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/complete-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/complete-feature)<a href="https://agentmods.dev/commands/tensorbee/rdocx/complete-feature"><img src="https://agentmods.dev/badge/commands/tensorbee/rdocx/complete-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/complete-feature"><img src="https://agentmods.dev/badge/commands/tensorbee/rdocx/complete-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 | $0.00019 | $0.02468 |
| Opus 5.5 | $0.00008 | $0.00987 |
| Sonnet 5.5 | $0.00004 | $0.00494 |
| Haiku 4.5 | $0.00002 | $0.00247 |
Grade A, and why
complete-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 — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/complete-feature F-XXX [--prepare]
Close out an F-ID. Every tracker is updated in one commit so the delivery record cannot drift from the code.
--prepare is the parallel-work variant a worker runs in its own worktree. It
stops short of the sprint ledgers and writes a handoff instead. See "Prepare
mode" below.
Steps
-
Check the preconditions.
- The F-ID is
in-progress. .claude/plans/F-XXX-design.mdexists and every local implementation item is ticked. Final sprint items may remain explicitly pending as below.- The latest
.claude/reviews/F-XXX-*pass reports zero defects and zero smells. - Actual
/verify --scoped F-XXXlocal evidence and clean microscope apply to the final feature source. Consume these observations, do not rerun them. Named final sprint checks remain due at the integrated gate.
If any fails, say which and stop. Before normal completion steps4 onward, require actual final checks to have passed, except the narrow approved local provider-prefix checkpoint below. Otherwise prepare only the explicit final sprint acceptance checkpoint, without delivery completion.
- The F-ID is
-
Confirm the test gate evidence is real. Read the retained named local old-source RED and fixed-source GREEN observations. Run only a missing or invalidated check. Do not repeat a passing test just because this command was invoked. A gate that passes against unmodified code is not a gate.
-
Confirm the HLD is current. Its exact approved impact files must already be included in implementation and review. Do not edit source intent after final verification. An unlisted contradiction requires a plan revision.
-
Append to
docs/sprints/AS_BUILT.mdusing the template in that file. The**Hash harness**field is mandatory for M1 through M6, recording either "unchanged" or the delta and its justification. -
Append to
docs/sprints/SPRINT_TRACKER.md: one row with the estimate and the actual.
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 · +12 lines a68492af4d94
- 11d ago Changed · +39 lines eeef66d34e73
- 14d ago Changed · +26 lines 6b404f81853c
- 26d ago First seen · 155 lines · 19 tokens per session scan A f2e03b74256c
complete-feature is a command published in the GitHub repository tensorbee/rdocx (44 stars, last pushed yesterday), licensed MIT. It adds 19 tokens to every session and 2,468 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
muggle-do
Quality-guranteed development workflow by Muggle AI. Takes a task through requirements, coding, testing, QA, and PR creation with iterative fix loops. Manages state in .muggle-do/sessions/ for auditability and crash recovery.
dev-story
Execute a story by implementing tasks/subtasks, writing tests, validating, and updating the story file per acceptance criteria.
gsd:validate-phase
Retroactively audit and fill Nyquist validation gaps for a completed phase.
session
Complete guide to managing pair programming sessions.
test-tdd
Run when user calls /test-tdd. Scans modified files, locates their corresponding unit/integration test suites, and runs them.
kill-mutants
Analyze surviving mutants from a mutation testing run and write targeted unit tests to kill them. Re-runs mutations to confirm kills.