agentmods.dev

coach GEMINI.md

coach GEMINI.md is an instructions file for Gemini CLI from watt-mind/coach. It costs 763 tokens per session, scanned A, original, Apache-2.0.

A set of instructions for Gemini CLI in the watt-mind/coach repository. It points to the main agent guidance and adds current notes about type checking, pricing, wellness data, integrations, and chat behavior.

In plain words
What is it for?
Use it when Gemini CLI works on this repository and needs guidance for type checks, pricing and entitlements, health integrations, location data, or AI chat implementation.
Why use it?
It gives Gemini CLI project context that may not be obvious from the code alone, including which checks are authoritative and which product areas are changing.

Instructions file for Gemini CLI

not rated 83 2d ago A scan 763 tokens original Apache-2.0
View the source file watt-mind/coach
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/watt-mind/coach/gemini-md
Clone the repo
git clone --depth 1 https://github.com/watt-mind/coach

Made for: Gemini CLI.

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 coach GEMINI.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/watt-mind/coach/gemini-md.svg)](https://agentmods.dev/instructions/watt-mind/coach/gemini-md)
Your own site
<a href="https://agentmods.dev/instructions/watt-mind/coach/gemini-md"><img src="https://agentmods.dev/badge/instructions/watt-mind/coach/gemini-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 763 This file is loaded in full into every session.
When invoked 763 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 $0.00763 $0.00763
Opus 5 $0.00381 $0.00381
Sonnet 5 $0.00153 $0.00153
Haiku 4.5 $0.00076 $0.00076

Measured 3d ago against content hash e7b72d204fa8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

coach GEMINI.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.

GEMINI.md · 36 lines

How it starts

The opening of the file, as written. The whole thing — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GEMINI.md

Gemini, please refer to AGENTS.md and docs/04-guides/issue-management.md for the primary repository context, architecture, commands, operational rules, and Linear issue management standards.

This file (GEMINI.md) is an entry point to ensure you find the centralized instructions.

Hot context (product notes)

Ongoing project state that has not yet been fully folded into AGENTS.md or docs/:

  • Typechecks: pnpm typecheck is the canonical fresh check; use pnpm typecheck:fast, :app, :server, or :watch for shorter feedback loops. See docs/04-guides/typechecking.md.
  • Pricing Transition: Transitioning from 'Free for Early Adopters' to tiered structure: Free ($0), Supporter ($8.99/mo), and Pro ($14.99/mo). See docs/06-plans/pricing-and-entitlements.md.
  • Wellness Tracking: Weight and Blood Pressure via Intervals.icu.
  • Oura Integration: SpO2, Stress, VO2 Max, and Weight. Raw biometrics (HRV/RHR) are extracted to avoid score conflicts.
  • Location Tracking: cw:cli users location tools manage user countries based on last login IP.
  • Chat Stability: AI SDK v5 UIMessage schema. See docs/04-guides/chat-development.md.
  • LLM Response Mocking: Flat JSON fixtures in tests/fixtures/llm-mocks/ when MOCK_LLM_RESPONSES=true. Update/create tests/fixtures/llm-mocks/${operation}.json when AI schemas or operations change. See docs/04-guides/e2e-testing.md.
  • Git & PR Workflow: PRs target develop (gh pr create --base develop). Merge: ticket branches → develop → master. No direct pushes to master or develop.

Feature pointers

  • CLI Reference: docs/04-guides/cli-reference.md — maintain whenever the CLI changes.
  • Nutrition Logic: docs/02-features/nutrition/fueling-logic.md
  • System Messages: docs/02-features/system-messages.md
  • Email System: docs/02-features/email-communication.md
  • Chat Development: docs/04-guides/chat-development.md
  • Timezone Handling: docs/04-guides/timezone-handling.md
  • E2E Testing: docs/04-guides/e2e-testing.md — targeted specs during development; full suite (pnpm test:e2e) when work is complete.

Read the full file on GitHub · 36 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. 3d ago First seen · 36 lines · 763 tokens per session scan A e7b72d204fa8

Subscribe to this mod's changes

coach GEMINI.md is an instructions file published in the GitHub repository watt-mind/coach (83 stars, last pushed 2d ago), licensed Apache-2.0. It adds 763 tokens to every session, about $0.0038 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.

DatabasesProductivityai-coachcyclingendurance-sportsfitnessrunningself-hosted
Related

Other instructions, from other repositories

garmin-health-data CLAUDE.md

Instructions for diegoscarabelli/garmin-health-data, covering claude.md, readme.md, database schema architecture, schema documentation and formatting ddl files.

diegoscarabelli/garmin-health-data · 1,240 tokens

strava-mcp AGENTS.md

Instructions for davidmosiah/strava-mcp, covering agent development notes, scope, commands and rules.

davidmosiah/strava-mcp · 152 tokens

igpsport-mcp CLAUDE.md

Instructions for dengxuhui/igpsport-mcp, covering claude.md, 项目定位, 不要做的事(已决策,勿回头), 核心架构 and 17 个 mcp tool.

dengxuhui/igpsport-mcp · 2,436 tokens

munin-memory CLAUDE.md

Claude Code instructions for Magnus-Gille/munin-memory, a project described as: Persistent memory for AI assistants, self-hosted and provider-portable. MCP server with SQLite + FTS5 + sqlite-vec.

Magnus-Gille/munin-memory · 39 tokens

strava-cli AGENTS.md

AGENTS.md instructions for eddmann/strava-cli: Prefer make targets over direct commands. Run make help to see available targets.

eddmann/strava-cli · 85 tokens

garmin-connect-cli AGENTS.md

Instructions for eddmann/garmin-connect-cli: Prefer make targets over direct commands. Run make help to see available targets.

eddmann/garmin-connect-cli · 85 tokens