Install the "audit-round" agent skill from https://github.com/Arch1eSUN/Arcgentic/tree/main/skills/audit-round into .claude/skills/audit-round/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "audit-round", then confirm the skill loads.
Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
skills CLI
$ npx skills add Arch1eSUN/Arcgentic --skill audit-round -a codex
Project install goes to .agents/skills/; add -g for ~/.codex/skills/.
Install the "audit-round" agent skill from https://github.com/Arch1eSUN/Arcgentic/tree/main/skills/audit-round into .agents/skills/audit-round/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "audit-round", then confirm the skill loads.
Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
skills CLI
$ npx skills add Arch1eSUN/Arcgentic --skill audit-round -a cursor
Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.
Install the "audit-round" agent skill from https://github.com/Arch1eSUN/Arcgentic/tree/main/skills/audit-round into .cursor/skills/audit-round/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "audit-round", then confirm the skill loads.
Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
skills CLI
$ npx skills add Arch1eSUN/Arcgentic --skill audit-round -a gemini-cli
Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.
Install the "audit-round" agent skill from https://github.com/Arch1eSUN/Arcgentic/tree/main/skills/audit-round into .gemini/skills/audit-round/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "audit-round", then confirm the skill loads.
Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
skills CLI
$ npx skills add Arch1eSUN/Arcgentic --skill audit-round -a github-copilot
Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.
Install the "audit-round" agent skill from https://github.com/Arch1eSUN/Arcgentic/tree/main/skills/audit-round into .github/skills/audit-round/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "audit-round", then confirm the skill loads.
GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
skills CLI
$ npx skills add Arch1eSUN/Arcgentic --skill audit-round -a opencode
OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
Install the "audit-round" agent skill from https://github.com/Arch1eSUN/Arcgentic/tree/main/skills/audit-round into .opencode/skills/audit-round/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "audit-round", then confirm the skill loads.
OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
Skill name
audit-round
GitHub stars
286
Token cost
~1.6k tokens
SKILL.md length
700 words
Files
9 (incl. references)
Skills in repo
19
Repo updated
First seen
Licence
MIT
At a glance
External-audit role for arcgentic rounds. An agent skill from Arch1eSUN/Arcgentic.
Works in 5 steps: .agentic-rounds/state.yaml (via… → The handoff doc for this round (path in… → The dev commit chain (SHAs in… → …
Explicitly requests an external audit of a finished round
SKILL.md covers Role boundary, Inputs you read (in order), Process (mechanical) and Verdict file structure…, plus 3 more sections
Calls bash and git
What it does
Audit Round is an agent skill from Arch1eSUN/Arcgentic. External-audit role for arcgentic rounds. Loaded when arcgentic state.yaml is in awaitingaudit or auditinprogress, OR when the user explicitly requests an external audit of a finished round, OR when reviewing a handoff doc + commit chain against the round's declared scope. Produces a PASS / NEEDSFIX / AUDITINCOMPLETE verdict document with mechanically-verifiable fact table, structured findings (P0-P3), and applies the lesson codification protocol. The output verdict file IS the handoff — do not paste verdict text…
Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 9 other files, including reference files (for example `references/doc-vs-impl-regrep.md`, `references/fact-table-design.md` and `references/fix-example-vs-contract.md`).
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
Explicitly requests an external audit of a finished round
When reviewing a handoff doc + commit chain against the rounds declared scope
Example prompts
“/audit-round”
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
1.agentic-rounds/state.yaml (via pickup.sh) — confirms you're in audit_in_progress
2The handoff doc for this round (path in state.yaml: current_round.handoff_doc.path)
3The dev commit chain (SHAs in state.yaml: current_round.dev_commits) — read EACH commit's diff
5(Optional) The lesson-codifier report — gives you cross-round pattern context
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
git
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.
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
Audit Round loads about 1.6k tokens when it runs, and up to ~9.3k if it reads all its reference files. Until then it costs about 137 tokens; SKILL.md has 700 words of instructions outside code blocks.
Always· name and description, kept in context so the agent knows when to use it
~137
When it runs· the whole SKILL.md, loaded when a task matches
~1.6k
With references· SKILL.md plus every file in references/, read only if the agent opens them
~9.3k
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.
Download SKILL.mdSave it as .claude/skills/audit-round/SKILL.md (or your agent's skills folder). This skill also uses 8 other files; get the full folder from GitHub.
name
audit-round
description
External-audit role for arcgentic rounds. Loaded when arcgentic state.yaml is in awaiting_audit or audit_in_progress, OR when the user explicitly requests an external audit of a finished round, OR when reviewing a handoff doc + commit chain against the round's declared scope. Produces a PASS / NEEDS_FIX / AUDIT_INCOMPLETE verdict document with mechanically-verifiable fact table, structured findings (P0-P3), and applies the lesson codification protocol. The output verdict file IS the handoff — do not paste verdict text into chat.
Audit round
Role boundary
You are the EXTERNAL auditor. You did NOT write the round being audited. You did NOT plan it. You are reading inputs cold and looking for problems.
