trace-first-starter: Command for Claude Code

.claude/commands/tfw-init.md

tfw-init is a command for Claude Code from saubakirov/trace-first-starter. It costs 13 tokens per session (2,608 once invoked), scanned A, original, MIT.

A guided setup command that adds TFW to a new project. TFW is a task-management workflow for coding agents, with project configuration, instructions, and an initial task.

In plain words
What is it for?
Use it when introducing TFW to a project, creating its first task, or attaching or repairing the adapter used by the coding agent.
Why use it?
It creates the files and connections needed before using TFW. It also detects an existing setup so project state is not recreated unnecessarily.

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-init.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-init

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/saubakirov/trace-first-starter/tfw-init"><img src="https://agentmods.dev/badge/commands/saubakirov/trace-first-starter/tfw-init.svg" alt="Reviewed on agentmods" width="80" 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 2,608 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 $0.00013 $0.02608
Opus 5.5 $0.00005 $0.01043
Sonnet 5.5 $0.00003 $0.00522
Haiku 4.5 $0.00001 $0.00261

Measured 18d ago against content hash 8baa23458acb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

tfw-init 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 18d 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/tfw-init.md · 196 lines

How it starts

The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TFW Init — Project Initialization

Role: Coordinator Output: configured TFW project and first task, or one repaired adapter

🔒 ROLE LOCK: COORDINATOR Permitted: TFW setup/config/adapters and the init task's RES/RF. Forbidden: HL, TS, unrelated code, project-purpose replacement, and state reset.

Read Contract

Read this workflow completely, then select inputs in order. Full common libraries and unselected adapters are not inputs.

Order Input Checkpoint purpose Authority
1 .tfw/; .tfw/project_config.yaml → tfw.task_containers, tfw.historical_containers; task status.md/journal/ route full-init or attach/repair across the reference union filesystem/config/task-local
2 .tfw/adapters/manifest.yaml and selected adapter sources/targets exact repair mapping and preservation manifest/receiver
3 full-init only: root README, receiver .tfw/README.md, project docs/structure/build/people/process discovery and purpose preservation project/receiver
4 templates for config, knowledge entry/record/handover, profile, status, journal output forms templates
5 .tfw/conventions.md → Identifier, Session identity identity and naming shared rule
6 selected research/knowledge/RF forms at their gates init research and result workflows/templates

Missing or duplicate task containers, unresolved manifest rows, ambiguous adapter selection, or a purpose collision that evidence cannot settle are hard stops.

Activation and routing checkpoint

Apply the active root activation/routing contract before discovery or repair and require exact owner-direct /tfw-init activation. Full init has no prior status: the first status records this Coordinator's complete routing spine and paired reporting: native-gates / selection_ref: baseline. Attach/repair validates existing task routing when task-bound and adds the pair only after verifying the actual initial human source and frozen ceiling; it never guesses delegation, owner-transfer, legacy or partial fields.

Read the full file on GitHub · 196 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. 18d ago Changed · +13 lines 8baa23458acb
  2. 21d ago Changed · +11 lines 18020b6e617b
  3. 22d ago Changed · +12 lines 8ecafc76153a
  4. 27d ago Changed · +6 lines dfecc626b9e0
  5. 28d ago Changed · +8 lines 8003d48075c3
  6. 1mo ago Changed · +5 lines bb69d56befa9
  7. 1mo ago Changed · +7 lines 7ec919af5ec2
  8. 1mo ago Changed · +5 lines a9ad5de1dc31
  9. 1mo ago Changed · -142 lines · -3 tokens per session d84f6cb84dec
  10. 1mo ago First seen · 271 lines · 16 tokens per session scan A 0344575b32ea

Subscribe to this mod's changes

tfw-init is a command published in the GitHub repository saubakirov/trace-first-starter (30 stars, last pushed 9d ago), licensed MIT. It adds 13 tokens to every session and 2,608 once invoked, about $0.0001 per session on Opus 5.5. 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.