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.
git clone --depth 1 https://github.com/phj128/autoworkerWrote 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/plugins/phj128/autoworker/autoworker)<a href="https://agentmods.dev/plugins/phj128/autoworker/autoworker"><img src="https://agentmods.dev/badge/plugins/phj128/autoworker/autoworker/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/plugins/phj128/autoworker/autoworker"><img src="https://agentmods.dev/badge/plugins/phj128/autoworker/autoworker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
autoworker 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.
What it actually says
{
"name": "autoworker",
"description": "Auto-loop execution workflow with quality gates for Claude Code. Automatically decomposes tasks, implements code, runs tests, and iterates through quality gates until completion.",
"author": { "name": "phj128" },
"version": "1.0.0",
"repository": "https://github.com/phj128/autoworker",
"license": "MIT"
}
What it installs
The manifest is a name and a version. 10 skills, 1 command travel with it, and installing the plugin installs all of them — 558 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill autoworker A 53 tokens
- Skill deep-plan A 50 tokens
- Skill sync-docs A 40 tokens
- Skill gate-check A 55 tokens
- Skill subtask-init A 49 tokens
- Skill subtask-plan A 44 tokens
- Skill subtask-update A 77 tokens
- Skill checkpoint A 50 tokens
- Skill code A 43 tokens
- Skill dispatch A 77 tokens
- Command autoworker A 20 tokens
What ships with it
1 file beside plugin.json 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.
- 1mo ago First seen · 9 lines scan A c83340a343fa
autoworker is a plugin published in the GitHub repository phj128/autoworker (18 stars, last pushed 6mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
review
PR review, interactive git diff annotation review, and writing style guide.
workinggenius
A development workflow that walks every piece of work through the six Working Geniuses — Wonder, Invention, Discernment, Galvanizing, Enablement, Tenacity — every stage a command the user types, every checkpoint a live exchange.
task
Chat-first task workflow: grill the plan one question at a time, then capture the discussion as the artifact you pick — to-task / to-roadmap / to-spec, never a flag — into a Markdown artifact under .task/. No execution skill — any session told to implement the artifact follows its stamped Execution block to a commit…
brana
AI development system — skills, agents, and hooks for systematic software engineering with Claude Code.
mojiemoji-github
A GitHub Markdown plugin that adds Mojiemoji image stamps using a shared skill, helper agent, and parameter checks.
devpace
AI-native BizDevOps rhythm manager for Claude Code — multi-role collaboration, change impact analysis, quality gates, goal-to-code traceability, and cross-session continuity.