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.
git 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/commands/smart-ai-memory/attune-ai/plan)<a href="https://agentmods.dev/commands/smart-ai-memory/attune-ai/plan"><img src="https://agentmods.dev/badge/commands/smart-ai-memory/attune-ai/plan/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/commands/smart-ai-memory/attune-ai/plan"><img src="https://agentmods.dev/badge/commands/smart-ai-memory/attune-ai/plan.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00012 | $0.01031 |
| Opus 5.5 | $0.00005 | $0.00412 |
| Sonnet 5.5 | $0.00002 | $0.00206 |
| Haiku 4.5 | $0.00001 | $0.00103 |
Grade A, and why
plan 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
plan
Planning hub — feature breakdowns, brainstorming, refactoring strategies, and architecture reviews.
This hub is advisory. It helps you think through plans before executing. Use it to break down complex work into safe, ordered steps.
Quick Shortcuts
| Shortcut | Action |
|---|---|
/plan feature <description> |
Break feature into implementation tasks |
/plan brainstorm |
Brainstorm ideas with structured discovery and export |
/plan refactor <path> |
Plan incremental refactoring steps |
/plan architecture |
Evaluate current architecture, propose improvements |
/plan review <path> |
Review code and plan improvements |
Natural Language
Describe what you need to plan:
- "plan adding user authentication"
- "break down this feature into steps"
- "help me think through this problem"
- "how should I refactor the config module?"
- "review the architecture of the agent system"
CRITICAL: Workflow Execution Instructions
When this command is invoked with arguments, you MUST execute the planning workflow, not answer ad-hoc.
Context Gathering (ALWAYS DO FIRST)
Before executing any action below, gather current project context:
- Run:
git status --short - Run:
git log --oneline -5 - Run:
git branch --show-current
Use this context to inform your planning (e.g., current branch, recent changes, uncommitted work).
Reasoning Approach
For planning tasks, use structured reasoning to produce thorough plans:
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 · 123 lines · 12 tokens per session scan A f3da972294ab
plan is a command published in the GitHub repository Smart-AI-Memory/attune-ai (10 stars, last pushed 5d ago), licensed Apache-2.0. It adds 12 tokens to every session and 1,031 once invoked, about $0.0000 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 2026-09-03.
Other commands, from other repositories
pm-competitive
Competitive teardown — for a given competitor or for the whole landscape around a JTBD. Spawns market-analyst. Outputs structured brief with positioning gaps.
pm-ownership
Show who owns what across initiatives, gates, drafts, and Beads issues. Surfaces orphaned artefacts (no owner) and over-loaded owners.
pm-pricing
Author or refresh a pricing plan — 2–3 monetization models with willingness-to-pay rationale per audience. Spawns pricing-strategist.
pm-save
Extract lessons from this session and save them to .great-pm/lessons.md. Optional cross-project promotion to /.great-pm/decisions.md for patterns seen 3+ times (proposed, never auto-promoted).
pm-burn
Cost burn-rate — LLM cost over the last N days vs a human-equivalent baseline (savingsx). Flags cost outliers and abnormal-burn agents.
agentos-status
Show AgentOS system status — agents, workers, health.