early_mcp: Instructions file for Codex

AGENTS.md

early_mcp AGENTS.md is an instructions file for Codex, OpenCode from sakebomb/early_mcp. It costs 612 tokens per session, scanned A, original, MIT.

Project-specific instructions for developing an MCP server and command-line tool for the EARLY time tracker, which records work time through the Timeular API. They point agents to the relevant code, documentation, tests, and commands.

In plain words
What is it for?
They are for navigating the repository, checking timer and API behavior, and running its Python test suite.
Why use it?
They reduce guesswork about where features live, how credentials work, and how to run the mocked tests.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions Claude Code; mentions AGENTS.md.

This is sakebomb/early_mcp's own configuration. It tells Codex and OpenCode how to work on early_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 early_mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to sakebomb/early_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/sakebomb/early_mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/sakebomb/early_mcp

Made for: Codex, OpenCode.

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 early_mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/sakebomb/early_mcp/agents-md/github.svg)](https://agentmods.dev/instructions/sakebomb/early_mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/sakebomb/early_mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/sakebomb/early_mcp/agents-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 early_mcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/sakebomb/early_mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/sakebomb/early_mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 612 This file is loaded in full into every session.
When invoked 612 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 $0.00612 $0.00612
Opus 5.5 $0.00245 $0.00245
Sonnet 5.5 $0.00122 $0.00122
Haiku 4.5 $0.00061 $0.00061

Measured 5d ago against content hash 70d72503f5aa, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

early_mcp AGENTS.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 5d 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.

AGENTS.md · 47 lines

How it starts

The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

early_mcp is an MCP server and CLI for the EARLY time tracker (Timeular v4 API). See its row in the Component Map. Tools, settings and CLI usage: README.md. This file is a map, not the full story. Details live in the docs it names, so open the named doc before answering from the map.

Where to look

You need Look in
MCP tool definitions, overlap refusal early.py; tool hints and stop-timer rules in README.md
API client, auth, date and timezone helpers early_client.py; dates and timezones in README.md
CLI for hooks and timers early_cli.py; usage in README.md ("Command line")
Tests (mocked HTTP) tests/; overlap rules in tests/test_overlaps.py
Dependencies and pytest config pyproject.toml, uv.lock
PR review workflow .github/workflows/claude.yml

Build and test

There is no test CI: the only workflow, claude.yml, reviews PRs. Run the tests by hand; they mock all HTTP and need no credentials:

uv sync
uv run pytest

The server reads its credentials from the environment, set in the MCP client's env block (README.md, "Claude Code"; the code does not load a .env file), by name only: EARLY_API_KEY, EARLY_API_SECRET. Optional: EARLY_BASE_URL, EARLY_TIMEZONE, EARLY_EXPLORE_ALLOW_WRITES.

Git

Branch from origin/main in your own worktree (feat/, fix/, refactor/, test/); the main checkout may hold someone's in-progress branch. One PR per change, squash-merged by the operator.

Where it runs

An MCP server over stdio, started by the client with uv run --directory <checkout> python early.py (registration is in README.md, "Claude Code"). early_cli.py runs the same way for hooks. A merged change takes effect when the operator pulls main in the checkout the client points at and the client restarts the server.

Never

  • Call the live EARLY API from tests or while investigating. It holds real time entries.
  • Bypass the overlap refusal in early.py: a write that overlaps existing entries is refused unless overwrite is set. Do not set it by default or to get a test or command past the check.
  • Commit credentials or a .env file.
  • Send POST/PATCH/PUT/DELETE through explore_api while testing.

Read the full file on GitHub · 47 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. 5d ago First seen · 47 lines · 612 tokens per session scan A 70d72503f5aa

Subscribe to this mod's changes

early_mcp AGENTS.md is an instructions file published in the GitHub repository sakebomb/early_mcp (1 stars, last pushed 5d ago), licensed MIT. It adds 612 tokens to every session, about $0.0024 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 2026-11-13.

Related

early_mcp AGENTS.md compared with instructions from other repositories

early_mcp AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
early_mcp AGENTS.mdsakebomb/early_mcpInstructions file15d agoMITA612Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file144kyesterdayMITA8,130Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file150ktodayMITA4,680Codex, OpenCode
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file284ktodayMITA4,342Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA3,153GitHub Copilot