agentmods.dev

excanon: Skill for Claude Code

.agents/skills/adversarial-review/SKILL.md

adversarial-review is a skill for Claude Code, Codex from jmalovera10/excanon. It costs 50 tokens per session (503 once invoked), scanned A, original, MIT.

A review process in which independent reviewers try to find ways a code change, specification, or plan could fail. A lead then sorts the findings by what must be acted on, considered, recorded, or dismissed.

In plain words
What is it for?
It helps challenge diffs, specifications, and plans with concrete failure cases and a clear triage decision.
Why use it?
It finds edge cases, contract problems, security risks, and maintainability issues before a high-impact change is released.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is jmalovera10/excanon's own configuration. It tells Claude Code and Codex how to work on excanon itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything excanon configures →

not rated 5repo 6d ago A scan 50 tokens original MIT
View source ↗ jmalovera10/excanon
Reuse

Borrowing it

Nothing to install: this file belongs to jmalovera10/excanon. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/jmalovera10/excanon/main/.agents/skills/adversarial-review/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/jmalovera10/excanon

Made for: Claude Code, 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/jmalovera10/excanon/adversarial-review/github.svg)](https://agentmods.dev/skills/jmalovera10/excanon/adversarial-review)
Your own site
<a href="https://agentmods.dev/skills/jmalovera10/excanon/adversarial-review"><img src="https://agentmods.dev/badge/skills/jmalovera10/excanon/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/jmalovera10/excanon/adversarial-review"><img src="https://agentmods.dev/badge/skills/jmalovera10/excanon/adversarial-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 503 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 $0.00050 $0.00503
Opus 5.5 $0.00020 $0.00201
Sonnet 5.5 $0.00010 $0.00101
Haiku 4.5 $0.00005 $0.00050

Measured today against content hash 187232ac511a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 today.

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.

.agents/skills/adversarial-review/SKILL.md · 38 lines

What it actually says

Adversarial review

Reviewers each try to prove the change is wrong. They work independently, from different angles. A lead then triages their findings. The deliverable is a verdict. Nothing gets fixed automatically.

Steps

  1. State the intent. Write one paragraph on what the change is meant to do, from the spec, plan and commits. If it's unclear, stop and ask the caller. Reviewing against the wrong intent produces noise.

  2. Fan out. Start 2 or 3 read-only reviewers at once, each with the same intent and diff but a different angle:

    Angle Hunts for
    Correctness Wrong results, unhandled edge cases (empty lists, nil, deep nesting, huge inputs), broken error tuples, callers left inconsistent
    Contract and security Public API or behavior drift, code execution paths, injection through rule JSON, resource exhaustion, unsafe defaults
    Maintainability Needless abstraction, missing tests for new logic, tests that check implementation instead of behavior, unclear naming

    Each reviewer lists only findings it can support with a concrete input, a line reference or a failing test. Guesses are labeled as guesses.

  3. Triage. The caller, or a fresh judge at the judgment tier for high-impact changes, merges duplicates and sorts each finding:

    • Act on: a real issue that would block a careful human reviewer.
    • Consider: a legitimate point, but the cost may outweigh it. Goes to the maintainer.
    • Noted: valid but not worth acting on now.
    • Dismissed: wrong or out of context. One line on why.

    A finding raised independently by two or more reviewers is the strongest signal.

  4. Hand back. "Act on" findings go back to the build stage as a fix brief. "Consider" findings go into the PR description for the maintainer.

Output

The verdict (ship, fix first or rethink) and the triaged findings table.

Cost

Reviewers, plus an optional judge: 2–4 agents.

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. today First seen · 38 lines · 50 tokens per session scan A 187232ac511a

Subscribe to this mod's changes

adversarial-review is a skill published in the GitHub repository jmalovera10/excanon (5 stars, last pushed 6d ago), licensed MIT. It adds 50 tokens to every session and 503 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-11-07.

Code reviewSecurity
Related

adversarial-review compared with skills from other repositories

adversarial-review next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
adversarial-reviewjmalovera10/excanonSkill56d agoMITA50Claude Code, Codex
autoreviewopenclaw/clawhubSkill9.5ktodayMITA17Claude Code, Codex
omh-code-reviewrlaope/oh-my-hermesSkill5.2ktodayMITA48Claude Code, Codex
agent-teams-simplify-and-hardenLeoYeAI/openclaw-master-skillsSkill2.2k6d agoMITA115Claude Code, Codex
revdiff-planumputun/revdiffSkill9472d agoMITA84Claude Code
explore-unknownsdzhng/skillsSkill1.4ktodayMITA162Claude Code, Codex
re0-mergeLilMGenius/paperthinSkill1.4k4d agoMITA70Claude Code