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/hubwizard/second-pass/strictgit clone --depth 1 https://github.com/HubWizard/second-passWhat 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 | $0.00033 | $0.00250 |
| Opus 5 | $0.00016 | $0.00125 |
| Sonnet 5 | $0.00007 | $0.00050 |
| Haiku 4.5 | $0.00003 | $0.00025 |
Grade A, and why
strict 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 yesterday.
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
Set Second Pass to strict mode
The user wants high-stakes grading. Apply the strict preset: passing_grade: A, iteration_cap: 5, confirm_revisions: true.
Perform these steps:
-
Ensure the config directory exists:
~/.claude/second-pass/. Create it if missing. -
Write the strict config to
~/.claude/second-pass/config.jsonas valid JSON (pretty-printed, 2-space indent):{ "passing_grade": "A", "iteration_cap": 5, "confirm_revisions": true } -
Confirm to the user in a single line:
Second Pass set to strict mode (bar A, cap 5, confirm revisions). High-stakes artifacts will iterate aggressively.
Do not ask the user questions. Do not list the rubric. Do not explain what Second Pass is. This is a preset — be terse and done.
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.
- yesterday First seen · 28 lines · 33 tokens per session scan A 4ad1c6b47b8e
strict is a command published in the GitHub repository HubWizard/second-pass (2 stars, last pushed 4mo ago), licensed MIT. It adds 33 tokens to every session and 250 once invoked, about $0.0002 per session on Opus 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 2026-08-31.
Other commands, from other repositories
review
코드를 적대적 관점에서 리뷰하고, 숨겨진 문제를 찾아낸다. — MUST TRIGGER: 커밋 전(로직 변경 시), PR 생성 전, 버그 수정 후 회귀 확인 시.
evolve
기술 동향을 스캔하고 Nova를 자동으로 진화시킨다. 사용자 대신 Nova 품질 게이트가 변경을 검증한다.
run
구현→검증을 한 사이클로 실행한다 (Full Cycle). --verify-only로 검증만 수행 가능.
ux-audit
5인 적대적 평가자로 UI/UX를 다관점 심층 평가. 접근성(WCAG 2.2)·인지 부하·성능(Core Web Vitals)·다크 패턴(EU DSA)까지 코드 기반 분석.
check
코드 품질 리뷰 + 설계-구현 정합성 검증을 한 번에 수행한다. — MUST TRIGGER: 커밋 전(3파일 이상 변경 시), 스프린트 완료 시, 사용자가 버그를 보고한 직후.
migrate-state
NOVA-STATE.md를 최신 v3 work-item registry로 변환한다. v1/v2 입력 모두 직접 v3 가능. dry-run → 사용자 검수 → apply + drift-check 자동. — MUST TRIGGER: 사용자가 STATE 변환 요청한 직후, session-start v1/v2 hint를 본 직후, 또는 .nova/work-items/ 부재.