Agent skill

Arcgentic

by Arch1eSUN in 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.

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/skills/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
~2.4k tokens
SKILL.md length
1,101 words
Files
1
Skills in repo
19
Repo updated
First seen
Licence
MIT

At a glance

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.

  • Works in 12 steps: Treat the current thread as Orchestrator… → Determine whether the current thread has… → If this is the first Arcgentic V2 run in… → …
  • The user says Arcgentic
  • SKILL.md covers Immediate behavior in Codex, Bootstrap if state is missing, Fail-closed rules and Continue
  • Calls bash and python

What it does

Arcgentic is an agent skill from Arch1eSUN/Arcgentic. Use 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.

Its SKILL.md is about 2.4k 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 says Arcgentic
  • Asks to use Arcgentic
  • Wants an idea taken through a complete plan → development → self-audit → external audit workflow in Codex

Example prompts

  • “/arcgentic”

Requirements

  • Python 3

Workflow steps

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

  1. Treat the current thread as Orchestrator and rename the current Codex
  2. Determine whether the current thread has a real project/workspace root.
  3. If this is the first Arcgentic V2 run in the project and no mode is already
  4. The two V2 modes are
  5. Use the chosen mode for the whole project. Do not ask again per round unless
  6. In multi-session-subthread, use the current project/workspace as the only
  7. Do not create projectless Planner / Developer / Test / Auditor threads.
  8. Use the strongest available Codex model for real Planner / Developer /
  9. Record the current thread as fixed role Orchestrator in
  10. Before reading implementation files, running tests, checking git log, or
  11. Initialize .agentic-rounds/state.yaml if it does not exist.
  12. Run v2-session-plan with the user-selected mode on first use, or without

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:

    • bash
    • python

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

  • Network

    No URLs in SKILL.md.

    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 2.4k tokens when it runs. Until then it costs about 44 tokens; SKILL.md has 1,101 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~44
When it runs · the whole SKILL.md, loaded when a task matches
~2.4k

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). 1,101 words, ~2,350 tokens.

Download SKILL.mdSave it as .claude/skills/arcgentic/SKILL.md (or your agent's skills folder).
name
arcgentic
description
Use 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.

Arcgentic

This is the Codex-facing entry skill for Arcgentic V2.

Use this before build-feature, executing-plans, or direct coding whenever the user asks to use Arcgentic.

Do not directly implement, test, or scaffold the requested feature from the Orchestrator, even in a greenfield or empty project. Arcgentic work starts by dispatching Planner.

Immediate behavior in Codex

  1. Treat the current thread as Orchestrator and rename the current Codex thread to exactly Orchestrator before dispatching any role.
  2. Determine whether the current thread has a real project/workspace root.
    • If yes, continue with project-scoped orchestration.
    • If no, stop and ask the user to open or create a saved project workspace.
  3. If this is the first Arcgentic V2 run in the project and no mode is already stored, judge the user's idea before dispatching Planner:
    • Run:

      bash
      arcgentic session-mode recommend-v2 --idea '<current user request>'
    • Present the recommended mode, confidence, reasons, and tradeoff in natural language.

    • Ask the user to confirm the recommendation or override it.

    • Do not dispatch Planner until the user has chosen one project-level mode.

  4. The two V2 modes are:
    • single-session-subagent: faster and usually finishes sooner. Planner, Developer, Test, and Auditor run as named subagents inside the current Orchestrator session, so audit isolation is weaker. The first use of a role creates that fixed named role identity; later rounds reuse it.
    • multi-session-subthread: slower. Planner, Developer, Test, and Auditor run in fixed project threads, so role separation and external-audit evidence are stronger.
  5. Use the chosen mode for the whole project. Do not ask again per round unless the user explicitly starts a new project or requests a reset.
  6. In multi-session-subthread, use the current project/workspace as the only valid target for role threads after initialization.
  7. Do not create projectless Planner / Developer / Test / Auditor threads.
  8. Use the strongest available Codex model for real Planner / Developer / Test / Auditor work. Do not default role threads to a lightweight or spark model unless the user explicitly asks for a low-cost smoke test.
  9. Record the current thread as fixed role Orchestrator in .agentic-rounds/state.yaml before dispatching Planner. If the host cannot provide the current Orchestrator thread id, stop because push-return cannot work. In Codex delegation-created threads, do not treat the delegation source_thread_id as the current Orchestrator id. It identifies the upstream supervising thread, not the project-scoped Orchestrator.
  10. Before reading implementation files, running tests, checking git log, or summarizing prior work, initialize/check .agentic-rounds/state.yaml and run v2-session-plan.
  11. Initialize .agentic-rounds/state.yaml if it does not exist. If state exists and current_round.state is closed, treat the new user request as input for Planner only when it asks for new work. Status, inspection, review, or "is this complete?" requests are terminal idle and must not rewrite active_user_request or dispatch Planner.
  12. Run v2-session-plan with the user-selected mode on first use, or without --mode after the mode is already stored:
bash
arcgentic v2-session-plan \
  --state .agentic-rounds/state.yaml \
  --host codex \
  --user-request '<current user request>' \
  --mode <single-session-subagent|multi-session-subthread>
  1. If the plan is active and contains an action, dispatch that one role before any verification or implementation inspection, then call arcgentic v2-dispatch-role and end the Orchestrator turn in multi-session-subthread, or create/reuse the named role agent directly in single-session-subagent. If state is closed and the plan has no actions, stop: the round is terminal at the project level, all role threads are idle, and Orchestrator should wait for a new user request.
  2. Load codex-thread-orchestration and follow it.

