trace-first-starter: Command for Claude Code

.claude/commands/tfw-handoff.md

tfw-handoff is a command for Claude Code from saubakirov/trace-first-starter. It costs 11 tokens per session (3,173 once invoked), scanned A, original, MIT.

A controlled handoff process for a new coding agent that receives an approved task plan, implements it, and records the results.

In plain words
What is it for?
Use it to onboard an executor agent, load the required project and task context, make approved code changes, and produce implementation evidence and a results file.
Why use it?
It prevents the implementing agent from changing the task’s scope or planning documents. It also makes the handoff and implementation outcome easier to trace.

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-handoff.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-handoff

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/saubakirov/trace-first-starter/tfw-handoff"><img src="https://agentmods.dev/badge/commands/saubakirov/trace-first-starter/tfw-handoff.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,173 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 $0.00011 $0.03173
Opus 5 $0.00005 $0.01587
Sonnet 5 $0.00002 $0.00635
Haiku 4.5 $0.00001 $0.00317

Measured yesterday against content hash 46d25df855fa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

tfw-handoff 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 yesterday.

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-handoff.md · 223 lines

How it starts

The opening of the file, as written. The whole thing — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TFW Handoff — Task Execution by New Agent

Roles: Coordinator (hands off) → Executor (receives, questions, implements) Input: Approved HL + TS files Output: RF file with implementation results

🔒 ROLE LOCK: EXECUTOR Permitted artifacts: ONB, RF. Forbidden actions: writing HL, writing TS, writing REVIEW, modifying HL, changing scope. The executor MUST NOT modify HL or TS. If scope issues are found — write them in ONB and STOP.

Read Contract

Root instructions are already active. Read this workflow completely, then select inputs in this order. Every shared range is addressed by its unique Markdown heading.

Order Input Checkpoint purpose Authority
1 selected phase/task status.md and journal/ current state, authority, and lineage before all other material task-local
2 master HL, phase HL when present, and the highest approved TS lineage frozen purpose, phase derivation, and one governing order governing task artifacts
3 prior REVIEW only on a returned REVISE; then artifacts referenced by the governing TS round basis and declared inputs governing task artifacts
4 .tfw/project_config.yamltfw.scope_budgets VALUE decomposition triggers and delegated-authority multiplier project configuration
5 .tfw/conventions.md headings Task control files, Session identity, Artifact file naming, Task Statuses, Safety and Execution Honesty, and Anti-patterns (prohibited) state/event writes, identity, revisions, lifecycle, evidence honesty, prohibitions shared rule
6 HL §7.2 citations, then relevant implementation files named by the TS inherited decision context and implementation facts named source
7 .tfw/templates/ONB.md, .tfw/templates/evidence/EV.md, and .tfw/templates/RF.md, each only at its gate output form template

Do not reload AGENTS.md or full conventions.md, glossary.md, or KNOWLEDGE.md. On a revision return, add the highest TS, prior REVIEW, and lineage range; do not reread unchanged HL, state, or shared authority in the same session. Missing or duplicate addressed headings are a hard stop under conventions.mdContext Selection.

Read the full file on GitHub · 223 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. yesterday Changed · +19 lines 46d25df855fa
  2. 4d ago Changed · +15 lines 84423d32308c
  3. 9d ago First seen · 189 lines · 11 tokens per session scan A 4d94c59d0b4d

Subscribe to this mod's changes

tfw-handoff is a command published in the GitHub repository saubakirov/trace-first-starter (29 stars, last pushed yesterday), licensed MIT. It adds 11 tokens to every session and 3,173 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.