Borrowing it
Nothing to install: this file belongs to DIGI-UW/OpenELIS-Global-2. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/DIGI-UW/OpenELIS-Global-2/develop/.specify/oe/commands/audit-branch.mdgit clone --depth 1 https://github.com/DIGI-UW/OpenELIS-Global-2Wrote 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/commands/digi-uw/openelis-global-2/audit-branch)<a href="https://agentmods.dev/commands/digi-uw/openelis-global-2/audit-branch"><img src="https://agentmods.dev/badge/commands/digi-uw/openelis-global-2/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/commands/digi-uw/openelis-global-2/audit-branch"><img src="https://agentmods.dev/badge/commands/digi-uw/openelis-global-2/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 | $0.00000 | $0.04359 |
| Opus 5 | $0.00000 | $0.02180 |
| Sonnet 5 | $0.00000 | $0.00872 |
| Haiku 4.5 | $0.00000 | $0.00436 |
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 10d 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 — 304 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit Branch
When the user invokes /audit-branch (optionally with arguments), perform a
tiered audit of the current branch diff against its PR target (or develop),
identifying LLM-assisted development artifacts, code quality issues, and
constitution violations.
This command produces a structured report with findings grouped by severity and detection tier. It is designed to run before PR submission to catch patterns that traditional linters miss — verbose comments, debug remnants, placeholder code, leaked task references, and architectural violations.
Key capabilities:
- Tier 1 (Mechanical): Regex-based pattern matching against added lines in the diff — fast, tuned for low false positives; findings still require quick human review
- Tier 2 (Heuristic): Structural analysis requiring context — comment-to-code adjacency, import usage, scope relevance
- Tier 3 (Semantic): LLM reasoning over diff chunks with constitution rules
as context — deepest analysis, opt-in via
--deep - Auto-fix: Optional per-category fix for mechanical (Tier 1) findings with user confirmation
- CI-ready: Exit codes and severity thresholds for pipeline integration
User Input
$ARGUMENTS
Interpret arguments best-effort. Support these patterns:
/audit-branch→ Full Tier 1+2 audit of current branch vs PR target/audit-branch --deep→ Include Tier 3 semantic analysis/audit-branch --tier 1→ Mechanical scan only (fastest)/audit-branch --fix→ After report, offer to auto-fix Tier 1 findings/audit-branch --threshold {CRITICAL|HIGH|MEDIUM|LOW}→ Set minimum severity for exit code failure (default: HIGH)/audit-branch --since <ref>→ Audit only changes since a specific ref (narrows diff scope, but full-branch is recommended)
Flags can be combined: /audit-branch --deep --fix --threshold MEDIUM
If any inputs are unclear, ask a single concise question and continue with safe defaults.
Safety Rules (non-negotiable)
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 304 lines · 0 tokens per session scan A 10f2426e7305
audit-branch is a command published in the GitHub repository DIGI-UW/OpenELIS-Global-2 (251 stars, last pushed yesterday), licensed MPL-2.0. It costs nothing until one of its globs matches a file; then it loads 4,359 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
devkit.github.review-pr
Provides comprehensive GitHub pull request review with code quality, security, and best practices analysis. Use when reviewing a PR before merging.
speckit.spex.submit
Push and create PR for team review, with optional watch mode for CI monitoring.
git
The pre-finish status: branch, hygiene findings, message checks, workflow lint, template state.
merge-conflict-analysis
You are analyzing merge conflicts for PR #${{ pr-number }}.
code-review
Code review for branch changes. Analyzes git diff between branches with multi-level depth (low/medium/high). Matches changes against task description. Returns structured report with severity levels and verdict.
repo-audit
Audit a codebase (local or remote GitHub/GitLab) against architecture principles and requirements, surfacing drift, risk, and missing decisions.