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-framenpx skills add appautomaton/automaton --skill auto-framegit 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-frame)<a href="https://agentmods.dev/skills/appautomaton/automaton/auto-frame"><img src="https://agentmods.dev/badge/skills/appautomaton/automaton/auto-frame.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 | $0.00033 | $0.02129 |
| Opus 5 | $0.00016 | $0.01064 |
| Sonnet 5 | $0.00007 | $0.00426 |
| Haiku 4.5 | $0.00003 | $0.00213 |
Grade A, and why
auto-frame 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 4d 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
auto-frame
Framing controller. Turns a request into one bounded SPEC.md, running as much conversation as the request needs and no more.
First action: run node .agent/.automaton/scripts/get-context.mjs from the project root.
Preamble
auto-frame produces the canonical artifact: SPEC.md. No file means no completed frame. It does not write code, create PLAN.md, or proceed to planning.
Depth is chosen after reading, never before: the call needs the repo and the request in hand, so it cannot be made at the door.
Loading discipline: hold the objective, constraints, risks, and source evidence that keep the spec real. Avoid exhaustive tree walks. When a lookup would pull wide reads into context, dispatch the read-only automaton-librarian (see .agent/.automaton/references/LIBRARIAN.md): it returns evidence, you keep the decision. Never ask what the repo can answer.
Artifact discipline: SPEC.md is the reloadable contract, not the whole dossier. Layout and linking rules live in .agent/.automaton/references/ARTIFACT-LIFECYCLE.md (Progressive Disclosure).
Interaction: keep chat plain, in the user's words. Do not expose the internal labels below. Follow .agent/.automaton/references/FRAMEWORK.md (Asking The User).
Quality Gate
- Make the objective observable.
- Preserve the user's broader intent. Do not silently narrow scope.
- Move implementation detail out unless it constrains scope.
- Mark uncertain claims as assumptions.
- Read
references/quality.mdbefore presenting alternatives or finalizingSPEC.md.
Do
Read The Request
Read the request, the conversation, and enough repo evidence to know what is already true. If a SPEC.md exists for this change, read it and preserve every ## Review: section.
Classify three axes and hold them internally:
- Mode: Startup mode for customers, revenue, or market. Builder mode for side projects, learning, or open source. Content mode for writing, article, brief, deck, newsletter, documentation, or any prose where audience and voice matter.
- Work scale: bug, feature, capability, or roadmap. Large is not roadmap. Capability-sized work stays one spec when it serves one coherent outcome. Roadmap-sized means multiple independently valuable outcomes that need decomposition.
- Work shape: feature, refactor, parity, audit, migration, coverage, content, or mixed.
What ships with it
8 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.
- 4d ago First seen · 138 lines · 33 tokens per session scan A 1c5309b11101
auto-frame is a skill published in the GitHub repository appautomaton/automaton (21 stars, last pushed 17d ago), licensed MIT. It adds 33 tokens to every session and 2,129 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 2026-08-30.
Other skills, from other repositories
ahk-review
Preview a code review against ticket/objective alignment, with deep semantic (name-vs-behavior) analysis. 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-triage
Triage a bug or unexpected behavior. Deep diagnostic analysis with structured report. 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.
wiki-ingest
Ingest a source into the project wiki as OKF v0.2 markdown. Point at a file, PR, or doc and the wiki-curator extracts knowledge, writes YAML frontmatter, and updates relevant concept pages.