Borrowing it
Nothing to install: this file belongs to bredmond1019/claude-sdk-rs. 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/bredmond1019/claude-sdk-rs/main/.claude/commands/close-out.mdgit clone --depth 1 https://github.com/bredmond1019/claude-sdk-rsWrote 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/bredmond1019/claude-sdk-rs/close-out)<a href="https://agentmods.dev/commands/bredmond1019/claude-sdk-rs/close-out"><img src="https://agentmods.dev/badge/commands/bredmond1019/claude-sdk-rs/close-out/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/bredmond1019/claude-sdk-rs/close-out"><img src="https://agentmods.dev/badge/commands/bredmond1019/claude-sdk-rs/close-out.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 | $0.00000 | $0.05268 |
| Opus 5.5 | $0.00000 | $0.02107 |
| Sonnet 5.5 | $0.00000 | $0.01054 |
| Haiku 4.5 | $0.00000 | $0.00527 |
Grade A, and why
close-out scanned grade A with 1 finding 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 11d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
diff = subprocess.run(['git','diff','-M','-U0', RANGE, '--', '*.md', '*.mdx'], capture_output=True, text=True).stdout.splitlines() How it starts
The opening of the file, as written. The whole thing — 387 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Close Out — Verify test coverage, patch docs, and hand off cleanly.
Run this after /sdlc-flow or any implementation session to close the
quality loop before handing off: run the full test suite, fill coverage gaps, patch stale
docs, then produce a clean /handoff.
Variables
$ARGUMENTS — optional. Parsed left to right:
--gap-check-only— run Steps 1–3 only (validation + coverage + docs); skip Step 4 (/handoff). Designed for automated per-block close-out from a roadmap orchestration run where handing off mid-run makes no sense. Preserves all gating and coverage logic.--skip-coverage— skip Step 2 (coverage scan + gap fill); use when coverage is already known good or was verified by a prior/review-task.--clean-worktree— run Step 5 (clean-worktree) at the very end to merge a worktree branch intomainand remove the worktree. Default is false (do not clean) to protect the "never auto-merge" rule.--merge-branch— run Step 5b at the very end to merge the current plain (non-worktree) branch into the base and regenerate derived surfaces (mev emit-state --write) on the base. Use this for a/sdlc-flowrun in its default branch mode (no worktree to remove). Default is false. Mutually exclusive with--clean-worktree(that one handles worktree branches; this one handles plain branches).--base <ref>— optional. Explicit diff base (branch, tag, or commit-ish) for the Step 1 emoji gate and the Step 2a coverage sweep. Overrides the auto-resolution in Step 0.5 entirely — use it when that resolution would guess wrong, or when Step 0.5 has nothing to resolve from (noflow.prBase, noorigin/HEAD, no localmain/master) and refuses to run.- Remaining text — passed through verbatim as the narrative note to
/handoff. If omitted,/handoffderives context from git history and status.md.
Examples:
- (no args) — run all steps;
/handoffderives the narrative --gap-check-only— run Steps 1–3 only; no handoff (used by automated orchestration)--clean-worktree— run all steps, and clean/merge the worktree at the end--merge-branch— run all steps, and merge the current plain branch into the base + emit-state at the end--base develop— scope the gates todevelopinstead of auto-resolvingshipped D36 close-out command— run all steps; pass note to/handoff--skip-coverage shipped D36— skip coverage scan; pass note to/handoff
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.
- 11d ago First seen · 387 lines · 0 tokens per session scan A d7b79dad82e0
close-out is a command published in the GitHub repository bredmond1019/claude-sdk-rs (23 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 5,268 tokens. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-26.
close-out compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| close-outbredmond1019/claude-sdk-rs | Command | 23 | 1mo ago | Apache-2.0 | A | 0 | Claude Code |
| implement-featureHoangNguyen0403/agent-skills-standard | Command | 583 | today | MIT | A | 0 | Claude Code |
| AGENTSmax-sixty/worktrunk | Command | 12k | yesterday | none | A | 0 | Claude Code |
| implementmarcusgoll/Spec-Flow | Command | 96 | 1mo ago | MIT | A | 20 | Claude Code |
| pr-readycostajohnt/oss-autopilot | Command | 26 | 4d ago | MIT | A | 45 | Claude Code |
| git-workflowHermeticOrmus/LibreUIUX-Claude-Code | Command | 115 | 1mo ago | MIT | A | 14 | Claude Code |
| check-fixjuliusz-cwiakalski/agentic-delivery-os | Command | 43 | today | MIT | A | 23 | OpenCode |