An opt-in automation loop for the rexyMCP architect/executor workflow. It repeatedly plans a phase, sends it for implementation, reviews the result, and responds to failures until a defined stopping point.

Use it to run a milestone hands-off, with automatic phase drafting, dispatch, review, escalation, and a final progress report.

It lets a project move through multiple work phases without requiring a person to pause between every phase, while retaining reviews and stop conditions.

auto — Skill for Claude Code by ryanczak/rexyMCP

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.

Any agent

npx skills add ryanczak/rexyMCP --skill auto

Clone the repo

git clone --depth 1 https://github.com/ryanczak/rexyMCP

Made for: Claude Code.

Or install rexymcp, the plugin that ships this one along with the rest of its 5 skills, 1 MCP server.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/ryanczak/rexymcp/auto/github.svg)](https://agentmods.dev/skills/ryanczak/rexymcp/auto)

Your own site

<a href="https://agentmods.dev/skills/ryanczak/rexymcp/auto"><img src="https://agentmods.dev/badge/skills/ryanczak/rexymcp/auto/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/ryanczak/rexymcp/auto"><img src="https://agentmods.dev/badge/skills/ryanczak/rexymcp/auto.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,764 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 1 finding, 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 8
Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.

Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00059	$0.03764
Opus 5.5	$0.00024	$0.01506
Sonnet 5.5	$0.00012	$0.00753
Haiku 4.5	$0.00006	$0.00376

Measured 2mo ago against content hash 652d77530ca9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

auto 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 2mo 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.

plugin/skills/auto/SKILL.md · 274 lines

How it starts

The opening of the file, as written. The whole thing — 274 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Auto Skill — the opt-in autonomous loop

This skill drives the architect/executor cycle hands-off across a whole milestone: it drafts the next phase, dispatches it, reviews the result, and escalates or re-dispatches on failure — cycling until the milestone closes or a stop condition fires. It exists so a user who wants a hands-off run gets one, without giving up any review rigor.

The one invariant: compose, never fork

This skill composes the existing four skills. It does not reimplement them.

Loop step	The skill it invokes
draft the next phase	`architect` (§3 phase-doc authoring)
dispatch a phase	`dispatch`
review a completed phase	`review`
decide an escalation lever	`escalate`

The loop adds only sequencing, the per-phase assist budget, journaling, the five stop conditions, and the loop report. It does not restate the Definition of Done, the bug-report template, the escalation levers, or the status-flip mechanics — each composed skill owns those, and running that skill's procedure verbatim is what keeps an autonomous run identical to an interactive one.

A behavior difference between an interactive run of a step and its autonomous run is a bug, not a feature. If you ever find yourself writing "in auto mode we do X differently," stop — that is the anti-pattern this skill exists to avoid.

Read these first

Before any action:

Read <repo>/docs/dev/NEXT.md (the active-phase pointer) and <repo>/docs/dev/WORKFLOW.md § "Opt-in autonomous loop (off by default)" and § "What Executors Never Decide" (the human-territory list this loop stops on).
Read all four composed skills — architect, dispatch, review, escalate — so you invoke their procedures unchanged.
Read <repo>/rexymcp.toml: confirm [executor] + [commands] are present (bootstrap done), and read [escalation] max_assists (the per-phase assist budget, default 3) and [architect] dispatch_model / review_model (the role models for delegation; unset = inherit the session model).

Read the full file on GitHub · 274 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.

2mo ago First seen · 274 lines · 59 tokens per session scan A 652d77530ca9

Subscribe to this mod's changes

auto is a skill published in the GitHub repository ryanczak/rexyMCP (85 stars, last pushed 12d ago), licensed MIT. It adds 59 tokens to every session and 3,764 once invoked, about $0.0002 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.

Building agents Planning

auto next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
autoryanczak/rexyMCP	Skill	85	12d ago	MIT	A	59	Claude Code
imagegenopenai/codex	Skill	134k	today	Apache-2.0	A	113	Codex
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	yesterday	MIT	A	200	Claude Code, Codex
playwright-climicrosoft/playwright	Skill	100k	yesterday	Apache-2.0	A	19	Claude Code
browser-automationopenclaw/openclaw	Skill	394k	today	MIT	A	36	Claude Code
systematic-debuggingobra/superpowers	Skill	314k	4d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code