Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/zywkloo/wtcraft/finishwtgit clone --depth 1 https://github.com/zywkloo/wtcraftWhat 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 | $0.00000 | $0.00085 |
| Opus 5 | $0.00000 | $0.00043 |
| Sonnet 5 | $0.00000 | $0.00017 |
| Haiku 4.5 | $0.00000 | $0.00009 |
Grade A, and why
finishwt scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
You are finishing a worktree task.
Read:
.agent-harness/finisher.mdworktrees/$ARGUMENTS/.worktree-task.md
Run verification, check boundaries, and report results. Then run the re-plan checkpoint from finisher.md: challenge the task's premises (especially Scope/Off-limits and task boundary) and get the user's confirmation before any push or PR.
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.
- 2d ago First seen · 11 lines · 0 tokens per session scan A 5a0d30f31bd5
finishwt is a command published in the GitHub repository zywkloo/wtcraft (3 stars, last pushed 12d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 85 tokens. 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 2026-08-31.
Other commands, from other repositories
release
Command "release" from CIrcui-try/Circuit, covering 절차, 1단계: 사전 확인, 2단계: 변경사항 수집, 직전 release 시점 (main의 가장 최근 release pr merge 시각) and 그 시점 이후 develop으로 머지된 pr 목록.
review-and-fix
로컬 변경사항을 직접 리뷰하고 문제점 수정 후 커밋·푸시.
takeoff
항공기 이륙 4단계 — develop 리베이스 → push → PR 생성 (원격 영향).
boarding
항공기 이륙 1단계 — Linear 이슈를 읽어 요구사항·코드 영향 범위 정리.
door-closing
항공기 이륙 2단계 — develop fetch + 워크트리 생성 + 구현 계획(plan.md) 작성.
harness-parallel
Run the parallel Auto-Harness orchestration flow with worktree workers. /auto-harness:harness-parallel.