trace-first-starter: Command for Claude Code

.claude/commands/tfw-review.md

tfw-review is a command for Claude Code from saubakirov/trace-first-starter. It costs 18 tokens per session (3,338 once invoked), scanned A, original, MIT.

A tightly controlled review workflow for checking a completed implementation against its requirements and task specification. It produces a review file and may record technical debt, meaning known work that should be addressed later.

In plain words
What is it for?
Use it to verify a completed task, load the project's required context, document findings, accept or reject the work, and update technical-debt records when allowed.
Why use it?
It separates review from implementation so the reviewer cannot quietly change the code or rewrite the requirements while judging the result.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions AGENTS.md.

This is saubakirov/trace-first-starter's own configuration. It tells Claude Code how to work on trace-first-starter 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 trace-first-starter configures →

Reuse

Borrowing it

Nothing to install: this file belongs to saubakirov/trace-first-starter. 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/saubakirov/trace-first-starter/master/.claude/commands/tfw-review.md
Clone the repo
git clone --depth 1 https://github.com/saubakirov/trace-first-starter

Made for: Claude Code.

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 tfw-review

README.md
[![agentmods](https://agentmods.dev/badge/commands/saubakirov/trace-first-starter/tfw-review/github.svg)](https://agentmods.dev/commands/saubakirov/trace-first-starter/tfw-review)
Your own site
<a href="https://agentmods.dev/commands/saubakirov/trace-first-starter/tfw-review"><img src="https://agentmods.dev/badge/commands/saubakirov/trace-first-starter/tfw-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 tfw-review

Your own site · 80×15
<a href="https://agentmods.dev/commands/saubakirov/trace-first-starter/tfw-review"><img src="https://agentmods.dev/badge/commands/saubakirov/trace-first-starter/tfw-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
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 3,338 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 $0.00018 $0.03338
Opus 5 $0.00009 $0.01669
Sonnet 5 $0.00004 $0.00668
Haiku 4.5 $0.00002 $0.00334

Measured today against content hash 5f86d9f3a4e5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

tfw-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 today.

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/tfw-review.md · 227 lines

How it starts

The opening of the file, as written. The whole thing — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TFW Review — Task Review by Reviewer

Role: Reviewer (coordinator in review-locked mode) Input: Completed RF file + TS (for DoD verification) Output: REVIEW file with verdict + a disposition on every debt item it captured

🔒 ROLE LOCK: REVIEWER Permitted artifacts: review stage files (map.md, verify.md, judge.md) + REVIEW file. Forbidden actions: writing code, writing ONB, writing RF, modifying HL/TS. Never modify implementation; fundamental defects go in REVIEW with verdict ❌ REJECT.

Read Contract

Root instructions are already active. Read this workflow completely, then make these stage-local reads in order. Every shared range is addressed by its unique Markdown heading.

Order Stage Input Checkpoint purpose Authority
1 Bootstrap selected phase/task status.md and journal/; master/phase HL; governing TS at its approval commit; RF; EV index current state, approval lineage, and one governing artifact set task-local/governing artifacts
2 Map RF claims, TS acceptance criteria, changed-file list, and referenced predecessors build the verification map governing artifacts
3 Verify actual changed files and evidence; .tfw/project_config.yaml key tfw.review.min_verify_ratio; .tfw/glossary.md heading Project Values (PV); independent P0–P4 and relevant P5–P7 sources verify claims, evidence, and citations independently files/config/routing index/named PV sources
4 Judge master HL at its contract baseline and Project North Star reread; verify output independent Purpose Check and ten-row judgment frozen contract/PV/stage evidence
5 Decide stage files; .tfw/conventions.md headings Task control files, Session identity, Artifact file naming, Task Statuses, The 🔄 REVISE route, Safety and Execution Honesty, Trace Discipline, and Role Lock Protocol; .tfw/templates/REVIEW.md identity, verdict, disposition, routing, trace stage/shared rule/template

Read the full file on GitHub · 227 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. today Changed · +3 lines 5f86d9f3a4e5
  2. yesterday Changed · +37 lines 7cde168f5d22
  3. 5d ago Changed · +17 lines · +1 tokens per session 61ecd9f0c721
  4. 9d ago First seen · 170 lines · 17 tokens per session scan A cfd4ff86d61e

Subscribe to this mod's changes

tfw-review is a command published in the GitHub repository saubakirov/trace-first-starter (29 stars, last pushed yesterday), licensed MIT. It adds 18 tokens to every session and 3,338 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.