Adversarial Review Before Shipping
oaustegard/claude-skills
Has a fresh-context adversary attack a blog post, recommendation, analysis brief or piece of code before you ship it, using a profile suited to that kind of artifact.
Acts as a skeptical checker for changes an implementer sub-agent made, running the tests, confirming the diff scope and returning approve, reject or escalate to a human.
Install Loop Change Verifier
$ npx skills add cobusgreyling/loop-engineering --skill loop-verifier -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install cobusgreyling/loop-engineering loop-verifier --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/cobusgreyling/loop-engineering.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/loop-verifier .claude/skills/loop-verifier && rm -rf skills-srcUse ~/.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/
Install the "loop-verifier" agent skill from https://github.com/cobusgreyling/loop-engineering/tree/main/skills/loop-verifier into .claude/skills/loop-verifier/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "loop-verifier", 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.
$skill-installer install https://github.com/cobusgreyling/loop-engineering/tree/main/skills/loop-verifierType 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.
$ npx skills add cobusgreyling/loop-engineering --skill loop-verifier -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install cobusgreyling/loop-engineering loop-verifier --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cobusgreyling/loop-engineering.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/loop-verifier .agents/skills/loop-verifier && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "loop-verifier" agent skill from https://github.com/cobusgreyling/loop-engineering/tree/main/skills/loop-verifier into .agents/skills/loop-verifier/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "loop-verifier", 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.
$ npx skills add cobusgreyling/loop-engineering --skill loop-verifier -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install cobusgreyling/loop-engineering loop-verifier --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cobusgreyling/loop-engineering.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/loop-verifier .cursor/skills/loop-verifier && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "loop-verifier" agent skill from https://github.com/cobusgreyling/loop-engineering/tree/main/skills/loop-verifier into .cursor/skills/loop-verifier/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "loop-verifier", 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.
$ gemini skills install https://github.com/cobusgreyling/loop-engineering.git --path skills/loop-verifier--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add cobusgreyling/loop-engineering --skill loop-verifier -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install cobusgreyling/loop-engineering loop-verifier --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cobusgreyling/loop-engineering.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/loop-verifier .gemini/skills/loop-verifier && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "loop-verifier" agent skill from https://github.com/cobusgreyling/loop-engineering/tree/main/skills/loop-verifier into .gemini/skills/loop-verifier/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "loop-verifier", 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.
$ gh skill install cobusgreyling/loop-engineering loop-verifierInstalls 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).
$ npx skills add cobusgreyling/loop-engineering --skill loop-verifier -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/cobusgreyling/loop-engineering.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/loop-verifier .github/skills/loop-verifier && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "loop-verifier" agent skill from https://github.com/cobusgreyling/loop-engineering/tree/main/skills/loop-verifier into .github/skills/loop-verifier/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "loop-verifier", 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.
$ npx skills add cobusgreyling/loop-engineering --skill loop-verifier -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install cobusgreyling/loop-engineering loop-verifier --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cobusgreyling/loop-engineering.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/loop-verifier .opencode/skills/loop-verifier && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "loop-verifier" agent skill from https://github.com/cobusgreyling/loop-engineering/tree/main/skills/loop-verifier into .opencode/skills/loop-verifier/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "loop-verifier", 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
loop-verifier- GitHub stars
- 11k
- Used in
- 1 other repo
- Token cost
- ~383 tokens
- SKILL.md length
- 147 words
- Files
- 1
- Skills in repo
- 21
- Repo updated
- First seen
- Licence
- MIT
At a glance
Acts as a skeptical checker for changes an implementer sub-agent made, running the tests, confirming the diff scope and returning approve, reject or escalate to a human.
- Works in 5 steps: Scope: Only relevant files changed; no… → Intent: Change clearly addresses the… → Tests: You ran tests (or equivalent) and… → …
- Reviewing a sub-agent's fix before it is accepted into a loop
- SKILL.md covers Inputs, Checklist (all must pass for…, Output and Rules
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
This skill sets up a maker and checker split. The agent in this role must never be the one that wrote the change, and its default stance is to reject until evidence says otherwise. It receives the implementer's summary and diff, the original issue, CI failure or comment, the project's test and lint commands, and any allowed file scope the loop defines.
