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 skills/coderadius-ai/coderadius/deploy-previewnpx skills add coderadius-ai/coderadius --skill deploy-previewgit clone --depth 1 https://github.com/coderadius-ai/coderadiusWhat 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 | $0.00013 | $0.00032 |
| Opus 5 | $0.00006 | $0.00016 |
| Sonnet 5 | $0.00003 | $0.00006 |
| Haiku 4.5 | $0.00001 | $0.00003 |
Grade A, and why
deploy-preview 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
Deploy Preview
Create and manage preview deployments for feature branches.
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 · 9 lines · 13 tokens per session scan A 8f6f23306c6f
deploy-preview is a skill published in the GitHub repository coderadius-ai/coderadius (24 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 13 tokens to every session and 32 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 skills, from other repositories
mandu-mcp-index
MCP 도구 오케스트레이션 라우터 (always-on). 108개 MCP 도구 중 상황에 맞는 워크플로우 skill 선택, 집계>세분 우선순위, anti-pattern 카탈로그. MCP 도구 호출 직전 자동 참조.
mandu-lint
Lint 가이드 — 가드레일의 한 축. oxlint 셋업 / 실행 / type-aware / lefthook 통합. "lint 켜줘", "코드 스타일 검사", lint 에러 발생 시 자동 호출.
mandu-mcp-create-flow
스펙 우선 생성 워크플로우. "만들어줘", 피처/리소스/라우트 추가 시 자동 호출. contract → generate 순서를 강제하고 생성 직후 verify loop 로 전이. granular 도구 (addroute + createcontract + generate) 를 손으로 엮지 않는다.
mandu-mcp-deploy
빌드/배포 파이프라인 워크플로우. "배포", "deploy", release 전 자동 호출. deploy.check 는 fail-fast 게이트. deploy.preview 로 프로덕션 리허설. manual build + guard + seo 나열 대신 aggregate 도구 사용.
mandu-mcp-safe-change
위험 변경 트랜잭션 래퍼. 마이그레이션 / 대규모 리팩터 / refactor 도구 / "돌이킬 수 없는 변경" 시 자동 호출. historysnapshot + txbegin 필수, verify green 이면 txcommit, 아니면 txrollback.
mandu-mcp-verify
편집 후 검증 루프. 파일 편집 직후, "check 해줘", stop-hook 자동 호출. ateautopipeline + guardcheck + doctor 를 병렬로. 개별 ate 도구로 수동 분해 금지 — 실패했을 때만 drill-down.