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.
npx agentmods add instructions/red-square-software/keeping-mcp/claude-mdgit clone --depth 1 https://github.com/Red-Square-Software/keeping-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/red-square-software/keeping-mcp/claude-md)<a href="https://agentmods.dev/instructions/red-square-software/keeping-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/red-square-software/keeping-mcp/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 | $0.03213 | $0.03213 |
| Opus 5 | $0.01606 | $0.01606 |
| Sonnet 5 | $0.00643 | $0.00643 |
| Haiku 4.5 | $0.00321 | $0.00321 |
Grade A, and why
keeping-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 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.
How it starts
The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project
keeping-mcp
Open-source Model Context Protocol (MCP) server that exposes the Keeping (api.keeping.nl) time-tracking API as tools an AI coding assistant can call. Built for solo developers who use Claude Code (or any MCP-capable client) and want their billable hours logged into Keeping at the end of a session instead of typed in by hand, while keeping Keeping's existing native Jortt invoicing integration intact.
Core Value: A Claude Code (or any MCP client) user can log a reviewed time entry into their Keeping account through a single tool call, with explicit confirmation before anything is written.
Constraints
- Tech stack: TypeScript on Node.js, official
@modelcontextprotocol/sdk, Zod for tool input schemas. — User's first MCP server; matches the dominant ecosystem and registry tooling. - License: MIT. — Standard for MCP servers; permissive enough for downstream packaging.
- Hosting / namespace: GitHub repo under the
Red-Square-Softwareorg; npm package namekeeping-mcp(unscoped) and MCP Registry namespaceio.github.Red-Square-Software/keeping-mcp. Canonical GitHub org casing is required by the OIDC subject claim. — Required by the MCP registry's GitHub-verified namespace model. - Security: Personal access token must never appear in logs, tool output, or commits. Read only from env var. — Billable-hours data and a write-capable API token; leak is high-impact.
- API: Must respect Keeping's 120 req/min rate limit, and must scope writes to the authenticated user (only admins can write other users' entries; v1 deliberately does not target that path).
- Platform: User runs Claude Code on Windows 11. Server must work on Windows + macOS + Linux (Node.js + npx covers this, but path/env handling needs to stay portable).
Technology Stack
Recommended Stack
Core Technologies
| Technology | Version | Purpose | Why Recommended |
|---|---|---|---|
@modelcontextprotocol/sdk |
^1.29.0 |
MCP protocol implementation (server primitives, stdio transport, tool registration) | Latest stable v1.x; v2.0 is pre-alpha (API unstable, stable v2 estimated Q3 2026). v1.29.0 is the most recent production-ready release. |
| TypeScript | ^5.8.0 |
Type-safe source language | SDK docs require "module": "Node16" + "moduleResolution": "Node16" or "Bundler" — TS 5.x enforces these correctly. |
| Node.js | >=22.0.0 |
Runtime | Node 20 reached EOL 2026-04-30; Node 22 is current Active LTS (supported until 2027-04-30). Stable native fetch. 30 % faster startup than Node 20. Target >=22 in engines field. |
| Zod | ^3.25.0 |
Tool input schema validation | SDK 1.x internally imports from zod/v4 but maintains backwards compatibility for Zod >=3.25. Zod v3.25+ is the safe floor — resolves the w._parse is not a function breakage seen in earlier SDK versions. Use import * as z from "zod" (v3 entry point). If you want v4 features, use import * as z from "zod/v4" — both work with SDK 1.29+. |
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.
- 4d ago First seen · 144 lines · 3,213 tokens per session scan A d4302fbee433
keeping-mcp CLAUDE.md is an instructions file published in the GitHub repository Red-Square-Software/keeping-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 3,213 tokens to every session, about $0.0161 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
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.
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.