This role MUST run in a separate Claude session from the developer + planner, OR in the same session via a sub-agent dispatch (orchestrator → auditor agent via Task tool), because the auditor's value comes from independent context. Reading the dev session's reasoning chain corrupts the audit.
Inputs you read (in order)
.agentic-rounds/state.yaml (via pickup.sh) — confirms you're in audit_in_progress
The handoff doc for this round (path in state.yaml: current_round.handoff_doc.path)
The dev commit chain (SHAs in state.yaml: current_round.dev_commits) — read EACH commit's diff
(Optional) The lesson-codifier report — gives you cross-round pattern context
You DO NOT read: any session transcript / planner's reasoning / developer's chat.
Process (mechanical)
Pre-round scan — invoke arcgentic:pre-round-scan first (mandatory)
Verdict outline — open references/verdict-template.md; copy it as <project>/<audits_dir>/<round-id>-external-audit-verdict.md
Fact table — for every claim the round makes (scope completed, tests pass, doc sections present, mandates followed), write a fact row with a Bash command. See references/fact-table-design.md.
Run every fact — bash <project>/scripts/dev.sh audit-check <verdict.md> --strict if project has it; otherwise loop the fact commands manually. NO fact can be ≥ N style — every fact has an exact expected value.
Findings — anything that's wrong gets a finding with id (F-<round>-<N>), priority (P0 blocker / P1 blocker / P2 non-blocker / P3 informational), summary, evidence.
Lesson codification — apply references/lesson-codification-protocol.md. Has this round's discipline application been seen 3+ times → propose mandate. Novel preservation type seen → declare it.
Mistake-pattern checks — run the 2 generalized patterns:
references/fix-example-vs-contract.md — is any fix-round only addressing the reproducer?
references/sibling-doc-sweep.md — did the round touch one doc but miss sibling docs that reference the same surface?
references/doc-vs-impl-regrep.md — does every spec claim grep-quote the impl source?
Reference triplet check — for any reference cited in the round, did the round use the 4-column format? See references/reference-triplet.md.
Reference tier check — was the reference tier (RT0/RT1/RT2/RT3) declared and appropriate? See references/rt-tier-taxonomy.md.
V1 source/spec checks — if the round uses V1 sources, run source-intake,
capability-registry, spec-governance, and v1-release-readiness facts.
Verdict completeness check — run:bash
arcgentic verdict-completeness <verdict.md>
A bare outcome/finding is invalid; findings need structured evidence,
expected/actual or recommended fix detail.
Verdict outcome — PASS, NEEDS_FIX, or AUDIT_INCOMPLETE.
PASS = fact_table_pass==total AND no P0/P1 findings.
NEEDS_FIX = any P0/P1.
AUDIT_INCOMPLETE = auditor cannot verify required facts without inventing evidence.
Update state.yaml — set current_round.audit_verdict per schema.
Don't accept a verdict that PASSes with P1 findings — by definition impossible
Don't approve audit_verdict.outcome=PASS while fact_table_pass < total — mechanical contradiction
Don't force PASS/NEEDS_FIX when required evidence is missing; use AUDIT_INCOMPLETE
Don't extend scope — if the auditor sees something out of round scope, log it as forward-debt, don't NEEDS_FIX on it
When to escalate to founder / human
The round's scope itself is wrong (handoff doc doesn't match standing mandates)
A mandate appears to need amendment because the round repeatedly bumps against it (this is lesson codification's job — but if the auditor sees a mandate-amendment opportunity, surface it)
The state machine itself appears stuck (gate fails repeatedly with no clear way forward)
Audit Round 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.
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
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.
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.
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…
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.
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.
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.
External-audit role for arcgentic rounds. An agent skill from Arch1eSUN/Arcgentic. Audit Round is an agent skill from Arch1eSUN/Arcgentic. External-audit role for arcgentic rounds.
When should I use Audit Round?
Audit Round fits situations like: explicitly requests an external audit of a finished round; when reviewing a handoff doc + commit chain against the rounds declared scope.
How do I install Audit Round in Claude Code?
Run `npx skills add Arch1eSUN/Arcgentic --skill audit-round -a claude-code`. Or copy the skill folder (skills/audit-round in Arch1eSUN/Arcgentic) into .claude/skills/audit-round in your project. Claude Code loads it when a task matches its description.
How do I install Audit Round in Codex?
Run `npx skills add Arch1eSUN/Arcgentic --skill audit-round -a codex`. Or copy the skill folder (skills/audit-round in Arch1eSUN/Arcgentic) into .agents/skills/audit-round in your project. Codex loads it when a task matches its description.
Can I use Audit Round 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 audit-round -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/audit-round, .gemini/skills/audit-round, .github/skills/audit-round and .opencode/skills/audit-round in your project.
What does Audit Round need to run?
Going by SKILL.md and its folder, Audit Round needs the command-line tools its instructions call (bash and git).
Does Audit Round access the network?
SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Audit Round 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 Audit Round use?
Audit Round 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 Audit Round use?
About 1.6k tokens (SKILL.md is roughly 6.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 7.7k tokens, read only when the agent opens those files.
What are the alternatives to Audit Round?
Skills that share tags, products or a category with Audit Round: 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 Audit Round?
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.
