adversarial-review

adversarial-review is a skill for Codex from Eliyce/paqad-ai. It costs 16 tokens per session (617 once invoked), scanned A, original, MIT.

A risk-focused review performed after software design or implementation is complete.

In plain words
What is it for?
Use it to review medium- or high-risk changes, customer-facing work, security-sensitive changes, or changes that are difficult to undo, using the available diffs and verification evidence.
Why use it?
It looks beyond whether the code works, checking for correctness problems, unsafe rollback assumptions, missing tests, broken contracts, performance concerns, and outdated documentation.

Skill for Codex

Written for Codex: agents/openai.yaml present.

Good fit Use it to review medium- or high-risk changes, customer-facing work, security-sensitive changes, or changes that are difficult to undo, using the available diffs and verification evidence.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/eliyce/paqad-ai/adversarial-review
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add Eliyce/paqad-ai --skill adversarial-review
Clone the repo
git clone --depth 1 https://github.com/Eliyce/paqad-ai

Made for: Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for adversarial-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/eliyce/paqad-ai/adversarial-review/github.svg)](https://agentmods.dev/skills/eliyce/paqad-ai/adversarial-review)
Your own site
<a href="https://agentmods.dev/skills/eliyce/paqad-ai/adversarial-review"><img src="https://agentmods.dev/badge/skills/eliyce/paqad-ai/adversarial-review/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for adversarial-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/eliyce/paqad-ai/adversarial-review"><img src="https://agentmods.dev/badge/skills/eliyce/paqad-ai/adversarial-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 16 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 617 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00016 $0.00617
Opus 5 $0.00008 $0.00309
Sonnet 5 $0.00003 $0.00123
Haiku 4.5 $0.00002 $0.00062

Measured 12d ago against content hash 11f2786947b2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

adversarial-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/digest-evidence.sh, scripts/lint-findings.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

runtime/base/skills/adversarial-review/SKILL.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

What It Does

Runs a risk-first review that looks for correctness defects, rollback hazards, missing coverage, and weak assumptions before work is treated as complete.

Use This When

Use this after design or implementation when the change is medium or high risk, customer-facing, security-sensitive, or hard to roll back safely.

Inputs

  • Read the request, accepted plan, code or doc diffs, and any claimed verification results.
  • Read the most relevant canonical docs for the changed behavior.
  • Read references/review-dimensions.md before structuring findings.

Procedure

  1. Run scripts/digest-evidence.sh to flatten .paqad/session/verification-evidence.json into a gate | category | file:line | ac_id | message table; cite this table directly when anchoring findings.
  2. Review the diff and digest against the dimensions in references/review-dimensions.md — correctness, safety, performance, docs drift, verification sufficiency.
  3. Prioritize user-visible failure, data corruption, migration risk, and contract breakage above style.
  4. Draft the output following assets/output.template.md. Severity tags must come from assets/severity-ranks.txt. Order findings non-increasing by severity.
  5. Validate with scripts/lint-findings.sh before returning — exit 0 means the structural contract is met.

Output Contract

  • Match assets/output.template.md: ## Findings heading, one bullet per finding tagged **Critical|High|Medium|Low**, each citing concrete file:line (or gate name) and ending in a Required action: segment. Optional ## Open Questions section.
  • Output must pass scripts/lint-findings.sh (exit 0).

Escalate / Stop Conditions

  • Block completion when a finding implies unsafe rollout, data loss, or broken customer behavior.
  • Ask when the review depends on environment details or hidden rollout assumptions that are not present.
  • Do not dilute confirmed defects with speculative style commentary.

Resources

  • references/review-dimensions.md
  • scripts/digest-evidence.sh
  • scripts/lint-findings.sh
  • assets/output.template.md
  • assets/severity-ranks.txt
  • runtime/capabilities/coding/checklists/database-review-20pt.md
  • agents/openai.yaml

Read the full file on GitHub · 69 lines

Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 69 lines · 16 tokens per session scan A 11f2786947b2

Subscribe to this mod's changes

adversarial-review is a skill published in the GitHub repository Eliyce/paqad-ai (8 stars, last pushed yesterday), licensed MIT. It adds 16 tokens to every session and 617 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.