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/planning/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/planning)<a href="https://agentmods.dev/skills/smart-ai-memory/attune-ai/planning"><img src="https://agentmods.dev/badge/skills/smart-ai-memory/attune-ai/planning.svg" alt="Measured on agentmods" 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 | $0.00032 | $0.00609 |
| Opus 5 | $0.00016 | $0.00304 |
| Sonnet 5 | $0.00006 | $0.00122 |
| Haiku 4.5 | $0.00003 | $0.00061 |
Grade A, and why
planning 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 7d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Planning
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:
Planning — Helps you plan features, architecture, and TDD strategy before writing code.
High-level development planning and architecture design.
Routes
| Subcommand | Action |
|---|---|
feature |
Plan a new feature |
tdd |
Plan TDD approach |
architecture |
Architecture review |
MCP Tools
| Tool | What It Does |
|---|---|
research_synthesis |
Synthesize insights from source documents at a path to inform planning |
Use research_synthesis when the user needs to gather
context from a directory of files or docs before planning.
Pass the directory (or file) as path; optionally set
depth to quick, standard, or deep:
research_synthesis(path="<dir or file>", depth="standard")
Scoping
Before running, ask:
- Type: "What kind of planning? Feature spec, TDD approach, or architecture review?"
- Subject: Depending on type:
- Feature: "What feature? What problem does it solve?"
- TDD: "What behavior should the tests verify?"
- Architecture: "What system? Any specific concerns?"
- Scope: "How deep? Quick outline or detailed plan?"
Surface. The Subject phrasing branches on Type, so don't
batch all three — ask Type first (a single AskUserQuestion) when
it isn't already given by the <what to plan> argument. Once the type
is known, Subject (a textarea) and Scope (quick / detailed) are
independent and open: gather those two as one form via the elicit
skill, preferring the rich widget surface (elicitation_render_widget
→ show_widget) with the AskUserQuestion mapping as fallback. If only
one dimension is open, ask it as a single question — never force a
one-field form (the §4 batching rule).
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.
- 7d ago First seen · 72 lines · 32 tokens per session scan A 209183fa1490
planning is a skill published in the GitHub repository Smart-AI-Memory/attune-ai (10 stars, last pushed yesterday), licensed Apache-2.0. It adds 32 tokens to every session and 609 once invoked, about $0.0002 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
taiyi-dev
A software-development stage that implements planned tasks using test-driven development, or TDD: write a failing test, make it pass, then improve the code. It checks the task plan, dependencies, file boundaries, and required completion evidence.
go
Go phase. Reads the approved SPEC file, maps Requirements to tasks (plan), executes via TDD (build), and integrates results verifying all Acceptance Criteria.
rpi-remediate
Validate and resolve every actionable pre-launch finding in ordered local waves with TDD, finding disposition and preservation of strategic exceptions.
tdd
Test-Driven Development enforcer. Red→Green→Refactor cycle with no production code without a failing test first. Use for new features and bug fixes.
lfe-tdd
Red-green-refactor quality pass on code the Builder just wrote. Use in the Builder sub-pipeline after lfe-builder completes implementation.
write-plan
Write a bite-sized TDD implementation plan from a spec before touching code. Saves under docs/plans/ / (gitignored WIP); promote to docs/features/ / when stable. Use when the user invokes write-plan, or when interview-plan hands off an assembled spec. Do not use to implement.