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 skills add appautomaton/automaton --skill auto-executegit 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-execute)<a href="https://agentmods.dev/skills/appautomaton/automaton/auto-execute"><img src="https://agentmods.dev/badge/skills/appautomaton/automaton/auto-execute/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/skills/appautomaton/automaton/auto-execute"><img src="https://agentmods.dev/badge/skills/appautomaton/automaton/auto-execute.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 2 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 8 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 16 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 132 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00017 | $0.02763 |
| Opus 5.5 | $0.00007 | $0.01105 |
| Sonnet 5.5 | $0.00003 | $0.00553 |
| Haiku 4.5 | $0.00002 | $0.00276 |
Grade A, and why
auto-execute 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
auto-execute
Implementation controller. Executes approved plan slices without reopening product scope.
First action: run node .agent/.automaton/scripts/get-context.mjs from the project root.
Preamble
auto-execute owns execute-stage orchestration, route selection, state, and scope. Direct implementation and subagent implementation are two routes inside this skill. It does not reopen product scope or modify the approved plan's intent. Execute and verify one approved slice at a time inside the selected execution window. Plan-declared parallel-safe groups are the one exception to that serial order. Continuation is the default after a verified slice; checkpoints and STOP conditions are the exceptions. An execution window is a context-management batch, not a completion boundary.
Loading discipline: keep the active slice, execution-window metadata, acceptance criteria, route metadata, verification commands, and active files in context. Load linked detail files and traceability IDs for the active slice only; read wider project files only when implementation correctness requires it. 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.
Quality Gate
Before marking a slice complete:
- Keep edits inside the active slice.
- Investigate root cause before fixing bugs. Read
references/debug-protocol.mdonly when bounded diagnosis needs more structure. - Record verification evidence before advancing or selecting the next slice.
- Read
references/quality.mdwhen the diff looks clever, defensive, or broader than the plan requires.
Do
Do NOT write code unless:
PLAN.mdis approved andcanonical_planin.agent/.automaton/state/current.jsonis set.canonical_specstill resolves: the spec chain holds end to end so cold resume can always load spec first.- The next executable slice has an objective, acceptance criteria, and verification command.
engineering_reviewis notneeds_correction(otherwise stop and return toauto-plan).- The route is direct, or the subagent route has passed its host capability check.
What ships with it
12 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.
- references/content-execution.md 2.2 KB
- references/debug-protocol.md 509 B
- references/git-rhythm.md 2.6 KB
- references/implementer-prompt.md 849 B
- references/quality-reviewer-prompt.md 443 B
- references/quality.md 856 B
- references/spec-reviewer-prompt.md 518 B
- references/stop-examples.md 691 B
- role-sources/implementer-role.md 3.0 KB
- role-sources/librarian-role.md 2.0 KB
- role-sources/quality-reviewer-role.md 2.4 KB
- role-sources/spec-reviewer-role.md 1.8 KB
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 · 162 lines · 17 tokens per session scan A 6687b3e64c43
auto-execute is a skill published in the GitHub repository appautomaton/automaton (24 stars, last pushed 1mo ago), licensed MIT. It adds 17 tokens to every session and 2,763 once invoked, about $0.0001 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 2026-08-30.
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-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.
ahk-docs
Explain how to use and operate Agent Harness Kit= workflows, providers, MCP, health gates, and upgrades. Read-only; does not create harness state or change a project.