A five-item checklist must pass in full for approval: only relevant files changed with no denylisted paths, the change addresses the stated target, the verifier itself ran the tests and reports output, no disabled tests or skipped assertions, and a recommendation for human review when risk is medium or higher. The output is a verdict of APPROVE, REJECT or ESCALATE_HUMAN with supporting evidence. A claim that tests passed is never trusted, and if tests cannot run because of the environment the verdict is escalation to a human.
When your agent uses it
- Reviewing a sub-agent's fix before it is accepted into a loop
- Confirming that a change stayed inside the allowed file scope
- Checking that a passing test run was not achieved by disabling tests
Example prompts
- “Verify the minimal-fix agent's patch for the failing CI job and give a verdict.”
- “Check this diff against the original issue and run the tests before approving.”
- “Look for reasons to reject the implementer's change to the payment retry logic.”
Requirements
- Test and lint commands the agent can run in the project
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- Scope: Only relevant files changed; no denylist paths; no unrelated edits.
- Intent: Change clearly addresses the stated target — not a different problem.
- Tests: You ran tests (or equivalent) and report pass/fail with output snippet.
- No cheating: No disabled tests, skipped assertions, or commented-out checks.
- Risk: For medium+ risk, recommend human review even if tests pass.
What it can do on your machine
Read from SKILL.md and the folder at commit 1f1e8a7. 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 markdown).
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
Loop Change Verifier loads about 383 tokens when it runs. Until then it costs about 56 tokens; SKILL.md has 147 words of instructions outside code blocks.
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 cobusgreyling/loop-engineering at commit 1f1e8a7, republished under its MIT licence (© cobusgreyling). 147 words, ~383 tokens.
Download SKILL.mdSave it as
.claude/skills/loop-verifier/SKILL.md (or your agent's skills folder).- name
- loop-verifier
- description
- Independent verification agent for loop-produced changes. Finds reasons to reject. Runs tests. Confirms diff scope. Use after minimal-fix or any implementer sub-agent — never in the same role as the implementer.
- user_invocable
- true
Loop Verifier Skill
You are the checker in a maker/checker split. Your job is to reject unless evidence is strong.
Inputs
- Implementer's proposal summary and diff
- Original issue / CI failure / comment being addressed
- Project test/lint commands
- Allowed file scope (if specified by the loop)
Checklist (all must pass for APPROVE)
- Scope: Only relevant files changed; no denylist paths; no unrelated edits.
- Intent: Change clearly addresses the stated target — not a different problem.
- Tests: You ran tests (or equivalent) and report pass/fail with output snippet.
- No cheating: No disabled tests, skipped assertions, or commented-out checks.
- Risk: For medium+ risk, recommend human review even if tests pass.
Output
## Verdict: APPROVE | REJECT | ESCALATE_HUMAN
### Evidence
- Tests: (command + result)
- Scope check: (pass/fail + notes)
### If REJECT
- Reasons: (numbered, specific)
- Suggested next step for implementerRules
- Default stance: REJECT until proven otherwise.
- Do not trust implementer's claim that tests passed — run them.
- If you cannot run tests (env issue) → ESCALATE_HUMAN.
- Be concise. The loop and human read this under time pressure.
© cobusgreyling, 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/loop-verifier of cobusgreyling/loop-engineering.
Open the folder on GitHubat commit 1f1e8a7
Used in 1 other repository
We found 2 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in cobusgreyling/loop-engineering, which our catalogue first saw on October 7, 2026.
Compare with similar skills
Loop Change Verifier 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Loop Change Verifier this skillcobusgreyling/loop-engineering | 11k | 1 repos | ~383 | Automated safety check: Pass | MIT | |
| Adversarial Review Before Shippingoaustegard/claude-skills | 150 | — | ~3.4k | Automated safety check: Pass | MIT | |
| Verification Skill Maintenancecursor/plugins | 10k | 8 repos | ~1.2k | Automated safety check: Pass | None | |
| Iteration Progress Auditprime-radiant-inc/iterative-development | 181 | — | ~1.1k | Automated safety check: Pass | Apache-2.0 | |
| Implementing Tasks with Subagent Reviewprime-radiant-inc/iterative-development | 181 | — | ~1.2k | Automated safety check: Pass | Apache-2.0 | |
| O2 Review Loopopenobserve/openobserve | 22k | — | ~3.7k | Automated safety check: Pass | AGPL-3.0 |
Similar skills
- Official
Verification Skill Maintenance
cursor/plugins
Audits a project's verification skill and its feature map against the source and the live app, then ships at most one pull request of proven corrections.
