agentmods.dev

mcpforwork CLAUDE.md

mcpforwork CLAUDE.md is an instructions file for coding agents from avivancos/mcpforwork. It costs 646 tokens per session, scanned A, original, Apache-2.0.

A Claude Code instruction file that adds tool-specific guidance while requiring agents to follow the project’s main AGENTS.md rules first.

In plain words
What is it for?
Use it to direct Claude Code through backlog states, real-database testing, zero-mock TDD, dependency decisions, and required project commands.
Why use it?
It gives Claude Code a concise operating contract, so it follows the backlog process, test-driven development, architecture limits, and project invariants consistently.

Instructions file

not rated 0 1mo ago A scan 646 tokens original Apache-2.0
View the source file avivancos/mcpforwork mcpfor.work
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/avivancos/mcpforwork/claude-md
Clone the repo
git clone --depth 1 https://github.com/avivancos/mcpforwork

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 mcpforwork CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/avivancos/mcpforwork/claude-md.svg)](https://agentmods.dev/instructions/avivancos/mcpforwork/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/avivancos/mcpforwork/claude-md"><img src="https://agentmods.dev/badge/instructions/avivancos/mcpforwork/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 646 This file is loaded in full into every session.
When invoked 646 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00646 $0.00646
Opus 5 $0.00323 $0.00323
Sonnet 5 $0.00129 $0.00129
Haiku 4.5 $0.00065 $0.00065

Measured 4d ago against content hash 9419b90693b3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

mcpforwork 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 4d 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 · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — Claude Code complement

Read AGENTS.md first — it is the source of truth. This file only adds Claude-Code-specific operational notes. Everything in AGENTS.md (product invariants, hexagonal boundaries, anti-over-engineering charter, zero-mocks TDD, backlog workflow, fused review gate, explicit-path commits) applies verbatim here. On conflict, AGENTS.md wins.

The same suite is read by OpenAI Codex and Cursor via AGENTS.md; when you change an obligation, mirror it.

Quick contract (the non-negotiables, condensed)

  1. Backlog-first. Card in backlog/pending/ → moved to in_progress/ before touching code. Lifecycle and states: backlog/agent_index.md §2 (the folder a card sits in IS its state). Override only if the user says "ignore the backlog".
  2. TDD, ZERO mocks. Red → green → refactor. Real SQLite at tmp_path, live Postgres behind @pytest.mark.live, pytest-httpserver + recorded fixtures for HTTP, time/seed injected. Details: AGENTS.md §4.
  3. Anti-over-engineering charter is P0. Rule of two, one justification line per new dependency, YAGNI, architecture freeze. AGENTS.md §3.
  4. Product invariants are structural. Zero server-side LLM, consent gate, open-core SQLite parity, facts inventory, packs-as-data. AGENTS.md §1.
  5. At close: targeted tests green → fused review gate (test-code-reviewer, model: inherit — includes the regression audit) PASS → documentor subagent updates the module docs under docs/ → move card to done/ → Conventional Commit staging only this task's files by explicit path (code + docs + card).

Claude Code specifics

  • Review gate: the single fused reviewer is .cursor/agents/test-code-reviewer.md (Cursor canonical; mirrored at .claude/agents/; test audit + code review + regression audit; model: inherit). Spawn via Task without a model parameter so Cursor inherits the parent. Fix P0/P1; rerun after fixes. Simplicity/security reviews are on-demand, not a gate (ADR 0007).
  • Plan first for non-trivial cards (plan mode); get sign-off before writing code.
  • Before saying "done": run the AGENTS.md §8 commands and report what you actually observed — never assume a check is green.

Read the full file on GitHub · 51 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. 4d ago First seen · 51 lines · 646 tokens per session scan A 9419b90693b3

Subscribe to this mod's changes

mcpforwork CLAUDE.md is an instructions file published in the GitHub repository avivancos/mcpforwork (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 646 tokens to every session, about $0.0032 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

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

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.

github/spec-kit · 7,104 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