cursor-session-tracer: Command for Claude Code

.cursor/commands/design-review.md

design-review is a command for Claude Code, Cursor from indranildchandra/cursor-session-tracer. It costs 0 tokens per session (1,264 once invoked), scanned A, original, MIT.

A command for running a structured design review with several independent reviewer roles, then recording the conclusions in an ADR, a document that explains an architecture decision. It selects a limited set of reviewers and connects the decision record to later implementation tracing.

In plain words
What is it for?
Use it to review simple, medium, or complex technical designs, consider security and cost concerns, and create an ADR in docs/adr/.
Why use it?
It exposes design risks from different viewpoints and leaves a written plan that can be compared with what was later implemented.

Command for Claude CodeCursor

Written for Cursor and Claude Code: installed under .cursor/, but also a Claude Code command (commands/*.md).

This is indranildchandra/cursor-session-tracer's own configuration. It tells Claude Code and Cursor how to work on cursor-session-tracer 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 cursor-session-tracer configures →

Reuse

Borrowing it

Nothing to install: this file belongs to indranildchandra/cursor-session-tracer. 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/indranildchandra/cursor-session-tracer/main/.cursor/commands/design-review.md
Clone the repo
git clone --depth 1 https://github.com/indranildchandra/cursor-session-tracer

Made for: Claude Code, Cursor.

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 design-review

README.md
[![agentmods](https://agentmods.dev/badge/commands/indranildchandra/cursor-session-tracer/design-review.svg)](https://agentmods.dev/commands/indranildchandra/cursor-session-tracer/design-review)
Your own site
<a href="https://agentmods.dev/commands/indranildchandra/cursor-session-tracer/design-review"><img src="https://agentmods.dev/badge/commands/indranildchandra/cursor-session-tracer/design-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,264 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 $0.00000 $0.01264
Opus 5 $0.00000 $0.00632
Sonnet 5 $0.00000 $0.00253
Haiku 4.5 $0.00000 $0.00126

Measured 7d ago against content hash 510b95b5ef0d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

design-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 7d 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.

.cursor/commands/design-review.md · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/design-review — Adversarial Review Council → ADR

Run a multi-persona adversarial design review, then distil the outcome into an ADR in docs/adr/. This is the planning half of the plan-vs-path model: the ADR is the plan; a later cursor-session-tracer trace (linked by adr_id) is the path; audit_trace.py checks the path stayed faithful to the plan.

Personas live in .cursor/review-council/standard-personas/ (20+ files) and .cursor/review-council/user-generated-personas/. Load only the 3–6 you select — never all of them.


Token budget — read this first

  • In Phase 2 you select 3–6 personas. Read only those files.
  • Each persona review runs in isolation — give it only its persona file + the domain profile + the scope brief. It must not see other personas' output.
  • Keep each persona's returned assessment to ~300 words. If you're loading more than 6 persona files, reduce the council.

Council size by complexity: simple → 3 · medium → 4–5 · complex → 5–6. Always include at least one of: staff-engineer, cloud-cost-architect, appsec-architect (cost and security must always have a voice).


Phase 0 — Scope + early human input

  1. If this command was invoked with a scope argument, use it. Otherwise scan the repo for the highest-risk or most recently changed area and propose it.
  2. Ask the human: Is this the right scope? What worries you most? Any constraints (deadline, regulatory, perf/cost budget)? Any personas to add or drop?
  3. Record the answers verbatim as the Phase 0 Human Brief.

Phase 1 — Domain fingerprint

Analyse the scoped code/design and produce (~200 words): tech stack, patterns, top 2–3 risk areas, scale characteristics, and a complexity rating (simple | medium | complex).

Phase 2 — Persona selection

From the domain profile + Phase 0 brief, pick 3–6 personas from .cursor/review-council/standard-personas/. Read only those files. Ensure at least one of staff-engineer / cloud-cost-architect / appsec-architect. Show the lineup to the human and confirm.

Read the full file on GitHub · 113 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. 7d ago First seen · 113 lines · 0 tokens per session scan A 510b95b5ef0d

Subscribe to this mod's changes

design-review is a command published in the GitHub repository indranildchandra/cursor-session-tracer (11 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,264 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.