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.
git clone --depth 1 https://github.com/sembraniteam/claude-pluginsWrote 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/sembraniteam/claude-plugins/audit-diff)<a href="https://agentmods.dev/commands/sembraniteam/claude-plugins/audit-diff"><img src="https://agentmods.dev/badge/commands/sembraniteam/claude-plugins/audit-diff/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/sembraniteam/claude-plugins/audit-diff"><img src="https://agentmods.dev/badge/commands/sembraniteam/claude-plugins/audit-diff.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 | $0.00046 | $0.01195 |
| Opus 5.5 | $0.00018 | $0.00478 |
| Sonnet 5.5 | $0.00009 | $0.00239 |
| Haiku 4.5 | $0.00005 | $0.00120 |
Grade A, and why
audit-diff 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.
How it starts
The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are running a diff-scoped security audit using the security-auditor plugin. This is the recommended way to audit a pull request, and the recommended fallback whenever a full /audit would need to read more source than fits in context — scoping to the diff solves both problems at once.
Step 1 — Parse arguments
$ARGUMENTS may contain, in any order:
- A mode hint:
dev/developmentorprod/production - A git ref (branch, tag, or commit) to diff against
Any remaining token that isn't a recognized mode keyword is treated as the base ref. If no mode is given, ask the same question /audit asks:
"Is this project currently in development or production?"
Step 2 — Resolve the base ref and list changed files
If a base ref was given, use it directly. Otherwise detect the repo's default branch:
git symbolic-ref refs/remotes/origin/HEAD 2>/dev/null | sed 's@^refs/remotes/origin/@@'
# falls back to checking for a local `main` then `master` branch if the above is empty
Then collect the changed file set as the union of:
git diff --name-only --diff-filter=ACMR <base>...HEAD # committed changes vs merge-base
git diff --name-only --diff-filter=ACMR HEAD # unstaged working-tree changes
git diff --name-only --diff-filter=ACMR --staged # staged changes
--diff-filter=ACMR keeps added/copied/modified/renamed files and drops deleted files (nothing to audit in a file that no longer exists). Deduplicate the combined list.
If this is not a git repository, has no commits, or the combined list is empty, say so plainly and stop:
"No git changes found against
<base>. Run/auditfor a full codebase scan instead."
Step 3 — Filter the changed set
Drop paths matching common generated/vendored directories before analysis: node_modules/, dist/, build/, vendor/, .venv/, target/, *.min.js, lockfiles that aren't being read for dependency scanning in Step 5, and any path Glob confirms doesn't exist (renamed/moved after the diff was taken).
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.
- 1mo ago First seen · 76 lines · 46 tokens per session scan A d624d7f22c2d
audit-diff is a command published in the GitHub repository sembraniteam/claude-plugins (2 stars, last pushed 2mo ago), licensed MIT. It adds 46 tokens to every session and 1,195 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
refactor
Systematic code refactoring with smart scope detection.
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
init
Install the formatters this repository needs, with every command visible before it runs.
spec-trace-requirements
You are verifying that implementation changes trace back to specification requirements.
merge-conflict-analysis
You are analyzing merge conflicts for PR #${{ pr-number }}.
boot
Start a new PromptKit prompt assembly session (alias for /bootstrap).