SubFrame: Skill for Claude Code

.agents/skills/sub-audit/SKILL.md

sub-audit is a skill for Claude Code from Codename-11/SubFrame. It costs 29 tokens per session (687 once invoked), scanned A, original, MIT.

A code-review and documentation-audit skill for recent project changes. It examines changed files for implementation problems, missing documentation, edge cases, and type-safety issues.

In plain words
What is it for?
It is for auditing changes across areas such as backend, frontend, shared code, and configuration. The review covers issues including null values, race conditions, error handling, loose types, platform differences, and security risks.
Why use it?
It provides a focused review of new work without requiring a review of the entire codebase. It can expose bugs or missing updates before the changes are treated as finished.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions subagents; installed under .agents/ (shared by several agents); mentions AGENTS.md.

This is Codename-11/SubFrame's own configuration. It tells Claude Code how to work on SubFrame 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 SubFrame configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Codename-11/SubFrame. 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/Codename-11/SubFrame/main/.agents/skills/sub-audit/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Codename-11/SubFrame

Made for: Claude Code.

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 sub-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/codename-11/subframe/sub-audit/github.svg)](https://agentmods.dev/skills/codename-11/subframe/sub-audit)
Your own site
<a href="https://agentmods.dev/skills/codename-11/subframe/sub-audit"><img src="https://agentmods.dev/badge/skills/codename-11/subframe/sub-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 sub-audit

Your own site · 80×15
<a href="https://agentmods.dev/skills/codename-11/subframe/sub-audit"><img src="https://agentmods.dev/badge/skills/codename-11/subframe/sub-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 687 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00029 $0.00687
Opus 5.5 $0.00012 $0.00275
Sonnet 5.5 $0.00006 $0.00137
Haiku 4.5 $0.00003 $0.00069

Measured 1mo ago against content hash 25dfe92b14ac, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

sub-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 1mo ago.

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/sub-audit/SKILL.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SubFrame Audit

Run a thorough audit on recent changes, combining code review and documentation checks.

Dynamic Context

Recent commits (last 15): !git log --oneline --no-decorate -15 2>/dev/null || echo "No git history"

Files changed vs main: !git diff --name-only main...HEAD 2>/dev/null | head -40

Instructions

Argument: $ARGUMENTS

The argument should describe the scope to audit. If empty, audit all changes since the last merge to main.

Phase 1: Identify Scope

Determine which files to audit:

  • If argument specifies a feature/scope, identify the relevant files
  • If empty, use git diff --name-only main...HEAD to find all changed files
  • Group files by layer (e.g., backend, frontend, shared, config, tests)

Phase 2: Code Review (spawn agent)

Spawn a code review agent (feature-dev:code-reviewer subagent type) to review the changed files. The agent should check for:

  1. Critical bugs — null/undefined access, race conditions, unhandled errors, infinite loops
  2. Type safety — as any casts, missing type imports, loose typing where strict types exist
  3. Platform issues — Windows path handling, file system edge cases
  4. Security — command injection, XSS in rendered content, path traversal
  5. Logic errors — off-by-one, incorrect conditions, missing edge cases

Phase 3: Documentation Audit (spawn agent)

Spawn an explore agent (Explore subagent type) to check documentation completeness:

  1. AGENTS.md — Are all modules/components listed?
  2. changelog.md — Does [Unreleased] reflect all new features?
  3. PROJECT_NOTES.md — Are architecture decisions documented?
  4. STRUCTURE.json — Is it up to date? (compare module count with actual files)

Phase 4: Report

Present findings in this format:

## Audit Report

### Critical Issues (must fix)
1. [FILE:LINE] Description — severity, impact

### Important Issues (should fix)
1. [FILE:LINE] Description — severity, impact

### Documentation Gaps
1. [FILE] What's missing

### Suggestions (nice to have)
1. Description

Read the full file on GitHub · 85 lines

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. 1mo ago First seen · 85 lines · 29 tokens per session scan A 25dfe92b14ac

Subscribe to this mod's changes

sub-audit is a skill published in the GitHub repository Codename-11/SubFrame (10 stars, last pushed yesterday), licensed MIT. It adds 29 tokens to every session and 687 once invoked, about $0.0001 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 2026-08-31.

Related

Other skills, from other repositories

refactoring-csharp

Rename and refactor C# symbols in a .NET solution or multi-solution monorepo with a one-shot Roslyn CLI. Use when the user asks to rename a symbol, preview impact, update references across a solution, or refactor shared projects across several solutions.

CodeAlive-AI/ai-driven-development · 60 tokens

agentic-readiness

Audit and improve repositories for reliable agentic work across Codex and Codex App, Claude Code, and OpenCode. Use when reviewing AGENTS.md or CLAUDE.md quality and discovery, instruction routing in monorepos or meta-repos, agent settings, MCP configuration, skills, subagents, context budgets, or repository…

CodeAlive-AI/ai-driven-development · 76 tokens

code-that-fits-in-your-head

Software-engineering heuristics based on Mark Seemann's Code That Fits in Your Head (2021), updated for agent-driven development. Use when writing or reviewing code, refactoring accidental complexity or a Big Ball of Mud, controlling technical or architectural debt in generated code, designing APIs and invariants…

CodeAlive-AI/ai-driven-development · 169 tokens

code-review

Use when reviewing code for bugs, security issues, performance problems, or adherence to best practices. Provides structured code review with severity levels and actionable feedback.

peintune/runjam · 33 tokens

intuitive-shape

Shape unsettled product ideas into bounded bets before planning; excludes settled fixes and approved execution.

MiaoDX/intuitive-flow · 23 tokens

intuitive-doc

Maintain README.md, ARCHITECTURE.md, STATUS.md, and docs/human/ when they drift or need cleanup.

MiaoDX/intuitive-flow · 29 tokens