Agent skill

Arcgentic

by Arch1eSUN in Arch1eSUN/Arcgentic

A skill your agent uses when the user mentions Arcgentic, or wants substantial AI-written code taken through a gated plan → development → self-audit → external audit workflow with role handoffs and…

MITAuto-check passedAgent Workflows

Install Arcgentic

skills CLI
$ npx skills add Arch1eSUN/Arcgentic --skill arcgentic -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Arch1eSUN/Arcgentic arcgentic --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Arch1eSUN/Arcgentic.git skills-src && mkdir -p .claude/skills && cp -r skills-src/packaging/agensi/arcgentic .claude/skills/arcgentic && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
arcgentic
GitHub stars
286
Token cost
~984 tokens
SKILL.md length
472 words
Files
1
Skills in repo
19
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when the user mentions Arcgentic, or wants substantial AI-written code taken through a gated plan → development → self-audit → external audit workflow with role handoffs and…

  • Works in 3 steps: Check whether the Arcgentic plugin is… → If it is installed, hand off to the… → If it is not installed, explain what…
  • The user mentions Arcgentic
  • SKILL.md covers When to use it, What to do when this skill…, Install and Supported agents, plus 2 more sections
  • Calls npm, pipx and claude

What it does

Arcgentic is an agent skill from Arch1eSUN/Arcgentic. Use when the user mentions Arcgentic, or wants substantial AI-written code taken through a gated plan → development → self-audit → external audit workflow with role handoffs and evidence before it counts as done. Explains what Arcgentic is, when it fits, and how to install the full plugin for Codex or Claude Code.

Its SKILL.md is about 980 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows. The repository describes itself as: Mechanical plan/dev/self-audit/external-audit gates for AI coding agents, with a configurable role-routing topology engine, an MCP-UI live status panel, and native-tooling Claude… The licence is MIT.

When your agent uses it

  • The user mentions Arcgentic

Example prompts

  • “/arcgentic”

Requirements

  • Python 3
  • Node.js

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. Check whether the Arcgentic plugin is already installed in this agent. In
  2. If it is installed, hand off to the plugin's own entry skill and follow it.
  3. If it is not installed, explain what Arcgentic does, show the install steps

What it can do on your machine

Read from SKILL.md and the folder at commit 8539955. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • npm
    • pipx
    • claude

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • pypi.org
    • npmjs.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Arcgentic loads about 984 tokens when it runs. Until then it costs about 81 tokens; SKILL.md has 472 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~81
When it runs · the whole SKILL.md, loaded when a task matches
~984

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Arch1eSUN/Arcgentic at commit 8539955, republished under its MIT licence (© Arch1eSUN). 472 words, ~984 tokens.

Download SKILL.mdSave it as .claude/skills/arcgentic/SKILL.md (or your agent's skills folder).
name
arcgentic
description
Use when the user mentions Arcgentic, or wants substantial AI-written code taken through a gated plan → development → self-audit → external audit workflow with role handoffs and evidence before it counts as done. Explains what Arcgentic is, when it fits, and how to install the full plugin for Codex or Claude Code.
license
MIT

Arcgentic

Arcgentic is a harness-engineering layer for Codex and Claude Code. It wraps the coding agent in roles, handoffs, audits, stop states, and pass/fix gates, so a round of work only closes when there is evidence: a plan, a developer self-audit, optional user testing, and an independent external audit.

This skill is the entry point listed on Agensi. The workflow itself lives in the open-source Arcgentic plugin (MIT), which ships its own skills, agents, hooks, and a Python CLI. This skill does not contain that code. It tells you when Arcgentic fits and how to install the real thing.

When to use it

Good fit:

  • real engineering work run through Codex or Claude Code, across multiple rounds;
  • complex repos, refactors, and agent products;
  • work where you must show that AI-written code was planned, tested, and audited before it was accepted;
  • sessions where a future reader needs to understand what happened and why.

Not a good fit: one-line commands, tiny edits, quick experiments, or exploratory questions with no development goal. Arcgentic is intentionally heavier than normal prompting.

