trace-first-starter: Command for Claude Code

.claude/commands/tfw-plan.md

tfw-plan is a command for Claude Code from saubakirov/trace-first-starter. It costs 16 tokens per session (3,423 once invoked), scanned A, original, MIT.

A task-planning workflow for researching a problem, writing a high-level plan, reviewing the scope, and producing a technical specification. TFW means Task Inception Workflow, a process for understanding work before implementation.

In plain words
What is it for?
Loading project context, checking whether shared knowledge needs updating, researching a task, showing the intended end state, recording unknowns, and writing the high-level and technical plans.
Why use it?
It helps teams identify missing information, test assumptions, and define the intended result before code is written. Its role limits keep planning separate from implementation and other workflow stages.

Command for Claude Code

Written for Claude Code: installed under .claude/.

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-plan.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-plan

README.md
[![agentmods](https://agentmods.dev/badge/commands/saubakirov/trace-first-starter/tfw-plan.svg)](https://agentmods.dev/commands/saubakirov/trace-first-starter/tfw-plan)
Your own site
<a href="https://agentmods.dev/commands/saubakirov/trace-first-starter/tfw-plan"><img src="https://agentmods.dev/badge/commands/saubakirov/trace-first-starter/tfw-plan.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,423 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 $0.00016 $0.03423
Opus 5 $0.00008 $0.01711
Sonnet 5 $0.00003 $0.00685
Haiku 4.5 $0.00002 $0.00342

Measured today against content hash 775e53088428, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

tfw-plan 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-plan.md · 220 lines

How it starts

The opening of the file, as written. The whole thing — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TFW Plan — Task Inception Workflow

🔒 ROLE LOCK: COORDINATOR You write HL and TS and may append Coordinator rulings to a live REVIEW. You do NOT write ONB, RF, RES, REVIEW proposals, or code. Violation = immediate stop + report.

Mindset: Architect before proposing: visualize the finish (§3.1), expose unknowns (§10), challenge assumptions, and apply Saint-Exupéry as judgment, never mechanical subtraction. Planning quality outranks pipeline speed.

Read Contract

Root instructions are already active. Read this workflow completely; then use this ordered contract. Every shared range is addressed by its unique Markdown heading.

Order Input Checkpoint purpose Authority
1 selected task/phase status.md and journal/, when one exists current state and lineage before global material task-local
2 .tfw/project_config.yamltfw.task_prefix, tfw.task_containers, tfw.knowledge, tfw.research, tfw.scope_budgets, and tfw.templates exact task, gate, research, VALUE, authority, and template values project config
3 .tfw/conventions.md headings Task control files, Session identity, Artifact file naming, Research subfolder, Review subfolder, Evidence subfolder, Multi-phase folder structure, Task Statuses, A phase carries its own state, Semantic value-bearing classification, Value-bearing accounting contract, Decomposition, constraints, and change authority, and Role Lock Protocol attribution, session identity, topology, lifecycle, VALUE contract, writer authority shared rule
4 .tfw/glossary.md heading Project Values (PV) independent P0–P4 scan and relevant P5–P7 routing routing index
5 .tfw/templates/HL.md and .tfw/templates/TS.md, only at their write gates output form template
6 relevant task artifacts and cited PV/knowledge items selected by Steps 3–8 task-specific decisions, not permanent preload named source

Full conventions.md, full glossary.md, full KNOWLEDGE.md, unrelated tasks, derived indexes, and historical traces are not inputs unless a named conflict or compatibility check triggers their exact range. Missing or duplicate addressed headings are a hard stop under conventions.mdContext Selection.

Read the full file on GitHub · 220 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 · +12 lines 775e53088428
  2. 4d ago Changed · +13 lines 7527ad2448b5
  3. 8d ago First seen · 195 lines · 16 tokens per session scan A 3707879dbc09

Subscribe to this mod's changes

tfw-plan is a command published in the GitHub repository saubakirov/trace-first-starter (29 stars, last pushed today), licensed MIT. It adds 16 tokens to every session and 3,423 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.