Bootstrap if state is missing

Find the plugin root:

bash
PLUGIN_ROOT="${ARCGENTIC_PLUGIN_ROOT:-$HOME/plugins/arcgentic}"

Then initialize state:

bash
bash "$PLUGIN_ROOT/scripts/state/init.sh" \
  --project-root . \
  --project-name "$(basename "$PWD")" \
  --round-naming "R<n>"

After init, update the state for V2 Codex mode:

bash
python - <<'PY'
from pathlib import Path
import yaml

path = Path(".agentic-rounds/state.yaml")
state = yaml.safe_load(path.read_text(encoding="utf-8"))
state.setdefault("project", {})["arcgentic_v2"] = {
    "host": "codex",
    "role_sessions": {},
}
path.write_text(yaml.safe_dump(state, sort_keys=False), encoding="utf-8")
PY
Show full SKILL.md (543 more words)Show less

Fail-closed rules

  • If arcgentic CLI is not available, report installation failure instead of pretending Arcgentic is active.

  • If the current thread is projectless or cannot create project-scoped role threads, stop.

  • If .agentic-rounds/state.yaml records delegation source_thread_id as the Orchestrator session by mistake, do not create Planner. Repair only that field with:

    bash
    arcgentic v2-record-session \
      --state .agentic-rounds/state.yaml \
      --host codex \
      --role orchestrator \
      --thread-id <current-orchestrator-thread-id> \
      --title Orchestrator \
      --repair-current-orchestrator
  • If .agentic-rounds/state.yaml cannot be created or validated, stop.

  • If role threads cannot be created in the current project/workspace, stop.

  • If a role thread is slow, send at most one status/constraint-tightening message. If it still does not return a valid RoleReturnSignal, stop with a role-timeout status. Do not continue the workflow in the Orchestrator.

  • After dispatching a role prompt, call arcgentic v2-dispatch-role and end the Orchestrator turn. The Orchestrator resumes only when the pending role actively sends return information back to the Orchestrator thread.

  • If arcgentic v2-return-signal rejects the role output, stop and report the rejected signal. Do not repair it by hand in the Orchestrator.

  • Do not silently fall back to "Arcgentic-style" hand-written evidence.

  • Do not treat "greenfield" or "empty repo" as permission for Orchestrator implementation.

  • Do not verify, summarize, or inspect a previous closed round as the response to a new implementation request. Route the request to Planner first.

  • Do not auto-dispatch Planner from project-level closed unless there is a new user request. Closed without a new request means the project workflow is stopped. Round-level PASS is not closed; it must advance through the stored project plan.

  • Do not run ordinary coding work before Planner has produced or approved the round plan.

  • Planner, Developer, Test, and Auditor must not mutate .agentic-rounds/state.yaml, run transition commands, dispatch roles, consume RoleReturnSignal, or close rounds. They write their role-owned artifacts and return natural-language output plus one arcgentic-role-return footer for the Orchestrator to consume.

  • Role threads must not stop after acknowledging their role. They must complete role-owned work in the same turn, using tools as needed, before returning RoleReturnSignal. Developer, Test, and Auditor consume prior-role artifacts from project.arcgentic_v2.last_signal.artifacts.

  • Role threads must actively wake the Orchestrator by sending their completed natural-language output and machine footer to the recorded Orchestrator thread. The Orchestrator must not poll role threads to discover completion.

  • Planner must do discovery before handoff: search GitHub or equivalent public references for reliable comparable projects, scan local skills/plugins/MCP servers/connectors/tools, then write the selected references and tools into a detailed Markdown handoff. Each downstream role must read the handoff artifact named in the Orchestrator prompt before acting.

  • Planner project-close returns must write a closeout artifact, create a local closeout commit, include artifacts.closeout and artifacts.commit, and use next_recommended_role: null. Closed projects are terminal idle unless the user provides a genuinely new work request.

  • Auditor PASS fact rows must use lifecycle-stable evidence: committed artifacts, fixed git hashes, artifact file contents, state history, and test/build output. Do not use mutable live routing fields such as current_round.state, project.arcgentic_v2.last_signal.role, or project.arcgentic_v2.last_signal.state as PASS facts unless the command reads an immutable committed snapshot.

  • Do not create source files, tests, handoff docs, self-audits, user-test reports, or external audit verdicts from the Orchestrator. Those belong to Planner, Developer, Test, and Auditor role threads.

Continue

Load and follow:

  • codex-thread-orchestration for Codex V2 fixed-role threads.
  • using-arcgentic for the general round-state vocabulary and state-machine rules.

© 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 skills/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—~2.4kAutomated 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 mentions Arcgentic, or wants substantial AI-written code taken through a gated plan → development → self-audit → external audit workflow with role handoffs and…

    286 GitHub stars~984 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 says Arcgentic, asks to use Arcgentic, or wants an idea taken through a complete plan → development → self-audit → external audit workflow in Codex. Arcgentic is an agent skill from Arch1eSUN/Arcgentic. Use 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.

When should I use Arcgentic?

Arcgentic fits situations like: the user says Arcgentic; asks to use Arcgentic; wants an idea taken through a complete plan → development → self-audit → external audit workflow in Codex.

How do I install Arcgentic in Claude Code?

Run `npx skills add Arch1eSUN/Arcgentic --skill arcgentic -a claude-code`. Or copy the skill folder (skills/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 (skills/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 (bash and python). Our summary lists: Python 3.

Does Arcgentic access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. 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 (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Arcgentic use?

About 2.4k tokens (SKILL.md is roughly 9.4k 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.