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/appautomaton/automaton/auto-plannpx skills add appautomaton/automaton --skill auto-plangit clone --depth 1 https://github.com/appautomaton/automatonWrote 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/appautomaton/automaton/auto-plan)<a href="https://agentmods.dev/skills/appautomaton/automaton/auto-plan"><img src="https://agentmods.dev/badge/skills/appautomaton/automaton/auto-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 | $0.00020 | $0.01923 |
| Opus 5 | $0.00010 | $0.00962 |
| Sonnet 5 | $0.00004 | $0.00385 |
| Haiku 4.5 | $0.00002 | $0.00192 |
Grade A, and why
auto-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 5d 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
auto-plan
Planning controller. Turns approved framing into ordered slices with verification commands.
First action: run node .agent/.automaton/scripts/get-context.mjs from the project root.
Preamble
auto-plan builds the smallest plan that makes execution safe while preserving the approved scope. It does not write code or broaden scope beyond the approved spec.
Loading discipline: hold SPEC.md, review state, and source files needed for accurate slices. Read wider project files when understanding existing code informs slice boundaries or verification commands. Read .agent/.automaton/references/CONTEXT-BUDGET.md when wider reads threaten context pressure. When a lookup would otherwise pull wide reads into context, dispatch the read-only automaton-librarian (see .agent/.automaton/references/LIBRARIAN.md): it returns evidence, you keep the decision.
Artifact discipline: PLAN.md is the reloadable execution index, not the whole implementation dossier. Keep PLAN.md compact enough to re-read. For large coherent work, summarize slices in PLAN.md and link optional detail files under .agent/work/<change>/slices/. Split only for independent outcomes, not because one coherent plan has many requirements.
Quality Gate
Before finalizing PLAN.md:
- Give every material slice a concrete output.
- Attach a verification command to every material slice.
- Name the execution topology: default continuation path, explicit checkpoints, subagent routes, and any parallel-safe groups.
- Remove vague tasks that do not define done.
- Read
references/quality.mdwhen the plan leaves execution decisions to the implementer.
Do
Context Loading
Load the canonical SPEC.md, linked spec detail that carries normative requirements, relevant DESIGN.md, and source files needed to choose slice boundaries, dependencies, and verification commands. Do not ignore linked spec/*.md files when they contain requirement IDs, gap IDs, invariants, audit questions, migration checkpoints, coverage targets, or acceptance detail.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 139 lines · 20 tokens per session scan A e45eddc7ddd2
auto-plan is a skill published in the GitHub repository appautomaton/automaton (21 stars, last pushed 18d ago), licensed MIT. It adds 20 tokens to every session and 1,923 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 2026-08-30.
Other skills, from other repositories
ahk-test
Design, write, and run behavior-focused tests for an objective or existing code. Writes test files only and reports evidence. No tasks created, no harness tracking.
ahk-review
Preview a code review against ticket/objective alignment, with deep semantic (name-vs-behavior) analysis. No tasks created, no harness tracking.
ahk-triage
Triage a bug or unexpected behavior. Deep diagnostic analysis with structured report. No tasks created, no harness tracking.
ahk-consultant
Get technical advice or review on an approach, idea, or change. References available skills for best practices. No tasks created, no harness tracking.
ahk-ask
Ask a question about this codebase — where is X, does Y exist, how does Z work. Read-only. No tasks created, no harness tracking.
assumptions
Generate an evidence-backed Assumptions ledger for a Git diff, feature, endpoint, worker, migration, or code path. Use when reviewing a change, asking what could break, preparing a release, finding edge cases, assessing deployment safety, analyzing retries or concurrency, or designing failure-focused tests.