instructions, from other repositories

data-scientist copilot-instructions.md

Repository instructions for a data-science workflow in GitHub Copilot, covering datasets, statistics, and analysis files.

realnghon/data-scientist · 373 tokens

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.

openai/codex · 5,182 tokens

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).

microsoft/vscode · 6,785 tokens

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.

vercel/next.js · 7,296 tokens

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.

langchain-ai/langchain · 4,469 tokens

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).

microsoft/vscode · 5,001 tokens