adversarial-skill-audit

adversarial-skill-audit is a skill for Claude Code, Codex from neverinfamous/memory-journal-mcp. It costs 50 tokens per session (1,115 once invoked), scanned A, original, MIT.

A multi-stage review process for checking directories of agent skills for completeness, clarity, correct triggers, security, and consistency.

In plain words
What is it for?
Use it to audit a skills directory before publishing, packaging, distributing, or improving a collection of agent instructions.
Why use it?
It finds skills that are incomplete, confusing, triggered at the wrong times, unsafe, redundant, or poorly connected to other skills.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to audit a skills directory before publishing, packaging, distributing, or improving a collection of agent instructions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/neverinfamous/memory-journal-mcp/adversarial-skill-audit
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 neverinfamous/memory-journal-mcp --skill adversarial-skill-audit
Clone the repo
git clone --depth 1 https://github.com/neverinfamous/memory-journal-mcp

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-skill-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/neverinfamous/memory-journal-mcp/adversarial-skill-audit/github.svg)](https://agentmods.dev/skills/neverinfamous/memory-journal-mcp/adversarial-skill-audit)
Your own site
<a href="https://agentmods.dev/skills/neverinfamous/memory-journal-mcp/adversarial-skill-audit"><img src="https://agentmods.dev/badge/skills/neverinfamous/memory-journal-mcp/adversarial-skill-audit/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-skill-audit

Your own site · 80×15
<a href="https://agentmods.dev/skills/neverinfamous/memory-journal-mcp/adversarial-skill-audit"><img src="https://agentmods.dev/badge/skills/neverinfamous/memory-journal-mcp/adversarial-skill-audit.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 1,115 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 $0.01115
Opus 5 $0.00025 $0.00558
Sonnet 5 $0.00010 $0.00223
Haiku 4.5 $0.00005 $0.00112

Measured 9d ago against content hash bf664d8addc9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

adversarial-skill-audit 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 9d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/check-skills.ps1, scripts/run-copilot.ps1), 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.

skills/adversarial-skill-audit/SKILL.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Adversarial Skill Audit

A multi-pass quality auditing system for agent skill directories. Evaluates each skill against the skill-builder quality standards through structured profiling and adversarial stress-testing — finding gaps in trigger coverage, instruction clarity, progressive disclosure, security, and cross-skill coherence.

When to Load

Load this skill when any of these apply:

  • Auditing an entire skills directory for quality and consistency
  • Reviewing a batch of skills before publishing or distributing
  • The user asks for skill quality review, audit, or improvement suggestions
  • The user says "audit my skills", "skill quality check", "review these skills", "check my skills", "how good are my skills", or "validate these skills"
  • Preparing a skills directory for npm packaging or distribution
  • You want to identify redundant, incomplete, or poorly triggered skills

Adversarial Protocol

This skill follows the standard dual-agent adversarial pattern (Agent A: The Evaluator, Agent B: The Adversarial User). For the core pipeline rules, phase definitions, and agent switching protocols, read: ../adversarial-security/references/adversarial-base-protocol.md

For the skill audit-specific protocol with scoring and templates, read: references/multi-pass-skill-protocol.md

Audit Categories

The 8 quality categories evaluated per skill:

  1. Frontmatter & Triggering
  2. Instruction Clarity
  3. Structure & Progressive Disclosure
  4. Output Formats & Templates
  5. Edge Cases & Error Handling
  6. Security & Safety
  7. Token Efficiency
  8. Maintenance & Versioning

Additionally, 4 directory-level categories assess the collection:

  1. Cross-Skill Coherence
  2. Trigger Collision Detection
  3. Coverage Gap Analysis
  4. Ecosystem Consistency

For the full checklist, read references/audit-categories.md.

External Validation (Phase 4)

Read the full file on GitHub · 119 lines

Files

What ships with it

7 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. 9d ago First seen · 119 lines · 50 tokens per session scan A bf664d8addc9

Subscribe to this mod's changes

adversarial-skill-audit is a skill published in the GitHub repository neverinfamous/memory-journal-mcp (20 stars, last pushed 1mo ago), licensed MIT. It adds 50 tokens to every session and 1,115 once invoked, about $0.0003 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 2026-08-30.

Related

Other skills, from other repositories

tech-writing

Write professional technical documents — requirements/PRD, tech spec/design doc, low-level design, decision records, and trade-off analysis — at a formality tier matched to the task. Grounds every claim in real code or a cited source, marks what it could not verify, and refuses to pad. Use when asked to write/update a…

nguyenthienthanh/aura-frog · 88 tokens

plan-orchestrator

Route hierarchical-planning intents to the correct backing script. Use when the user invokes /aura-frog:plan (with or without subcommand), mentions plan verbs (expand/next/replan/promote/archive/freeze/thaw/undo/status/conflicts), or types a plan-vocabulary bare word with .claude/plans/active.json present. Owns verb…

nguyenthienthanh/aura-frog · 91 tokens

context-end

Close a workspace session by reviewing a proposed summary, recording approved outcomes, updating state and decisions, and checking repository safety. Use only when the user explicitly asks to end, close, or hand off the current session.

conorbronsdon/agent-context-os · 46 tokens

context-setup

Build, import, or refresh this workspace's identity, project, reusable-workflow, and weekly-state files through a guided review. Use only when the user explicitly asks to initialize or redo workspace context.

conorbronsdon/agent-context-os · 44 tokens

context-start

Load this workspace's current state, recent decisions, blockers, priorities, and session continuity, then give a concise briefing. Use only when the user explicitly asks to begin or resume a workspace session.

conorbronsdon/agent-context-os · 42 tokens

perf-profiling

Systematic performance profiling and optimization across frontend (Core Web Vitals, code splitting, lazy loading), backend (N+1 queries, async), and database (EXPLAIN ANALYZE, indexing) layers. Use when the user reports slow code, latency, memory leaks, needs to benchmark, or wants to speed up an application. Measure…

nguyenthienthanh/aura-frog · 107 tokens