auto-execute

An execution workflow for carrying out approved slices of a software plan while keeping the implementation within the plan's agreed scope.

In plain words
What is it for?
Use it after planning is approved, to implement one slice at a time, run its verification commands, and stop or continue based on checkpoints and results.
Why use it?
It preserves the intended product scope and verifies each completed slice before continuing. It can choose between direct implementation and delegated work when the plan allows it.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/appautomaton/automaton/auto-execute
Any agent
npx skills add appautomaton/automaton --skill auto-execute
Clone the repo
git clone --depth 1 https://github.com/appautomaton/automaton

Made for: Claude Code, Codex.

Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,763 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00017 $0.02763
Opus 5 $0.00009 $0.01381
Sonnet 5 $0.00003 $0.00553
Haiku 4.5 $0.00002 $0.00276

Measured 3d ago against content hash 6687b3e64c43, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 3d 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.

skills/auto-execute/SKILL.md · 162 lines

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.md only when bounded diagnosis needs more structure.
  • Record verification evidence before advancing or selecting the next slice.
  • Read references/quality.md when the diff looks clever, defensive, or broader than the plan requires.

Do

Do NOT write code unless:

  • PLAN.md is approved and canonical_plan in .agent/.automaton/state/current.json is set.
  • canonical_spec still 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_review is not needs_correction (otherwise stop and return to auto-plan).
  • The route is direct, or the subagent route has passed its host capability check.

Read the full file on GitHub · 162 lines

Changes

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.

  1. 3d ago First seen · 162 lines · 17 tokens per session scan A 6687b3e64c43

Subscribe to this mod's changes

auto-execute is a skill published in the GitHub repository appautomaton/automaton (21 stars, last pushed 16d ago), licensed MIT. It adds 17 tokens to every session and 2,763 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.

Related

Other skills, from other repositories

ask

Process-first advisor routing for Claude, Codex, Gemini, Antigravity, Grok, or Cursor via omc ask, with artifact capture and no raw CLI assembly.

Yeachan-Heo/oh-my-claudecode · 37 tokens

external-context

Invoke parallel document-specialist agents for external web searches and documentation lookup.

Yeachan-Heo/oh-my-claudecode · 16 tokens

reflect

Review recent work, find repeated workflow patterns, and suggest reusable skills, agents, commands, config changes, or playbooks. Use when the user asks to learn from past sessions, improve recurring workflows, or identify what should be turned into reusable agent instructions.

alvinunreal/oh-my-opencode-slim · 53 tokens

codemap

Generate comprehensive hierarchical codemaps for UNFAMILIAR repositories. Expensive operation - only use when explicitly asked for codebase documentation or initial repository mapping.

alvinunreal/oh-my-opencode-slim · 34 tokens

scientific-schematics

Create publication-quality scientific diagrams using Nano Banana 2 AI with smart iterative refinement. Uses Gemini 3.1 Pro Preview for quality review. Only regenerates if quality is below threshold for your document type. Specialized in neural network architectures, system diagrams, flowcharts, biological pathways…

xintaofei/codeg · 68 tokens

openpets

Use when the user asks to install, configure, verify, troubleshoot, or understand OpenPets; install or select a pet; connect Claude Code, OpenCode, Cursor, Codex, or MCP clients; configure a project to use a specific pet; or debug openpetsstatus, openpetsreact, or openpetssay.

alvinunreal/openpets · 70 tokens