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/claim-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/claim-feature)<a href="https://agentmods.dev/commands/tensorbee/rdocx/claim-feature"><img src="https://agentmods.dev/badge/commands/tensorbee/rdocx/claim-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/claim-feature"><img src="https://agentmods.dev/badge/commands/tensorbee/rdocx/claim-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 | $0.00024 | $0.00946 |
| Opus 5.5 | $0.00010 | $0.00378 |
| Sonnet 5.5 | $0.00005 | $0.00189 |
| Haiku 4.5 | $0.00002 | $0.00095 |
Grade A, and why
claim-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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/claim-feature F-XXX
Assign one story to one worker so two sessions cannot write the same tree. Run this only from the canonical sprint worktree, never from a worker's.
/run-sprint performs claims itself and does not ask separately. Invoke this by
hand when you are driving a parallel sprint manually.
Preconditions
Check all of these before touching anything. If one fails, name it and stop without altering sprint state, branches or worktrees.
-
The branch is
sprint/sNNmatching the heading indocs/sprints/CURRENT_SPRINT.md. -
The tree is clean, with one exception. The approved design plan for F-XXX may be present and uncommitted, because a manual
/designleaves it there. Refuse every other staged, unstaged or untracked path. Without this exception the claim would be impossible, since it needs both an approved plan and a clean tree. -
F-XXX is
pendingin bothdocs/sprints/CURRENT_SPRINT.mdanddocs/sprints/BACKLOG.md. -
.claude/plans/F-XXX-design.mdexists and isapproved, with non-empty## Spec reference,## Test plan,## Risk routingand## HLD impactsections. A whole-document spec citation is a failure here, the same as it is in/start-feature. -
The owner is the actual lowercase implementing host identity, such as
claude,codexorgrok, using only lowercase letters, digits and hyphens. Do not impersonate another model to fit an old example. -
The worktree path is given explicitly and does not exist. Do not infer a path and do not delete one. Put it outside the repository, as a sibling directory.
-
work/<fid-lower>-<agent>does not exist, locally or on the remote.
The claim
- Set F-XXX to
in-progressinCURRENT_SPRINT.mdandBACKLOG.md. - Write the agent name into the
Ownercell of the current-sprint wave row. Unclaimed rows keep-. - Regenerate the AUTOGEN counts in
BACKLOG.md. - Stage the claim plus the approved design plan, nothing else, and commit to the sprint branch:
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 · +3 lines 162126da60e5
- 26d ago First seen · 94 lines · 24 tokens per session scan A 6510b14bc8b7
claim-feature is a command published in the GitHub repository tensorbee/rdocx (44 stars, last pushed yesterday), licensed MIT. It adds 24 tokens to every session and 946 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
gsd:quick
Execute a quick task with GSD guarantees (atomic commits, state tracking) but skip optional agents.
standup
Review my git commits from the past workday and generate a standup summary.
gsd:remove-phase
Remove a future phase from roadmap and renumber subsequent phases.
iterate
Execute a single Ralph loop iteration - complete one work unit from tasks.md with proper commits and progress tracking.
weekly-summary
Generate weekly work summary from git activity.
afp
Prioritise feature - assigns ID, moves to backlog (shortcut for feature-prioritise).