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.
curl -O https://raw.githubusercontent.com/saubakirov/trace-first-starter/master/.claude/commands/tfw-release.mdgit clone --depth 1 https://github.com/saubakirov/trace-first-starterWrote 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.
[](https://agentmods.dev/commands/saubakirov/trace-first-starter/tfw-release)<a href="https://agentmods.dev/commands/saubakirov/trace-first-starter/tfw-release"><img src="https://agentmods.dev/badge/commands/saubakirov/trace-first-starter/tfw-release.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00012 | $0.00821 |
| Opus 5 | $0.00006 | $0.00411 |
| Sonnet 5 | $0.00002 | $0.00164 |
| Haiku 4.5 | $0.00001 | $0.00082 |
Grade A, and why
tfw-release 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.
How it starts
The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TFW Release — Version Release Workflow
Role: Coordinator / Maintainer Trigger: Manually, when accumulated changes justify a new version Prerequisite:
RELEASE.mdexists with project-specific release context
Prerequisites
- Read
RELEASE.md— understand what a release means for this project - Read
.tfw/CHANGELOG.md— see the last released version - Read
.tfw/VERSION— confirm current version - Read task state across the configured containers — identify tasks whose
lifecyclereachedDONEsince the last release. The portfolio index is a convenience for finding them; the task's ownstatus.mdis what the release records.
Who Is Acting
Resolve the acting handle before the first durable write — before any status.md change,
any journal event, any commit. Once per session, not per turn.
| Situation | What happens |
|---|---|
One profile in team/ |
it is used, silently |
| Several profiles | read the binding on this machine — ~/.tfw/bindings.yaml, or %LOCALAPPDATA%\tfw\bindings.yaml |
| No binding · a shared device · a copied binding · a handle whose profile is gone | ask exactly one short question, then proceed |
Identity is never inferred from an OS username, hostname, folder name or account display
string. Every event this session writes carries on_behalf_of (always a human) and via
(the tool). A writer is not named yet — that is TFW-54 — so do not create a profile per
session. → conventions.md §4
Step 1: Scope the Release
- List all tasks completed since the last version tag
- Categorize changes:
- Framework changes — templates, workflows, conventions, adapters
- Project changes — task artifacts, documentation, internal improvements
- Decide: do the accumulated changes justify a release? Consult
RELEASE.md§4 (triggers)
If NO → stop. Record decision in next RF if applicable.
Step 2: Determine Version Bump
Consult RELEASE.md §3 (version scheme):
| Change type | Bump |
|---|---|
| Breaking changes (conventions, template structure, workflow steps changed/removed) | MAJOR |
| New features (new workflows, new templates, new optional artifacts) | MINOR |
| Fixes, clarifications, typos | PATCH |
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.
- 7d ago First seen · 95 lines · 12 tokens per session scan A e314626bc9cb
tfw-release is a command published in the GitHub repository saubakirov/trace-first-starter (29 stars, last pushed 4d ago), licensed MIT. It adds 12 tokens to every session and 821 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.
Other commands, from other repositories
release
Command "release" from voodootikigod/skills-check, covering arguments and steps.
ship
Run the pre-launch checklist via parallel fan-out to specialist personas, then synthesize a go/no-go decision.
commit-push-pr
Commit, push, and open a PR.
upstream-watch
Review pydantic-ai and pydantic-ai-harness releases published since the last watch entry, and record a verdict in .github/upstream-watch.md.
release-update
(dev-only) release-update maintainer harness — Claude Code upstream change tracker (release-notes version-delta sweep + docs sync). NOT distributed to user projects.
iteration-loop
Autonomous full iteration loop for cloud agents — Phase 1 (code-first auto direction lock + compass/plans + Review & Edit chain) through Phase 2–5 (execute → close → PR → merge-ready). Optional args: direction, scale (S|M|L|XL, default M). Not Done until Phase 5 exit checklist passes. Minimal human intervention; no…