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.
npx agentmods add skills/codename-11/subframe/sub-auditnpx skills add Codename-11/SubFrame --skill sub-auditgit clone --depth 1 https://github.com/Codename-11/SubFrameWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00029 | $0.00687 |
| Opus 5 | $0.00015 | $0.00344 |
| Sonnet 5 | $0.00006 | $0.00137 |
| Haiku 4.5 | $0.00003 | $0.00069 |
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 2d 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.
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...HEADto 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:
- Critical bugs — null/undefined access, race conditions, unhandled errors, infinite loops
- Type safety —
as anycasts, missing type imports, loose typing where strict types exist - Platform issues — Windows path handling, file system edge cases
- Security — command injection, XSS in rendered content, path traversal
- 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:
- AGENTS.md — Are all modules/components listed?
- changelog.md — Does [Unreleased] reflect all new features?
- PROJECT_NOTES.md — Are architecture decisions documented?
- 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
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.
- 2d ago First seen · 85 lines · 29 tokens per session scan A 25dfe92b14ac
sub-audit is a skill published in the GitHub repository Codename-11/SubFrame (10 stars, last pushed 8d ago), licensed MIT. It adds 29 tokens to every session and 687 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.
Other skills, from other repositories
intuitive-tests
Use this skill whenever the user asks about unit test best practices, test organization, flat test suites, redundant tests, test refactors, pytest/JUnit/Jest/xUnit layout, test taxonomy, flaky tests, coverage quality, fixtures, mocks, parametrization, pruning existing UTs, or "which tests are worth keeping." It…
intuitive-flow
Stable execution/change router after an approved plan, preflight contract, or tiny concrete task. Refactor-shaped work delegates to intuitive-refactor, and durable work runs through staged planning, review, GSD handoff, implementation, cleanup, and verification while keeping plan ledgers and active capsules compact by…
intuitive-preflight
Turn a vague task, plan, issue, or "LGTM/go ahead" request into an approval-ready preflight contract before implementation starts. Use when the user wants prompt preflight, clearer scope, non-goals, context package, acceptance criteria, definition of done, verification, stop gates, the exact execution command, or…
intuitive-squash
Squash local GSD or agent-generated commit history into a clean, reviewable story while preserving important fixes. Use when the user asks to squash commits, clean git history, compress phase commits, prepare a branch before PR, compare aggressive vs moderate squash options, or preserve hotfix/security commits during…
multica-goal-tracker
Track goal-driven Multica issues. Use when a user creates or maintains Multica issues by pasting a /goal prompt, wants Codex to summarize that goal into a concise issue purpose, append a normalized goal-start comment, record completion evidence from real Multica execution run messages or a supplied session transcript…
cross-review
Challenge an existing agent proposal through a small bounded set of independent review perspectives, then judge the findings into one simpler or more defensible recommendation. Use immediately after an agent proposes a solution when the user asks whether there is a simpler approach, wants a second opinion or other…