ai-adversarial-loop SKILL.md skillA
ai-adversarial-loop from arcasilesgroup/ai-engineering is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add arcasilesgroup/ai-engineering/ai-adversarial-loop@git:20260926.b0fd9cfPins git:20260926.b0fd9cf in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- arcasilesgroup/ai-engineering
- Path
skills/ai-adversarial-loop/SKILL.md- Versions recorded
- 1
- Latest version
- git:20260926.b0fd9cf, committed Sep 26, 2026
- Size
- 4,573 bytes
- Repository stars
- 62
- License
- Apache-2.0
Coordinate a multi-round debate between two agents until the code is clean. adversarial-reviewer (the critic) assumes everything is wrong; fixer implements fixes or disputes them with evidence. They exchange findings through a shared thread file, and each keeps its memory across rounds. Use as the orchestrator's review gate, or when the user asks for an adversarial review-and-fix loop on recent changes (e.g. "/ai-adversarial-loop", "have the critic and fixer go at checkpoint 3").
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Adversarial loop You are the **coordinator**. You run in the main session because only the main session can start and resume agents. Subagents can't launch other agents, and agent-team teammates can't be the lead. You never review code or fix it yourself, and you **never read the thread file**. You pass turns between the two agents and act on their short returns. ## Setup - **Thread file:** under `/ai-orchestrator`, it's `.ai-engineering/workflow/reviews/<slug>-<id>.md`. Standalone, it's `.ai-engineering/workflow/reviews/<topic>-<YYYY-MM-DD>.md`. Create it with a header: the checkpoint's goal and acceptance criteria (or the user's scope), the `changed_files`, and the verify commands. Nothing else. - **Scope:** the checkpoint slice and `changed_files`. Standalone, it's `git diff HEAD` plus untracked files, and the verify commands are the full test suite, lint and build from the **Project config** section of `AGENTS.md`. - **Under `/ai-orchestrator`,** prompts start with the gate markers: `[checkpoint <slug>#<id> review]` for the critic and `[checkpoint <slug>#<id> fix]` for the fixer. ## Rounds (at most 4) …
Read the whole file at its exact version.
How to install
mdr add arcasilesgroup/ai-engineering/ai-adversarial-loop@sha256:bda5c3a60bff9a46The line at the top of this page pins the label git:20260926.b0fd9cf, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_wjg4kco3bjiiw5vw)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Sep 26, 2026.
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (4573 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
arcasilesgroup/ai-engineering · 62 stars · license Apache-2.0 · pushed 2026-10-19 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_wjg4kco3bjiiw5vw GET https://markdownregistry.com/api/v1/resolve?ref=arcasilesgroup/ai-engineering/ai-adversarial-loop GET https://markdownregistry.com/api/v1/blob/bda5c3a60bff9a468db53926178117e26b4170546e09f929323c3290b0d97833
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.