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 commands/niels-emmer/myace/plangit clone --depth 1 https://github.com/niels-emmer/myaceWrote 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/niels-emmer/myace/plan)<a href="https://agentmods.dev/commands/niels-emmer/myace/plan"><img src="https://agentmods.dev/badge/commands/niels-emmer/myace/plan.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 | $0.00031 | $0.00455 |
| Opus 5 | $0.00015 | $0.00228 |
| Sonnet 5 | $0.00006 | $0.00091 |
| Haiku 4.5 | $0.00003 | $0.00046 |
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 yesterday.
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.
What it actually says
- Restate the task in one or two sentences, in your own words — confirms you've understood what's actually being asked before designing around a misreading of it.
- Read the project's memory files (
docs/memory/core-principles.md,docs/memory/workflow.md, and the tail ofdocs/memory/decisions.mdfor anything relevant) so the plan fits existing conventions and doesn't repeat a decision already made and logged. - Decide whether this task needs a design pass — a new module or service boundary, a change to identity or networking, a state migration, or a genuinely ambiguous approach all qualify. If it does, write the short design note the
architecture-reviewskill describes before continuing. - Break the task into an ordered list of concrete, checkable steps — not vague phases. Each step should be small enough to verify on its own (e.g., "add the Terraform module," "update the security group," "add the pipeline stage," not "implement the feature").
- Identify what could go wrong or turn out to be bigger than expected — a step that touches production infrastructure, a state migration without an obvious rollback, a security-relevant boundary — and flag those specifically rather than letting them look like routine steps.
- Set up tracking for the plan per the
plan-trackingskill so progress stays visible as steps complete. - Share the plan before starting implementation if the task is large, ambiguous, or touches something risky enough that the user would want a chance to redirect before code gets written; otherwise proceed straight into the
builderagent's work with the plan as the checklist. - Before any
apply/deploy/destroy, show the plan/diff and get explicit human approval — never run a state-changing command and explain afterward.
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.
- yesterday First seen · 14 lines · 31 tokens per session scan A 23549eaae113
plan is a command published in the GitHub repository niels-emmer/myace (1 stars, last pushed 4d ago), licensed MIT. It adds 31 tokens to every session and 455 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 2026-09-03.
Other commands, from other repositories
brainstorm
已弃用 - 请改用 superpowers:brainstorming 技能.
execute-plan
已弃用 - 请改用 superpowers:executing-plans 技能.
handoff
Force a session catchup or a memory promotion outside the hook lifecycle. Default is catchup (read-only); promote is HITL gated.
fix
Apply a single safe quick win from DESIGN.md.critique.md. HITL gated. Re-lints DESIGN.md after every edit; reverts if lint regresses.
memory
Save or recall via the three-tier memory layer. Routes to scratch (file-tier), WHERE (QMD via code-memory-router), or WHY (MemPalace via code-memory-router). Every WHY-tier write goes through the HITL gate.
compose
One-shot wiring check for MDDesign. Verifies planning-with-files, DESIGN.md, code-memory-router, and Google linter are all reachable. Surfaces any missing piece with a one-line fix-it. Read-only.