Borrowing it
Nothing to install: this file belongs to Smart-AI-Memory/attune-ai. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Smart-AI-Memory/attune-ai/main/.agents/skills/coach/SKILL.mdgit clone --depth 1 https://github.com/Smart-AI-Memory/attune-aiWrote 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/skills/smart-ai-memory/attune-ai/coach)<a href="https://agentmods.dev/skills/smart-ai-memory/attune-ai/coach"><img src="https://agentmods.dev/badge/skills/smart-ai-memory/attune-ai/coach/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.
<a href="https://agentmods.dev/skills/smart-ai-memory/attune-ai/coach"><img src="https://agentmods.dev/badge/skills/smart-ai-memory/attune-ai/coach.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00046 | $0.01223 |
| Opus 5.5 | $0.00018 | $0.00489 |
| Sonnet 5.5 | $0.00009 | $0.00245 |
| Haiku 4.5 | $0.00005 | $0.00122 |
Grade A, and why
coach 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 1mo 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 — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Coach
IMPORTANT: Start your response by telling the user:
Coach — Explains any Attune topic with progressive depth — concept, then how-to, then full reference.
How It Works
Each depth level serves a different type of content, not just more of the same:
| Level | Type | What you get |
|---|---|---|
| 0 | Concept | What is it? When to use it? |
| 1 | Procedural | Step-by-step: how to run it |
| 2 | Reference | Full detail, edge cases, links |
Repeated calls on the same topic auto-advance. A new topic resets to concept.
Commands
Topic Lookup (default)
If the user provided a topic, call:
help_lookup(topic="<topic>", mode="progressive")
Use the bare topic slug — the engine resolves the right template type at each level:
| User says | Topic slug |
|---|---|
| security audit | security-audit |
| code review | code-review |
| code quality | code-quality |
| bug predict | bug-predict |
| test gen | test-generation |
| release | release-prep |
| refactor | refactor-plan |
| doc gen | doc-gen |
If the user says "tell me more" or "go deeper"
without a new topic, call help_lookup with the
same topic again — it auto-advances to the next
level.
If the user says "start from the beginning" or "reset", call:
help_lookup(topic="<topic>", mode="progressive", reset=true)
If the user just finished a workflow, use
last_workflow to skip the concept and start at
procedural:
help_lookup(
topic="<topic>",
mode="progressive",
last_workflow="<workflow-name>"
)
For file-based warnings:
help_lookup(
topic="warnings",
mode="precursor",
file_path="<path to file>"
)
Init (/coach init)
Bootstrap a project-local help system. Two-step
Socratic flow using the help_init MCP tool.
Step 1 — Scan and propose:
help_init(action="scan")
This returns a list of proposed features with name, description, files, tags, confidence, and reason.
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.
- 1mo ago First seen · 225 lines · 46 tokens per session scan A 26b25b81fa89
coach is a skill published in the GitHub repository Smart-AI-Memory/attune-ai (11 stars, last pushed yesterday), licensed Apache-2.0. It adds 46 tokens to every session and 1,223 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
tome
Converting technical knowledge into durable learning documents and publishable articles. Use for diff-based teaching, decision records, onboarding, note/Zenn/Qiita/dev.to posts, article series, retrospectives, and cross-platform repurposing.
retro
Facilitate a structured sprint retrospective — what went well, what didn't, and prioritized action items with owners and deadlines. Use when running a retrospective, reflecting on a sprint, creating action items from team feedback, or learning how to run effective retros.
edtech-compliance
Playbook for edtech regulatory compliance — COPPA (US under-13), FERPA (US schools), GDPR-K (EU age of digital consent matrix), state student-privacy laws (CA, NY 2-D, etc.), Section 508 accessibility.
Tutor Reasoning
Visible reasoning contract for teaching, guided explanation, and learning-oriented tool use.
traffic_signs
Vietnamese traffic signs: prohibitory, warning, mandatory, informational.
asa-reader-layer-writer
Use when turning structured skill decomposition artifacts into beginner, expert, report, or Obsidian reading layers.