What to do when this skill triggers

  1. Check whether the Arcgentic plugin is already installed in this agent. In Claude Code, look for the arcgentic plugin and its skills such as using-arcgentic. In Codex, look for the arcgentic skill from the plugin.
  2. If it is installed, hand off to the plugin's own entry skill and follow it. Do not improvise the workflow from this summary.
  3. If it is not installed, explain what Arcgentic does, show the install steps below for the user's agent, and let the user run them. Do not install anything without the user's go-ahead.
Show full SKILL.md (188 more words)Show less

Install

Claude Code
text
/plugin marketplace add Arch1eSUN/Arcgentic
/plugin install arcgentic@arc-studio

Then, inside your project:

text
Use Arcgentic to build this idea: <your idea>
Codex
bash
npm install -g arcgentic
arcgentic install-codex-local

Then start in a saved project workspace and ask:

text
Use Arcgentic to build this idea: <your idea>
Command-line helper only
bash
pipx install arcgentic
arcgentic --help
Optional MCP status panel

Arcgentic also ships an optional MCP server that renders the current round's status, role dispatch progress, and audit verdict as an inline panel:

bash
claude mcp add --transport stdio arcgentic -- uvx --python 3.13 --from 'arcgentic[mcp]' arcgentic mcp-serve

Requires Python 3.13 or newer.

Supported agents

Arcgentic's full workflow is built for Codex and Claude Code. In other agents, this skill can still explain Arcgentic and the command-line helper works anywhere Python 3.13 is available, but the role dispatch and session orchestration are not supported there.

How a round works

  1. Planner turns the idea into a scoped handoff.
  2. Developer implements it and writes a self-audit.
  3. Test (optional) runs a realistic user test.
  4. Auditor reviews independently and returns PASS or a fix list.
  5. The round closes only on PASS with evidence; otherwise it loops back.

Arcgentic recommends a session mode before the first round: a faster single-session mode with named subagents, or a slower multi-session mode with fixed role threads and stronger audit isolation.

License

MIT. See LICENSE in this package and in the GitHub repository.

© Arch1eSUN, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in packaging/agensi/arcgentic of Arch1eSUN/Arcgentic.

Open the folder on GitHubat commit 8539955

Compare with similar skills

Arcgentic next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Arcgentic compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Arcgentic this skillArch1eSUN/Arcgentic286—~984Automated safety check: PassMIT
MCP Server Builderanthropics/skills180k63 repos~2.3kAutomated safety check: PassApache-2.0
Hook Development for Claude Code Pluginsanthropics/claude-plugins-official38k10 repos~4.1kAutomated safety check: NotesApache-2.0
Using Superpowersfarm-fe/farm5.6k35 repos~1.4kAutomated safety check: PassMIT
Executing Plans Inlineobra/superpowers297k2 repos~5.1kAutomated safety check: PassMIT
Skill CreatorAzure/azqr79589 repos~8.2kAutomated safety check: PassApache-2.0

Similar skills

  • MCP Server Builder

    anthropics/skills

    Official

    Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.

    180k GitHub starsUsed in 63 repos~2.3k tokens
    Agent WorkflowsAuto-check passed
  • Hook Development for Claude Code Plugins

    anthropics/claude-plugins-official

    Official

    Explains how to write Claude Code plugin hooks, both prompt-based checks and bash commands, for events such as PreToolUse, Stop and SessionStart.

    38k GitHub starsUsed in 10 repos~4.1k tokens
    Agent WorkflowsAuto-check: notes
  • Using Superpowers

    farm-fe/farm

    A skill your agent uses when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions

    5.6k GitHub starsUsed in 35 repos~1.4k tokens
    Agent WorkflowsAuto-check passed
  • Executing Plans Inline

    obra/superpowers

    Has the agent carry out an implementation plan itself, task by task in the current session, keeping a ledger, proving each step with a test and ending with one whole-branch review.

    297k GitHub starsUsed in 2 repos~5.1k tokens
    Agent WorkflowsAuto-check passed
  • Skill Creator

    Azure/azqr

    Official

    Create new skills, modify and improve existing skills, and measure skill performance.

    795 GitHub starsUsed in 89 repos~8.2k tokens
    Agent WorkflowsAuto-check passed
  • Claude Code Agent Development

    anthropics/claude-plugins-official

    Official

    Explains how to write agents for Claude Code plugins: the markdown file with YAML frontmatter, trigger descriptions, model and color settings, and system prompt design.

