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/shdsjh123-cpu/claude-code-blog-builder/setup-tonegit clone --depth 1 https://github.com/shdsjh123-cpu/claude-code-blog-builderWrote 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/shdsjh123-cpu/claude-code-blog-builder/setup-tone)<a href="https://agentmods.dev/commands/shdsjh123-cpu/claude-code-blog-builder/setup-tone"><img src="https://agentmods.dev/badge/commands/shdsjh123-cpu/claude-code-blog-builder/setup-tone.svg" alt="Measured on agentmods" 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 | $0.00029 | $0.00450 |
| Opus 5 | $0.00015 | $0.00225 |
| Sonnet 5 | $0.00006 | $0.00090 |
| Haiku 4.5 | $0.00003 | $0.00045 |
Grade A, and why
setup-tone 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.
What it actually says
/setup-tone — 톤 학습 (Phase 2)
여러분 회사의 실제 블로그 글을 수집해서 AI가 톤을 학습하게 합니다. 첫 글의 품질을 크게 올립니다.
사전 조건
/setup완료 (knowledge/brand-facts.md 존재 + placeholder 아님)- 운영 중인 블로그 또는 벤치마킹할 블로그 URL 3~5개 보유
실행 절차
setup-interviewer서브에이전트 호출 (Phase 2 모드).- 서브에이전트가 다음을 묻는다:
"여러분 회사가 이미 운영 중인 블로그 글 URL 3~5개를 알려주세요. 줄바꿈으로 구분. (없으면 경쟁사/벤치마킹하는 회사 URL도 OK. 같은 산업이면 됩니다)"
- URL 검증 (도메인 다양성, 형식)
- 자동 수집 실행:
node scripts/setup-tone-fetch.js --urls "URL1,URL2,URL3" --output "knowledge/tone-samples/real-blog-posts.txt" - 결과 확인:
- 수집 텍스트 길이 (목표 80KB+, 최소 30KB)
- 너무 적으면 URL 추가 요청
- 시그니처 문장 5개 자동 추출 → 사용자에게 보여주고 검증
- CLAUDE.md에 "톤 시그니처" 섹션 자동 추가
실패 처리
- 일부 URL 수집 실패 → 성공한 것만으로 진행, 실패 URL 보고
- 모두 실패 → "수동 모드"로 전환: 사용자에게 "글 5~10편을 직접 복사해서 knowledge/tone-samples/real-blog-posts.txt에 붙여넣어주세요" 안내
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 First seen · 36 lines · 29 tokens per session scan A 679fda24f493
setup-tone is a command published in the GitHub repository shdsjh123-cpu/claude-code-blog-builder (21 stars, last pushed 5mo ago), licensed MIT. It adds 29 tokens to every session and 450 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.