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/tracegazer/clockify-mcp/claude-mdgit clone --depth 1 https://github.com/tracegazer/clockify-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/tracegazer/clockify-mcp/claude-md)<a href="https://agentmods.dev/instructions/tracegazer/clockify-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/tracegazer/clockify-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 | $0.02024 | $0.02024 |
| Opus 5 | $0.01012 | $0.01012 |
| Sonnet 5 | $0.00405 | $0.00405 |
| Haiku 4.5 | $0.00202 | $0.00202 |
Grade A, and why
clockify-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 3d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Project Overview
clockify-mcp is an MCP server for the Clockify time-tracking API. It exposes Clockify workspaces, users, groups, clients, projects, tasks, and tags as Model Context Protocol tools so any MCP-compatible client (Claude Desktop, Cursor, etc.) can query time-tracking data in natural language.
Current phase: Phase 0–8b (v1 complete + extensions) — 112 tools across 18 domains (48 read + 64 opt-in write; 117 @mcp.tool registrations — time_entries re-registers 5 time-entry writes for the time-tracking mode) (Workspaces, Users, Groups, Clients, Projects, Tasks, Tags, Time entries, Reports, Shared reports, Time off, Holidays, Expenses, Approvals, Custom fields, Scheduling, Invoices, Webhooks). Writes (create/update/delete for clients/projects/tasks/tags/time_entries/holidays, plus time-entry duplicate/bulk, time-off policy/request create/approve/reject/withdraw, expense + expense-category create/update/delete/archive, approval submit/resubmit/update, custom-field create/update/delete and project set/remove, scheduling assignment create/update/delete/publish/copy, invoice create/update/change-status/duplicate/delete and item/payment management, and webhook create/update/delete/generate-token) register according to CLOCKIFY_ACCESS_MODE: read (default, none), time-tracking (only time-entry writes — duplicate/bulk self-scoped to the authenticated user), or full (all writes; CLOCKIFY_ENABLE_WRITES=true is an alias for full). All planned v1 domains are implemented; OpenTelemetry OTLP export (traces, metrics, logs) is implemented and opt-in via CLOCKIFY_TELEMETRY.
Architecture
Python-based MCP server using the mcp package (FastMCP). Modular by domain: each src/clockify_mcp/domains/*.py module owns its tools and registers them via register(mcp, client). The server layer (server.py) is thin — it builds the client + telemetry, calls each domain's register(), and exposes a main() entry point with argparse.
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.
- 3d ago First seen · 62 lines · 2,024 tokens per session scan A 53435649f8a3
clockify-mcp CLAUDE.md is an instructions file published in the GitHub repository tracegazer/clockify-mcp (1 stars, last pushed 1mo ago), licensed MIT. It adds 2,024 tokens to every session, about $0.0101 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
llm-context.py CLAUDE.md
Instructions for cyberchitta/llm-context.py, covering claude.md, working notes (gitignored) and draining the field notes.
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
seekstone CLAUDE.md
Instructions for shaqmughal/seekstone, covering claude.md, what this repo is, commands, the harness itself (run after npm install) and architecture.
Plonk AGENTS.md
AGENTS.md instructions for ostapondo/Plonk, covering agent rules, layout, adding a module, build & verify and code style.
mcp-dockhand copilot-review.instructions.md
Copilot instructions for strausmann/mcp-dockhand: When reviewing pull requests in this repository.
second-brain AGENTS.md
Instructions for LindaHaviv/second-brain, covering instructions for ai coding agents, what to read first, the rules (non-negotiable), common tasks, the sanctioned way and enforcement, not just instructions.