security-review

security-review is a command for coding agents from fockus/skill-memory-bank. It costs 13 tokens per session (1,157 once invoked), scanned A, original, MIT.

A code security review command that checks for common vulnerabilities, exposed secrets, and unsafe dependencies across several programming languages.

In plain words
What is it for?
Use it to review changed files or a chosen module in Go, Python, JavaScript or TypeScript, Rust, Java, or Kotlin projects.
Why use it?
It helps find security problems in changed code or a selected part of a project before they reach users.

Command

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/fockus/skill-memory-bank/security-review
Clone the repo
git clone --depth 1 https://github.com/fockus/skill-memory-bank

Wrote 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.

agentmods badge for security-review

README.md
[![agentmods](https://agentmods.dev/badge/commands/fockus/skill-memory-bank/security-review.svg)](https://agentmods.dev/commands/fockus/skill-memory-bank/security-review)
Your own site
<a href="https://agentmods.dev/commands/fockus/skill-memory-bank/security-review"><img src="https://agentmods.dev/badge/commands/fockus/skill-memory-bank/security-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,157 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 $0.00013 $0.01157
Opus 5 $0.00006 $0.00579
Sonnet 5 $0.00003 $0.00231
Haiku 4.5 $0.00001 $0.00116

Measured 5d ago against content hash b56dd945ea2d, 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 5d 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.

commands/security-review.md · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security Review: $ARGUMENTS

0. Scope

  • If $ARGUMENTS is provided, analyze the specified module / directory.
  • If empty, analyze changed files from git diff --name-only + git diff --staged --name-only.

1. Stack detection

eval "$(bash ~/.claude/skills/memory-bank/scripts/mb-metrics.sh)"
# Exposes: stack, test_cmd, lint_cmd, src_count

If stack=unknown, ask the user which stack(s) to scan before proceeding. Do not assume.

2. Automated analysis per stack

Run the scanners that match $stack. For multi, run each applicable set. All tools are optional — skip with a warning if a binary is missing.

Go

gosec -quiet ./... 2>/dev/null
golangci-lint run --enable=gosec,errcheck,govet 2>/dev/null
govulncheck ./... 2>/dev/null

Python

bandit -r . -f txt -ll 2>/dev/null
pip-audit 2>/dev/null || safety check 2>/dev/null

Node.js / TypeScript

npm audit 2>/dev/null || pnpm audit 2>/dev/null || yarn audit 2>/dev/null
npx eslint-plugin-security . 2>/dev/null

Rust

cargo audit 2>/dev/null
cargo clippy -- -W clippy::suspicious 2>/dev/null

Java / Kotlin

# Prefer trivy for fast filesystem scan
trivy fs . --scanners vuln,misconfig,secret 2>/dev/null
# Or OWASP dependency-check if configured
dependency-check --project "$(basename $PWD)" --scan . 2>/dev/null

Ruby

brakeman --quiet 2>/dev/null
bundle-audit check --update 2>/dev/null

.NET

dotnet list package --vulnerable --include-transitive 2>/dev/null

Secret scanning (stack-agnostic)

Prefer trufflehog or gitleaks when installed — they understand entropy, known-key shapes, and git history. Fall back to grep only if neither is available.

# Preferred:
trufflehog filesystem --no-verification --only-verified=false . 2>/dev/null
gitleaks detect --no-banner 2>/dev/null

# Fallback grep (less accurate):
grep -rn --include="*.go" --include="*.py" --include="*.js" --include="*.ts" \
  --include="*.rs" --include="*.java" --include="*.kt" --include="*.rb" \
  --include="*.cs" --include="*.yaml" --include="*.yml" --include="*.env*" \
  -E "(password|secret|api_key|token|AKIA[0-9A-Z]{16}|ghp_[a-zA-Z0-9]{36}|sk_live_|sk-ant-)" .

Read the full file on GitHub · 140 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. 5d ago First seen · 140 lines · 13 tokens per session scan A b56dd945ea2d

Subscribe to this mod's changes

security-review is a command published in the GitHub repository fockus/skill-memory-bank (25 stars, last pushed 1mo ago), licensed MIT. It adds 13 tokens to every session and 1,157 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 2026-08-30.