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/run-sprint.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/run-sprint)<a href="https://agentmods.dev/commands/tensorbee/rdocx/run-sprint"><img src="https://agentmods.dev/badge/commands/tensorbee/rdocx/run-sprint/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/run-sprint"><img src="https://agentmods.dev/badge/commands/tensorbee/rdocx/run-sprint.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 | $0.00038 | $0.05338 |
| Opus 5.5 | $0.00015 | $0.02135 |
| Sonnet 5.5 | $0.00008 | $0.01068 |
| Haiku 4.5 | $0.00004 | $0.00534 |
Grade A, and why
run-sprint 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 — 470 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/run-sprint [--prepare] [--reviewer NAME] [--max-review-passes N] [--max-workers N]
Drive the whole active sprint. Design every story before implementing any of
them, run independent stories in parallel worktrees, complete scoped dependency-prefix
checkpoints and verify the final integrated result, then loop on /sprint-review until
it comes back clean.
Defaults are three review passes and as many workers as the wave allows.
Each worker keeps its implementation scoped to its approved F-ID, with focused
RED/GREEN regressions, F-ID-bound fast /verify --scoped and a zero-finding
/microscope. Reserve /verify --full, the union of sprint risk riders and
/sprint-review for the integrated final result. A dependency-prefix
checkpoint uses actual scoped local evidence and focused reconciliation checks.
External oracles, complete suites and risk riders run only in the final union.
Subcommands consume the same evidence instead of repeating its execution.
Workers batch related local cases sharing a test binary when practical, with individual RED/GREEN outcomes retained. Compilation and linking cost matter alongside runtime. Preserve checkpoints needed to resolve real uncertainty.
scripts/sprint_workflow.py is the state authority. Everything below is
resumable through .claude/scratch/SNN-run.json. Reuse it rather than starting
over.
This command never merges to main or creates a release tag. It ends by
telling you the exact /close-sprint invocation. Release preparation F-IDs
finish with local evidence. Publication follows sprint close through
/release from the reviewed main merge SHA.
Prepare only and reviewer selection
--prepare performs read-only GitHub intake, state/dependency/source inspection,
then drafts the detailed designs and consolidated open questions in sections1
and2. It may write the existing planning, intake and run-state artifacts. It
stops before approving unresolved decisions, committing plans, claiming workers
or implementing code. Preserve already approved/running/reviewed work and its
observations rather than resetting it to draft. Report the exact later run
command and any material questions. This flag belongs to this orchestration
command, not scripts/sprint_workflow.py init. It is unrelated to the worker
handoff flag on /complete-feature --prepare.
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 · +82 lines b96ef89dfabc
- 11d ago Changed · +36 lines c504cca1f269
- 14d ago Changed · +25 lines 02a34b0556a2
- 26d ago First seen · 327 lines · 38 tokens per session scan A 8a4676a41634
run-sprint is a command published in the GitHub repository tensorbee/rdocx (44 stars, last pushed yesterday), licensed MIT. It adds 38 tokens to every session and 5,338 once invoked, about $0.0002 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.