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/andamio-platform/coach/agents-mdgit clone --depth 1 https://github.com/Andamio-Platform/coachWrote 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/andamio-platform/coach/agents-md)<a href="https://agentmods.dev/instructions/andamio-platform/coach/agents-md"><img src="https://agentmods.dev/badge/instructions/andamio-platform/coach/agents-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 | $0.01246 | $0.01246 |
| Opus 5 | $0.00623 | $0.00623 |
| Sonnet 5 | $0.00249 | $0.00249 |
| Haiku 4.5 | $0.00125 | $0.00125 |
Grade A, and why
coach 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 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Project context for AI agents working in this repository. Read this file to understand the project, conventions, and workflow.
Project Overview
Coach is a skills and knowledge workspace for AI-assisted course development. The primary artifacts are agent skill definitions (skills/), YAML knowledge files (knowledge/), and markdown documentation.
This is not a code project. Course content lives in separate repos that symlink to this one. See docs/setup-course-repo.md for the pattern.
Directory Structure
skills/ # Agent skill definitions (15 skills, Agent Skills standard)
start/ # Entry point — welcome and pathway selection
beginner/ # Guided pathway for new course creators
apprentice/ # Collaborative pathway for content experts
teacher/ # Fast-track pathway for experienced educators
course-workflow/ # Orchestrates the 12-phase workflow
draft-slts/ # Generates SLTs from topic, audience, and goals
assess-slts/ # Evaluates SLT quality across 5 dimensions
self-assess-readiness/ # Evaluates coaching readiness per SLT
classify-lesson-types/ # Classifies SLTs by lesson type
gather-screenshots/ # Screenshot checklists for Product Demo lessons
gather-code-examples/ # Code example checklists for Developer Documentation
compound/ # Extracts patterns to improve future runs
compile/ # Packages modules into Andamio import format
andamio-cli/ # Import/export content via Andamio CLI
release/ # Publishes new versions across all channels
knowledge/ # Compound knowledge base (YAML files)
index.yaml # Master index and aggregate stats
voice-patterns.md # Prose style guide for lesson writing
slt-patterns/ # Verb bank, quality issues, successful rewrites
readiness/ # Context leverage rankings, calibration data
lesson-types/ # Heuristics and edge cases
lesson-writing/ # Style anti-patterns and acceptable patterns
compile/ # Import gotchas discovered during platform uploads
research/ # SLT research report
docs/ # Framework and product documentation
scripts/ # Setup script for course repos
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 · 95 lines · 1,246 tokens per session scan A ed9acf16990e
coach AGENTS.md is an instructions file published in the GitHub repository Andamio-Platform/coach (6 stars, last pushed 1mo ago), licensed MIT. It adds 1,246 tokens to every session, about $0.0062 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
redux-saga-skill AGENTS.md
Instructions for anivar/redux-saga-skill, covering redux-saga — complete guide, abstract, 1. effects & yielding, rule: always yield effects and rule: use call() for async functions.
echo-kaoyan-english-skill CLAUDE.md
Claude Code instructions for nghjjnjnf/echo-kaoyan-english-skill, covering echo考研英语skill for claude code, canonical instructions, operating rules and broad request policy.
echo-kaoyan-english-skill AGENTS.md
AGENTS.md instructions for Echo1LZJY/echo-kaoyan-english-skill, covering echo考研英语skill agent guide, source of truth, agent routing, corpus workflow and broad request policy.
echo-kaoyan-english-skill CLAUDE.md
Claude Code instructions for Echo1LZJY/echo-kaoyan-english-skill, covering echo考研英语skill for claude code, canonical instructions, operating rules and broad request policy.
open-dictionary AGENTS.md
Instructions for ahpxex/open-dictionary, covering open dictionary rewrite charter, product framing, core workflow, technical framework and 1. raw ingestion layer.
ab900 CLAUDE.md
Instructions for timothywarner-org/ab900, covering claude.md, repository purpose, architecture, commands and 2. non-ascii punctuation -- must return zero.