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 skills add MintedKenny/skills --skill audit-branchgit clone --depth 1 https://github.com/MintedKenny/skillsWrote 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.
[](https://agentmods.dev/skills/mintedkenny/skills/audit-branch)<a href="https://agentmods.dev/skills/mintedkenny/skills/audit-branch"><img src="https://agentmods.dev/badge/skills/mintedkenny/skills/audit-branch/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.
<a href="https://agentmods.dev/skills/mintedkenny/skills/audit-branch"><img src="https://agentmods.dev/badge/skills/mintedkenny/skills/audit-branch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00034 | $0.01106 |
| Opus 5 | $0.00017 | $0.00553 |
| Sonnet 5 | $0.00007 | $0.00221 |
| Haiku 4.5 | $0.00003 | $0.00111 |
Grade A, and why
audit-branch 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.
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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit the branch
Critically review what's been changed and decide: are these changes good, and is anything missing?
Before evaluating, read references/audit-posture.md.
Scope
- Get the diff with the host's diff tool. If none is available, use
git diff --stat origin/main...first, then inspect focused file diffs withgit diff origin/main... -- <path>. - Audit uncommitted (or branch-local) changes only unless told otherwise. Don't re-audit work already on the base branch.
- Match the project's compatibility stance — don't flag backwards-incompatibility the project doesn't require (e.g. a pre-release schema that resets freely).
Evaluate (the diff as a whole, and each change)
- Root cause vs bandaid — fix or papering over? Shortcuts taken?
- Design direction — does the branch move the codebase toward the product and architecture direction you want, and would you build it this way from scratch today?
- Architectural economy — first identify the best greenfield long-term shape, then ask whether any layer, branch, API, helper, or defensive check can be deleted, inlined, moved, narrowed, or reused without making that design worse. Simplicity is subordinate to correctness and greenfield fit; never choose a smaller shape that is less right.
- Code placement & ownership — does each change live at the right layer/module, or does it smear responsibility across routes, hooks, libraries, schemas, or UI?
- Complexity & blast radius — overcomplicated? unintended downstream effects?
- Duplication & abstraction — redundant code, unnecessary layers, premature generalization?
- Pattern coherence — fighting existing patterns, introducing competing ones, leaving stale ones in place?
- Surface area & defense calibration — attack surface bloat, expanded public API, missing guardrails, or defense-in-depth that adds ceremony without a real threat model?
- Gaps — tests, DI consistency, portability assumptions (don't over-index on tests).
- Missing pieces — what should be in this change but isn't?
What ships with it
2 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.
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.
- 9d ago First seen · 72 lines · 34 tokens per session scan A 2220bb01a04a
audit-branch is a skill published in the GitHub repository MintedKenny/skills (2 stars, last pushed 3mo ago), licensed MIT. It adds 34 tokens to every session and 1,106 once invoked, about $0.0002 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
review-implement-phase
Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.
engram-branch-pr
PR creation workflow for Engram following the issue-first enforcement system. Trigger: When creating a pull request, opening a PR, or preparing changes for review.
verify-behavior
Verify or reproduce visible product behavior by driving the real UI with pi-computer-use's checked tools, requiring verified expect postconditions and durable state evidence for meaningful UI flows. Use when triage needs visual reproduction, implementation needs behavioral proof, review needs interactive confirmation…
github-contributor
End-to-end playbook for shipping high-quality pull requests to open-source projects you don't maintain — discovery, CONTRIBUTING compliance, PR-size check, minimal-diff implementation, PR description with AI-assisted disclosure, conflict resolution, and post-submission maintainer interaction. Use whenever creating…
revdiff
Review diffs, files, and documents with inline annotations in a TUI overlay, or answer questions about revdiff usage, configuration, themes, and keybindings. Opens revdiff in agterm/tmux/zellij/herdr/kitty/wezterm/cmux/ghostty/iterm2/emacs-vterm, captures annotations, and addresses them. Works in git, hg, and jj repos…
write-pr
Reference standards for writing pull request titles and descriptions in the tldraw repository, plus the pre-flight comment sweep over the diff. Use as supporting guidance when another skill or workflow needs PR content standards, not as the user-facing create/update PR workflow.