security-review

A command for reviewing the repository’s recent changes for security issues by comparing them with the remote default branch. A remote is a configured copy of the repository hosted elsewhere.

In plain words
What is it for?
Use it to check changed code for security risks after confirming the project is a Git repository with an origin remote and a usable default branch.
Why use it?
Its preflight checks explain setup problems, such as a missing Git repository or origin remote, before the security review runs.

Command for Claude Code

Install

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.

agentmods
npx agentmods add commands/codeverbojan/claude-code-kickstart/security-review
Clone the repo
git clone --depth 1 https://github.com/codeverbojan/claude-code-kickstart

Made for: Claude Code.

Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 791 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00018 $0.00791
Opus 5 $0.00009 $0.00396
Sonnet 5 $0.00004 $0.00158
Haiku 4.5 $0.00002 $0.00079

Measured 2d ago against content hash 74e5b18afad7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

security-review 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.

.claude/commands/security-review.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security Review

Audits the diff between the working tree and the remote default branch (origin/HEAD) for security issues. Wraps the built-in review with preflight checks that fail loudly and explain how to fix common setup problems — instead of bubbling up cryptic git errors.

1. Preflight — verify git state

Run these checks in order. If any fails, STOP and print the matching "Fix" block to the user verbatim. Do not proceed until the user has fixed the issue.

Check A — is this a git repo?

git rev-parse --is-inside-work-tree

If it fails:

Not a git repository. /security-review diffs against a remote branch, so it needs a git repo. Either cd into a repo, or run git init && git remote add origin <url> first.

Check B — does the repo have a remote named origin?

git remote get-url origin

If it fails:

No origin remote. /security-review diffs against origin/HEAD, which requires a remote. Add one with:

git remote add origin <your-repo-url>
git fetch origin
git remote set-head origin --auto

If this repo intentionally has no remote, run a full-tree audit instead by invoking the security-reviewer agent directly.

Check C — is refs/remotes/origin/HEAD set?

git symbolic-ref refs/remotes/origin/HEAD

If it fails with "is not a symbolic ref":

origin/HEAD is not set on this repo. This is the most common cause of /security-review failures and happens on repos that weren't freshly cloned. Fix it with one command:

git remote set-head origin --auto

This is a local-only, non-destructive bookkeeping change. It asks the remote which branch is default and points the local ref at it. Reverse with git remote set-head origin --delete if needed.

If --auto fails (remote unreachable, or remote has no default branch), set it explicitly:

git remote set-head origin main   # or master, develop, etc.

Read the full file on GitHub · 111 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. 2d ago First seen · 111 lines · 18 tokens per session scan A 74e5b18afad7

Subscribe to this mod's changes

security-review is a command published in the GitHub repository codeverbojan/claude-code-kickstart (2 stars, last pushed 4mo ago), licensed MIT. It adds 18 tokens to every session and 791 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.