Borrowing it
Nothing to install: this file belongs to tensorbee/rdocx. 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/tensorbee/rdocx/main/.claude/commands/start-feature.mdgit clone --depth 1 https://github.com/tensorbee/rdocxWrote 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/tensorbee/rdocx/start-feature)<a href="https://agentmods.dev/commands/tensorbee/rdocx/start-feature"><img src="https://agentmods.dev/badge/commands/tensorbee/rdocx/start-feature/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/tensorbee/rdocx/start-feature"><img src="https://agentmods.dev/badge/commands/tensorbee/rdocx/start-feature.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 | $0.00017 | $0.00912 |
| Opus 5.5 | $0.00007 | $0.00365 |
| Sonnet 5.5 | $0.00003 | $0.00182 |
| Haiku 4.5 | $0.00002 | $0.00091 |
Grade A, and why
start-feature 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 6d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/start-feature F-XXX [--claimed]
Transition an approved design into an in-progress feature with failing test stubs. No implementation in this command.
--claimed is what a worker runs first in a worktree that /claim-feature
created. The claim already set the trackers and cut the branch, so this becomes
the stub-creation half of the command.
Steps
-
Confirm the branch. The current branch must be
sprint/sNNmatching the sprint indocs/sprints/CURRENT_SPRINT.md. If it ismain, create the sprint branch first through/sync-sprint.Under
--claimed, the branch must instead bework/<fid-lower>-<agent>, in the worktree the claim created, with F-XXX alreadyin-progressand owned by that agent. If the branch issprint/sNN, you are in the canonical worktree and the claim did not happen. Stop. -
Read the design plan.
.claude/plans/F-XXX-design.mdmust exist and its status must beapproved. -
Validate the spec reference. The plan's
## Spec referencemust name specific sections. Refuse a whole-document citation such as "see docs/hld/". This check exists because a vague reference is how a story silently drifts from its specification. -
Check the dependencies are
doneindocs/sprints/BACKLOG.md. An approved provider design is insufficient. Inspect the plan's dependency readiness record and any required dependency-prefix checkpoint evidence. -
Check readiness and create the test stubs from the plan's
## Test plan. Each is a real test function that fails for the right reason, nottodo!(). Confirm the plan's consumer map, A-ID acceptance rows and test matrix are concrete first. A new or revised plan must also satisfy/design's validation checklist, including applicable behavior contracts and answered blocking decisions. A repaired contradiction must have an actual discriminator across its affected consumers or modes. Include empty cases and valid/refusal controls where applicable. Record the expected assertion before running old source. A stub that passes vacuously is worse than no stub.
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.
- 6d ago Changed · +8 lines 3b8948159539
- 11d ago Changed · +4 lines de1bd230c327
- 26d ago First seen · 64 lines · 17 tokens per session scan A 4bcfc97c4293
start-feature is a command published in the GitHub repository tensorbee/rdocx (44 stars, last pushed yesterday), licensed MIT. It adds 17 tokens to every session and 912 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 2026-10-04.
Other commands, from other repositories
checkpoint
Save verification state and progress checkpoint.
verify-work
Verify feature, bug, UI, API, mobile, security, or deployment work against acceptance criteria.
boss:dev
A development workflow that assigns frontend and backend coding work from an existing task or architecture plan. It follows TDD, or test-driven development: write a failing test, implement the smallest fix, then refactor.
workflow-implement
Exécuter la phase d'Implémentation - développement TDD/BDD d'un sprint, d'un epic, d'une story ou de la file batch (séquentiel, ou parallèle via /team:delivery --phase=implementation).
aqa-flow
Router workflow for test automation: routes to ui-aqa-flow, api-aqa-flow, or testgen-flow. Kept for backward compatibility.
complete
Review implementation evidence and plan the spec completion transaction.