    38k GitHub starsUsed in 7 repos~2.8k tokens
    Agent WorkflowsAuto-check passed

More from Arch1eSUN/Arcgentic

All 19 skills in this repo
  • Audit Round

    Arch1eSUN/Arcgentic

    External-audit role for arcgentic rounds. An agent skill from Arch1eSUN/Arcgentic.

    286 GitHub stars~1.6k tokensUpdated 7 days ago
    Auto-check passed
  • Orchestrate Round

    Arch1eSUN/Arcgentic

    Main-session orchestrator for arcgentic rounds. An agent skill from Arch1eSUN/Arcgentic.

    286 GitHub stars~1.5k tokensUpdated 7 days ago
    Auto-check passed
  • Verify Gates

    Arch1eSUN/Arcgentic

    Runs the mechanical quality gates that the arcgentic state machine requires for state transitions.

    286 GitHub stars~653 tokensUpdated 7 days ago
    Auto-check passed
  • Arcgentic

    Arch1eSUN/Arcgentic

    A skill your agent uses when the user says Arcgentic, asks to use Arcgentic, or wants an idea taken through a complete plan → development → self-audit → external audit workflow in Codex.

    286 GitHub stars~2.4k tokensUpdated 7 days ago
    Auto-check passed
  • Claude Code Session Broker

    Arch1eSUN/Arcgentic

    A skill your agent uses when running Arcgentic V2 in Claude Code and fixed Planner, Developer, and Auditor role sessions must be coordinated through a broker.

    286 GitHub stars~3.4k tokensUpdated 7 days ago
    Auto-check passed
  • Codex Thread Orchestration

    Arch1eSUN/Arcgentic

    A skill your agent uses when running Arcgentic V2 in Codex and the current thread must orchestrate fixed Planner, Developer, Test, and Auditor role threads.

    286 GitHub stars~4.6k tokensUpdated 7 days ago
    Auto-check passed

Categories

Questions about Arcgentic

What does Arcgentic do?

A skill your agent uses when the user mentions Arcgentic, or wants substantial AI-written code taken through a gated plan → development → self-audit → external audit workflow with role handoffs and…. Arcgentic is an agent skill from Arch1eSUN/Arcgentic. Use when the user mentions Arcgentic, or wants substantial AI-written code taken through a gated plan → development → self-audit → external audit workflow with role handoffs and evidence before it counts as done.

When should I use Arcgentic?

Arcgentic fits situations like: the user mentions Arcgentic.

How do I install Arcgentic in Claude Code?

Run `npx skills add Arch1eSUN/Arcgentic --skill arcgentic -a claude-code`. Or copy the skill folder (packaging/agensi/arcgentic in Arch1eSUN/Arcgentic) into .claude/skills/arcgentic in your project. Claude Code loads it when a task matches its description.

How do I install Arcgentic in Codex?

Run `npx skills add Arch1eSUN/Arcgentic --skill arcgentic -a codex`. Or copy the skill folder (packaging/agensi/arcgentic in Arch1eSUN/Arcgentic) into .agents/skills/arcgentic in your project. Codex loads it when a task matches its description.

Can I use Arcgentic in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Arch1eSUN/Arcgentic --skill arcgentic -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/arcgentic, .gemini/skills/arcgentic, .github/skills/arcgentic and .opencode/skills/arcgentic in your project.

What does Arcgentic need to run?

Going by SKILL.md and its folder, Arcgentic needs the command-line tools its instructions call (npm, pipx and claude). Our summary lists: Python 3; Node.js.

Does Arcgentic access the network?

SKILL.md names 2 domains. As links in the text: pypi.org and npmjs.com. This is read from the text; nothing was executed.

Is Arcgentic safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Arcgentic use?

Arcgentic is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Arcgentic use?

About 984 tokens (SKILL.md is roughly 3.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Arcgentic?

Skills that share tags, products or a category with Arcgentic: MCP Server Builder (anthropics/skills, 180k stars), Hook Development for Claude Code Plugins (anthropics/claude-plugins-official, 38k stars), Using Superpowers (farm-fe/farm, 5.6k stars) and Executing Plans Inline (obra/superpowers, 297k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Arcgentic?

Arch1eSUN (a GitHub user) maintains it in Arch1eSUN/Arcgentic, which has 286 GitHub stars. The repository holds 19 skills in this directory. The repository was last updated on October 2, 2026.

Source: Arch1eSUN/Arcgentic on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.