New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Adversarial Verify

by Archive228 in Archive228/loopkit

Review a diff against the goal spec assuming the code is BROKEN.

MITAuto-check passedDevelopment

Install Adversarial Verify

skills CLI
$ npx skills add Archive228/loopkit --skill adversarial-verify -a claude-code

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

GitHub CLI
$ gh skill install Archive228/loopkit adversarial-verify --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/Archive228/loopkit.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/adversarial-verify .claude/skills/adversarial-verify && 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
adversarial-verify
GitHub stars
755
Token cost
~454 tokens
SKILL.md length
209 words
Files
1
Skills in repo
43
Repo updated
First seen
Licence
MIT

At a glance

Review a diff against the goal spec assuming the code is BROKEN.

  • Works in 11 steps: Relaxed tests — assertions weakened or… → Swallowed errors — try/except that hides… → Fake renames — a function "fixed" by… → …
  • Tasks that involve Code review
  • SKILL.md covers Read first, The 11 shortcuts agents take… and Output (JSON, no prose)
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Adversarial Verify is an agent skill from Archive228/loopkit. Review a diff against the goal spec assuming the code is BROKEN. The reviewer that lives in the maker's head always agrees with itself — this pulls review into a hostile, separate pass. Invoke after every code change before marking work done.

Its SKILL.md is about 450 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 Development, covering Code review. The repository describes itself as: 33 battle-tested skills + minimal .claude harness for any coding agent (Claude Code, Cursor, Codex, Gemini CLI). The licence is MIT.

When your agent uses it

  • Tasks that involve Code review

Example prompts

  • “/adversarial-verify”

Workflow steps

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

  1. Relaxed tests — assertions weakened or deleted to make red go green.
  2. Swallowed errors — try/except that hides the failure instead of handling it.
  3. Fake renames — a function "fixed" by renaming, behavior unchanged.
  4. Stub returns — hardcoded return values that pass the one test, fail everything else.
  5. Comment-as-fix — the bug is now a TODO.
  6. Happy-path only — 500s, empty inputs, missing files unhandled.
  7. Scope creep — changes unrelated to the goal ("while I was in there").
  8. Invented API — a method/param that doesn't exist in the actual source.
  9. Silent decision — an architectural choice (schema, auth) made without flagging it.
  10. Pass-by-mock — the test mocks the exact thing it claims to verify.
  11. Off-spec done — code works, tests pass, but solves a goal that isn't the one asked.

What it can do on your machine

Read from SKILL.md and the folder at commit 5ae033e. 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

    No scripts in the folder and no shell commands in SKILL.md (its code samples are json).

    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

Adversarial Verify loads about 454 tokens when it runs. Until then it costs about 65 tokens; SKILL.md has 209 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~65
When it runs · the whole SKILL.md, loaded when a task matches
~454

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 Archive228/loopkit at commit 5ae033e, republished under its MIT licence (© Archive228). 209 words, ~454 tokens.

Download SKILL.mdSave it as .claude/skills/adversarial-verify/SKILL.md (or your agent's skills folder).
name
adversarial-verify
description
Review a diff against the goal spec assuming the code is BROKEN. The reviewer that lives in the maker's head always agrees with itself — this pulls review into a hostile, separate pass. Invoke after every code change before marking work done.
when_to_use
a code change is "done", before flipping a task to complete, before commit

Adversarial Verify

Default stance: the code is broken until proven otherwise. Your job is to find where. Do not be polite. Do not propose fixes. Do not run the code. Just hunt.

Read first

  • The goal spec (PROMPT.md / the task). What does "done" actually require?
  • The diff. Every changed line.

The 11 shortcuts agents take to fake "done" — check each

  1. Relaxed tests — assertions weakened or deleted to make red go green.
  2. Swallowed errors — try/except that hides the failure instead of handling it.
  3. Fake renames — a function "fixed" by renaming, behavior unchanged.
  4. Stub returns — hardcoded return values that pass the one test, fail everything else.
  5. Comment-as-fix — the bug is now a TODO.
  6. Happy-path only — 500s, empty inputs, missing files unhandled.
  7. Scope creep — changes unrelated to the goal ("while I was in there").
  8. Invented API — a method/param that doesn't exist in the actual source.
  9. Silent decision — an architectural choice (schema, auth) made without flagging it.
  10. Pass-by-mock — the test mocks the exact thing it claims to verify.
  11. Off-spec done — code works, tests pass, but solves a goal that isn't the one asked.

Output (JSON, no prose)

json
{"passes": false, "failures": [{"line": 42, "shortcut": "swallowed errors", "why": "..."}]}

If it genuinely passes, say so in one line. Most of the time, it doesn't.

© Archive228, 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/adversarial-verify of Archive228/loopkit.

Open the folder on GitHubat commit 5ae033e

Compare with similar skills

Adversarial Verify 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.

Adversarial Verify compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Adversarial Verify this skillArchive228/loopkit755—~454Automated safety check: PassMIT
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
Code Review ChecklistshareAI-lab/learn-claude-code78k5 repos~1.1kAutomated safety check: PassMIT
Backend Code Reviewlangflow-ai/langflow155k—~3.5kAutomated safety check: NotesMIT
Mole Bug Patternstw93/Mole70k—~2kAutomated safety check: PassGPL-3.0
Backend Code Reviewlanggenius/dify158k—~676Automated safety check: PassCustom licence

Similar skills

  • PR Babysitter

    openinterpreter/openinterpreter

    Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.