Iteration Progress Audit
prime-radiant-inc/iterative-development
Checks the quality of behavior evidence after each iteration in three tiers, using two auditor subagents in parallel to review the same work and find gaps.
Implementing Tasks with Subagent Review
prime-radiant-inc/iterative-development
Runs a batch of TDD-sized tasks by dispatching an implementer subagent per task, followed by two-stage parallel adversarial review and fix loops.
O2 Review Loop
openobserve/openobserve
Splits a change into planner, coder and independent reviewer roles: you confirm a spec, a subagent implements it, and a separate reviewer checks each round's local WIP commit.
Clawteam
win4r/ClawTeam-OpenClaw
Multi-agent swarm orchestration. An agent skill from win4r/ClawTeam-OpenClaw.
More from cobusgreyling/loop-engineering
All 21 skills in this repoInstall Loop Engineering
cobusgreyling/loop-engineering
Installs Loop Engineering into a project through the single @cobusgreyling/loop CLI, scaffolding a report-only loop and a readiness score.
Loop Constraints Enforcer
cobusgreyling/loop-engineering
Loads a project's loop-constraints.md before any other action and blocks pushes, edits or merges that violate the rules it defines.
Release Notes Drafter
cobusgreyling/loop-engineering
Turns a structured list of changes from changelog-scan into a categorized, user-facing release notes draft file, and never publishes anything.
Issue Triage Loop
cobusgreyling/loop-engineering
Scans open GitHub issues and discussions, flags duplicates, scores priority and proposes labels into issue-triage-state.md without ever labeling or closing.
Loop Triage Report
cobusgreyling/loop-engineering
Turns CI failures, open issues, recent commits and chat threads into a prioritized markdown report that an automation loop can act on without inventing architecture work.
Loop Token Budget Guard
cobusgreyling/loop-engineering
Check token budget and run-log spend before and after a loop run. Enforces early exit when over budget or when there is no actionable work.
Related
Categories
Questions about Loop Change Verifier
What does Loop Change Verifier do?
Acts as a skeptical checker for changes an implementer sub-agent made, running the tests, confirming the diff scope and returning approve, reject or escalate to a human. This skill sets up a maker and checker split. The agent in this role must never be the one that wrote the change, and its default stance is to reject until evidence says otherwise.
When should I use Loop Change Verifier?
Loop Change Verifier fits situations like: reviewing a sub-agent's fix before it is accepted into a loop; confirming that a change stayed inside the allowed file scope; checking that a passing test run was not achieved by disabling tests.
How do I install Loop Change Verifier in Claude Code?
Run `npx skills add cobusgreyling/loop-engineering --skill loop-verifier -a claude-code`. Or copy the skill folder (skills/loop-verifier in cobusgreyling/loop-engineering) into .claude/skills/loop-verifier in your project. Claude Code loads it when a task matches its description.
How do I install Loop Change Verifier in Codex?
Run `npx skills add cobusgreyling/loop-engineering --skill loop-verifier -a codex`. Or copy the skill folder (skills/loop-verifier in cobusgreyling/loop-engineering) into .agents/skills/loop-verifier in your project. Codex loads it when a task matches its description.
Can I use Loop Change Verifier 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 cobusgreyling/loop-engineering --skill loop-verifier -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/loop-verifier, .gemini/skills/loop-verifier, .github/skills/loop-verifier and .opencode/skills/loop-verifier in your project.
What does Loop Change Verifier need to run?
SKILL.md names no scripts, command-line tools or credentials: Loop Change Verifier is instructions for the agent only. Our summary lists: Test and lint commands the agent can run in the project.
Does Loop Change Verifier 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 Loop Change Verifier 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 Loop Change Verifier use?
Loop Change Verifier 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 Loop Change Verifier use?
About 383 tokens (SKILL.md is roughly 1.5k 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 Loop Change Verifier?
Skills that share tags, products or a category with Loop Change Verifier: Adversarial Review Before Shipping (oaustegard/claude-skills, 150 stars), Verification Skill Maintenance (cursor/plugins, 10k stars), Iteration Progress Audit (prime-radiant-inc/iterative-development, 181 stars) and Implementing Tasks with Subagent Review (prime-radiant-inc/iterative-development, 181 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Loop Change Verifier?
cobusgreyling (a GitHub user) maintains it in cobusgreyling/loop-engineering, which has 11,429 GitHub stars. The repository holds 21 skills in this directory. The repository was last updated on October 7, 2026.
Source: cobusgreyling/loop-engineering on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.