attune-ai: Skill for Claude Code

.agents/skills/attune/SKILL.md

attune is a skill for Claude Code, Codex from Smart-AI-Memory/attune-ai. It costs 12 tokens per session (1,728 once invoked), scanned A, original, Apache-2.0.

A developer workflow assistant that uses questions to guide coding tasks. It can route a request to activities such as debugging, security checks, or code changes.

In plain words
What is it for?
It helps investigate errors, review or improve code, run security audits, and select workflows through commands or natural-language requests.
Why use it?
It helps turn a vague request into the right development workflow while allowing clear, specific requests to proceed directly.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: names the AskUserQuestion tool; installed under .agents/ (shared by several agents).

This is Smart-AI-Memory/attune-ai's own configuration. It tells Claude Code and Codex how to work on attune-ai 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 attune-ai configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/Smart-AI-Memory/attune-ai/main/.agents/skills/attune/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Smart-AI-Memory/attune-ai

Made for: Claude Code, Codex.

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 attune

README.md
[![agentmods](https://agentmods.dev/badge/skills/smart-ai-memory/attune-ai/attune.svg)](https://agentmods.dev/skills/smart-ai-memory/attune-ai/attune)
Your own site
<a href="https://agentmods.dev/skills/smart-ai-memory/attune-ai/attune"><img src="https://agentmods.dev/badge/skills/smart-ai-memory/attune-ai/attune.svg" alt="Measured on agentmods" height="20"></a>
Per session 12 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,728 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00012 $0.01728
Opus 5 $0.00006 $0.00864
Sonnet 5 $0.00002 $0.00346
Haiku 4.5 $0.00001 $0.00173

Measured 8d ago against content hash b49a64464a43, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

attune 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 8d 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/skills/attune/SKILL.md · 249 lines

How it starts

The opening of the file, as written. The whole thing — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.

attune

Your AI-powered developer workflow assistant with Socratic discovery.

One command. Every workflow.

How It Works

Type /attune and I'll guide you through questions to find the right workflow.

/attune                              # Start Socratic discovery
/attune "I need to fix a bug"        # Natural language
/attune debug                        # Direct shortcut

Fast-Path Detection

When the user provides sufficient context inline, skip scoping questions and execute directly. This satisfies the Socratic requirement because the user's explicit args provide the scoping context.

Fast-path triggers (execute immediately):

  • Specific subcommand + target path: /attune security-audit ./src
  • Natural language with clear scope: /attune "review src/auth"
  • Explicit --auto flag: /attune commit --auto

Socratic flow (ask questions first):

  • /attune (no args)
  • /attune "fix something" (vague)

Rule: If input contains BOTH an action AND a target, proceed to execution. If either is missing or ambiguous, use AskUserQuestion.

Workflows by Goal

🔧 Fix or Improve Something

Debugging:

  • Investigate errors and exceptions
  • Trace execution flow
  • Identify root causes

Code Review:

  • Quality and pattern analysis
  • Security review
  • Performance review

Refactoring:

  • Improve structure and organization
  • Extract functions/classes
  • Simplify complex code

✅ Validate My Work

Testing:

  • Run test suites
  • Generate new tests

Coverage:

  • Analyze test coverage
  • Identify gaps
  • Boost coverage

Security Audit:

  • Vulnerability scanning
  • Dependency analysis
  • Code security review

Performance Audit:

  • Identify bottlenecks
  • Memory analysis
  • Optimization recommendations

🚀 Ship My Changes

Commit:

  • Stage and commit changes
  • Generate commit messages
  • Follow conventional commits

Pull Request:

  • Create PR with description
  • Review checklist
  • Link to issues

Read the full file on GitHub · 249 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. 8d ago First seen · 249 lines · 12 tokens per session scan A b49a64464a43

Subscribe to this mod's changes

attune is a skill published in the GitHub repository Smart-AI-Memory/attune-ai (10 stars, last pushed today), licensed Apache-2.0. It adds 12 tokens to every session and 1,728 once invoked, about $0.0001 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.