    69k GitHub starsUsed in 3 repos~4.2k tokens
    DevelopmentAuto-check passed

  • Code Review Checklist

    shareAI-lab/learn-claude-code

    Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.

    78k GitHub starsUsed in 5 repos~1.1k tokens
    DevelopmentAuto-check passed

  • Backend Code Review

    langflow-ai/langflow

    Review backend code for quality, security, maintainability, and best practices based on established checklist rules.

    155k GitHub stars~3.5k tokensUpdated yesterday
    DevelopmentAuto-check: notes

  • Mole Bug Patterns

    tw93/Mole

    A catalog of recurring bug shapes in the Mole Mac cleaner, used to review safety-sensitive diffs for deletion safety, unbounded commands, shell traps and weak tests.

    70k GitHub stars~2k tokensUpdated yesterday
    DevelopmentAuto-check passed

  • Backend Code Review

    langgenius/dify

    Reviews backend code under api/ for concrete, reproducible defects, routes to rule packs for architecture, schema, repositories and SQLAlchemy, and ranks findings from P0 to P3.

    158k GitHub stars~676 tokensUpdated today
    DevelopmentAuto-check passed

  • WooCommerce Code Review

    woocommerce/woocommerce

    Reviews WooCommerce code changes against the project's standards, flagging backend PHP architecture, naming, documentation, data integrity and testing violations.

    11k GitHub starsUsed in 3 repos~1.1k tokens
    DevelopmentAuto-check passed

More from Archive228/loopkit

All 43 skills in this repo

  • Hitl Escalate

    Archive228/loopkit

    Escalate blocked runs to a human via configured channel or fallback to BLOCKED.md and exit the loop.

    755 GitHub stars~1.2k tokensUpdated 2 mo ago
    Auto-check passed

  • Structured Output

    Archive228/loopkit

    Get JSON out of the model reliably. An agent skill from Archive228/loopkit.

    755 GitHub stars~830 tokensUpdated 2 mo ago
    Auto-check passed

  • Using Loopkit

    Archive228/loopkit

    A skill your agent uses when starting any conversation in a loopkit-enabled project - establishes how to find and use loopkit's 49 skills, requiring skill invocation before ANY response including…

    755 GitHub stars~1.4k tokensUpdated 2 mo ago
    Auto-check passed

  • Active Memory Reminder

    Archive228/loopkit

    Before compaction Loopkit extracts decisions into claude-decisions.json (machine-readable).

    755 GitHub stars~1.2k tokensUpdated 2 mo ago
    Auto-check passed

  • Eval Harness

    Archive228/loopkit

    Build a repeatable eval loop that grades agent output with an LLM judge, so prompt/skill changes get scored against a baseline instead of eyeballed.

    755 GitHub stars~876 tokensUpdated 2 mo ago
    Auto-check passed

  • Feature List JSON

    Archive228/loopkit

    Enumerate every end-to-end feature as strict JSON entries with passes:false, editable-passes-only discipline, and priority order.

    755 GitHub stars~1.2k tokensUpdated 2 mo ago
    Auto-check passed

Categories

Questions about Adversarial Verify

What does Adversarial Verify do?

Review a diff against the goal spec assuming the code is BROKEN. Adversarial Verify is an agent skill from Archive228/loopkit. Review a diff against the goal spec assuming the code is BROKEN.

When should I use Adversarial Verify?

Adversarial Verify fits situations like: tasks that involve Code review.

How do I install Adversarial Verify in Claude Code?

Run `npx skills add Archive228/loopkit --skill adversarial-verify -a claude-code`. Or copy the skill folder (skills/adversarial-verify in Archive228/loopkit) into .claude/skills/adversarial-verify in your project. Claude Code loads it when a task matches its description.

How do I install Adversarial Verify in Codex?

Run `npx skills add Archive228/loopkit --skill adversarial-verify -a codex`. Or copy the skill folder (skills/adversarial-verify in Archive228/loopkit) into .agents/skills/adversarial-verify in your project. Codex loads it when a task matches its description.

Can I use Adversarial Verify 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 Archive228/loopkit --skill adversarial-verify -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/adversarial-verify, .gemini/skills/adversarial-verify, .github/skills/adversarial-verify and .opencode/skills/adversarial-verify in your project.

What does Adversarial Verify need to run?

SKILL.md names no scripts, command-line tools or credentials: Adversarial Verify is instructions for the agent only.

Does Adversarial Verify 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 Adversarial Verify 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 Adversarial Verify use?

Adversarial Verify 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 Adversarial Verify use?

About 454 tokens (SKILL.md is roughly 1.8k 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 Adversarial Verify?

Skills that share tags, products or a category with Adversarial Verify: PR Babysitter (openinterpreter/openinterpreter, 69k stars), Code Review Checklist (shareAI-lab/learn-claude-code, 78k stars), Backend Code Review (langflow-ai/langflow, 155k stars) and Mole Bug Patterns (tw93/Mole, 70k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Adversarial Verify?

Archive228 (a GitHub user) maintains it in Archive228/loopkit, which has 755 GitHub stars. The repository holds 43 skills in this directory. The repository was last updated on July 14, 2026.

Source: Archive228/loopkit on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.