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 skills/smart-ai-memory/attune-ai/specnpx skills add Smart-AI-Memory/attune-ai --skill specgit 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/spec)<a href="https://agentmods.dev/skills/smart-ai-memory/attune-ai/spec"><img src="https://agentmods.dev/badge/skills/smart-ai-memory/attune-ai/spec.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 5.1 | $0.00054 | $0.03782 |
| Opus 5 | $0.00027 | $0.01891 |
| Sonnet 5 | $0.00011 | $0.00756 |
| Haiku 4.5 | $0.00005 | $0.00378 |
Grade A, and why
spec 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 2d 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 — 407 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spec-Driven Development
Model recommendation: Spec planning and XML-enhanced-prompt
authoring benefit from the Opus tier (claude-opus-4-8). Before
proceeding, suggest a model switch once:
"This is spec work — recommend
/model claude-opus-4-8for stronger structured reasoning. Want to switch?"
Defer to the user's choice if they've already picked a model.
IMPORTANT: Start your response with a context preamble.
Call help_lookup(topic="spec-engine", mode="preamble") and
display the returned preamble text as a blockquote. Then
tell the user they can say "tell me more" for a step-by-step
guide, or answer the scoping questions below to proceed.
If the MCP call fails, fall back to:
Spec — Walks you from idea to working code through brainstorm, plan, review, approve, and execute phases.
Scoping
Use AskUserQuestion to determine the mode:
question: "What would you like to do?"
header: "Spec"
options:
- label: "Start a new spec"
description: "Brainstorm, decompose into tasks, then execute"
- label: "Resume an in-progress spec"
description: "Pick up where you left off"
- label: "Import a spec file"
description: "Load a plan from another project or path"
- label: "Execute a spec"
description: "Review and execute tasks from a saved plan"
If the user provides arguments (e.g., "resume" or a file path), skip the picker and route directly.
New-spec intake (one form, not N questions)
When the route is "Start a new spec", gather the framing as ONE form per the Socratic rule — never as sequential question turns:
python -m attune.elicitation.spec_intake
The JSON payload carries a validated form definition
(attune.elicitation.spec_intake.build_spec_intake_form) —
outcome, done-when acceptance, primary code area (options derived
from the tree's packages), and an optional slug — plus
taken_slugs for collision awareness. Render it widget-first with
the AskUserQuestion fallback (batching opts in via
metadata.source containing "form"). If the user's invocation
already stated what to build, carry it into the outcome field
instead of asking again.
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.
- 2d ago Changed · +26 lines de1151ca2c6a
- 5d ago First seen · 381 lines · 54 tokens per session scan A 714087650803
spec is a skill published in the GitHub repository Smart-AI-Memory/attune-ai (10 stars, last pushed today), licensed Apache-2.0. It adds 54 tokens to every session and 3,782 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
tmux
Manage long-running shell sessions with tmux — start a detached session, run a long task, reattach later, capture output. Use when a task takes longer than a single tool call (build, test, log tail).
lynkr
Universal LLM gateway with intelligent routing, Graphify code intelligence, Distill compression, routing telemetry, Code Mode, and 12+ provider support. 60-80% cost reduction for Claude Code, Cursor, and Codex.
web-research
Use this skill for requests related to web research; it provides a structured approach to conducting comprehensive web research.
story-setup
网文写作工具集基础设施部署。将 hooks/rules/agents/CLAUDE.md/AGENTS.md 等基础设施部署到用户项目目录，支持 Claude Code / OpenCode / Codex / OpenClaw。触发方式：/story-setup、$story-setup、「准备写书」「帮我搭一下环境」「配置写作项目」。.
novel-writing-assets
查看、启用、停用、组合、绑定、试写和重新编译 novel-studio 的长期写法资产。触发：「列出写法特征」「启用/停用某个写法」「组合写法」「绑定写法」「试写写法」「重编译写法规则」「维护写法资产」。.
novel-rewrite
通过 novel-studio pipeline 的 rewrite 阶段按评审反馈逐章 Writer 重写，会改动章节原文。触发：「按评审改写」「重写这几章」「根据意见润色正文」，在 novel-review 之后据反馈落地修改时使用。.