se-skills: Command for Claude Code

.claude/commands/se-review.md

se-review is a command for Claude Code from ddddjaak/se-skills. It costs 38 tokens per session (230 once invoked), scanned A, original, MIT.

A command for an adversarial design review of a systems-engineering artifact. It uses separate hardware, software, test, and whole-system perspectives to look for gaps, inconsistencies, and unstated assumptions.

In plain words
What is it for?
Use it to review requirements, architecture, or specifications and produce categorized findings, cross-team tensions, and tracked resolutions.
Why use it?
Independent reviews expose problems that a single team or author may overlook, especially where departments depend on one another.

Command for Claude Code

Written for Claude Code: installed under .claude/.

This is ddddjaak/se-skills's own configuration. It tells Claude Code how to work on se-skills itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything se-skills configures →

Part of the se-skills plugin — 16 skills, 6 commands, 5 agents, 1 hook, 3 MCP servers shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to ddddjaak/se-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/ddddjaak/se-skills/main/.claude/commands/se-review.md
Clone the repo
git clone --depth 1 https://github.com/ddddjaak/se-skills

Made for: Claude Code.

Or install se-skills, the plugin that ships this one along with the rest of its 16 skills, 6 commands, 5 agents, 1 hook, 3 MCP servers.

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 se-review

README.md
[![agentmods](https://agentmods.dev/badge/commands/ddddjaak/se-skills/se-review/github.svg)](https://agentmods.dev/commands/ddddjaak/se-skills/se-review)
Your own site
<a href="https://agentmods.dev/commands/ddddjaak/se-skills/se-review"><img src="https://agentmods.dev/badge/commands/ddddjaak/se-skills/se-review/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.

agentmods 80×15 button for se-review

Your own site · 80×15
<a href="https://agentmods.dev/commands/ddddjaak/se-skills/se-review"><img src="https://agentmods.dev/badge/commands/ddddjaak/se-skills/se-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 230 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00038 $0.00230
Opus 5 $0.00019 $0.00115
Sonnet 5 $0.00008 $0.00046
Haiku 4.5 $0.00004 $0.00023

Measured 9d ago against content hash 6e68c430f90e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

se-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 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.

.claude/commands/se-review.md · 14 lines

What it actually says

Invoke the se-skills:design-review skill.

Work through the four-step process:

  1. SCOPE — confirm the artifact to review, review depth (quick scan / standard / exhaustive), focus areas, and which lenses to use
  2. LENS-REVIEW — spawn four parallel adversarial reviewers (HW, SW, Test, System), each receiving ONLY the artifact with a department-specific "find issues" prompt. Reviewers do not see each other's output
  3. RECONCILE — classify every finding using precedence: artifact misread → actionable → trade-off → noise. Surface cross-lens tensions (where two lenses disagree with each other) — these are the highest-value outputs
  4. REPORT — produce structured review report with actionable findings, trade-off findings, cross-lens tensions, and resolution tracking table

Save the output to docs/reviews/[project]-[artifact]-review-[YYYY-MM-DD].md.

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. 9d ago First seen · 14 lines · 38 tokens per session scan A 6e68c430f90e

Subscribe to this mod's changes

se-review is a command published in the GitHub repository ddddjaak/se-skills (4 stars, last pushed 1mo ago), licensed MIT. It adds 38 tokens to every session and 230 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.