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-resume.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-resume)<a href="https://agentmods.dev/commands/saubakirov/trace-first-starter/tfw-resume"><img src="https://agentmods.dev/badge/commands/saubakirov/trace-first-starter/tfw-resume/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.
<a href="https://agentmods.dev/commands/saubakirov/trace-first-starter/tfw-resume"><img src="https://agentmods.dev/badge/commands/saubakirov/trace-first-starter/tfw-resume.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00013 | $0.00977 |
| Opus 5 | $0.00006 | $0.00489 |
| Sonnet 5 | $0.00003 | $0.00195 |
| Haiku 4.5 | $0.00001 | $0.00098 |
Grade A, and why
tfw-resume 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.
How it starts
The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TFW Resume — Selected Work and Phase Status
Role: Coordinator (new or returning) Output: Selected closing/recovery result, or phase status matrix and recommendation
🔒 ROLE LOCK: COORDINATOR Permitted: selected Coordinator closing/control records and separately attributed REVIEW closing entries; read-only status analysis, then Phase HL/TS only after the user selects planning. Forbidden: execution, ONB, RF, RES, REVIEW creation/proposals, and code changes.
Read Contract
Read this workflow completely, then select inputs in order; shared ranges use unique headings.
| Order | Input | Checkpoint purpose | Authority |
|---|---|---|---|
| 1 | named task/phase state; else .tfw/project_config.yaml → tfw.task_containers only to resolve it, then status.md/journal/ |
state first | task/config |
| 2 | each current phase's own status.md and journal/ for unselected next-phase work when the task is PHASES; an explicitly selected phase uses its own state |
phase truth without task-level rollup | phase-local |
| 3 | referenced authority/lineage; master HL/TS only if named | governing purpose/scope/artifact | governing artifacts |
| 4 | highest completed/returned REVIEW; RF only for claim detail | verdict/disposition/return | governing artifacts |
| 5 | .tfw/conventions.md headings Task control files, Session identity, Artifact file naming, Task Statuses, and The 🔄 REVISE route |
identity/state/route | shared rule |
| 6 | for selected closing/recovery: .tfw/conventions.md heading Closing and record recovery; only referenced acceptance, evidence and actual final effects |
selected close or reconstructable carrier repair | shared rule/governing artifacts |
Indexes/globs/chat/unrelated RF/full libraries are not state; heading/lineage defects stop under Context Selection.
Who Is Acting
Before writing resolve handle: one profile, valid binding, or one question. Never infer; events use human on_behalf_of and tool via.
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.
- today Changed · +9 lines · -1 tokens per session db547cf4ef2e
- 2d ago Changed · -40 lines e65fc0229f8e
- 6d ago Changed · -5 lines b1d8c69e523a
- 10d ago First seen · 114 lines · 14 tokens per session scan A 93e073f4da4a
tfw-resume is a command published in the GitHub repository saubakirov/trace-first-starter (29 stars, last pushed today), licensed MIT. It adds 13 tokens to every session and 977 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
fw-setup-use
Workspace FDK stack switch — nvm use from .nvmrc or explicit 10/9 (Node 24.11 vs 18); optional --write-nvmrc and --global flags.
fdk-migrate
Migrate a legacy Freshworks app from platform-version 2.3 (2.x), FDK 9.x, and Node 18 to Platform 3.0 with FDK 10.0.1 and Node 24.11.0. Transforms manifest, request templates, Crayons UI, and validates on the new toolchain. Does not install fdk/Node—use fw-setup (or prompt user to add it) per SKILL.md.
fw-setup-status
Check FDK and Node.js installation status (/fw-setup status); optional --verbose diagnostics.
openehr-explain
One-stop router that explains or looks up any openEHR thing — auto-detects an archetype, a template, an RM/AM/BASE type, an RM structural concept, an ADL idiom, an AQL query or keyword, or a terminology code (replaces /archetype-explain, /template-explain, /type-spec, /rm-structure, /adl-idiom, /terminology).
bottleneck-detect
Analyze performance bottlenecks in swarm operations and suggest optimizations.
swarm-init
Initialize a Ruflo swarm with specified topology and configuration.