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/rockyhong/super-bootstrap/releasenpx skills add RockyHong/super-bootstrap --skill releasegit clone --depth 1 https://github.com/RockyHong/super-bootstrapWrote 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/skills/rockyhong/super-bootstrap/release)<a href="https://agentmods.dev/skills/rockyhong/super-bootstrap/release"><img src="https://agentmods.dev/badge/skills/rockyhong/super-bootstrap/release.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 | $0.00024 | $0.01577 |
| Opus 5 | $0.00012 | $0.00788 |
| Sonnet 5 | $0.00005 | $0.00315 |
| Haiku 4.5 | $0.00002 | $0.00158 |
Grade A, and why
release 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release
Project Config
- Type: generic (Claude Code plugin / marketplace)
- Version file (single source of truth):
plugins/super-bootstrap/.claude-plugin/plugin.json→version(marketplace.jsoncarries noversion)
- Derived manifest mirror:
.claude-plugin/marketplace.json→plugins[0].description(synced fromplugin.jsonat release; direct edits get overwritten)
- Platforms: none (single artifact)
- Main branch: main
Protocol
Code blocks below are POSIX bash — on a PowerShell-primary device, run them via the Bash tool; if porting to PowerShell, rewrite in its idiom and single-quote git's caret/brace revisions (git rev-parse 'v1.2.3^{commit}').
1. Qualify
Run in parallel:
git status— working tree must be clean. If dirty, stop: "Commit or stash changes first."git branch --show-current— must be onmain. If not, warn and ask to continue.
1.5 Dispatch-shell pre-flight (warn, not block)
Scan plugins/*/skills/*/SKILL.md for bounded-judgment verbs — classify, rank, scan, digest (case-insensitive) — appearing in the skill's protocol/execution body. For each hit, check whether that skill dispatches a typed agent (a sibling agents/<name>.md, or a subagent_type: / "dispatch the ... agent" reference in the same file). A skill frontmatter alone can't pin a model — bounded judgment left inline runs unpinned, at the gateway's tier.
Skip skills whose row in plugins/super-bootstrap/README.md § "Inline vs Dispatch" documents an inline rationale — those are decided placements, not misses; warning on them every release trains the reader to ignore the check.
Bounded-judgment verb(s) found, no agent dispatch, and no documented inline rationale → warn, one line, don't block:
⚠ dispatch-shell check: {file} — bounded-judgment verb(s) ({verbs}) with no agent dispatch. Consider splitting into dispatch-shell + typed agent (see
skills/todo+agents/todo.md).
List every matching file on one line if more than one hits. Never halts the release — this is a nudge surfaced in the release report, not a qualify gate.
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.
- 4d ago First seen · 138 lines · 24 tokens per session scan A ae72bf6926b9
release is a skill published in the GitHub repository RockyHong/super-bootstrap (3 stars, last pushed 7d ago), licensed MIT. It adds 24 tokens to every session and 1,577 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 2026-08-31.
Other skills, from other repositories
craft-plugin-release
Releasing Craft CMS plugins — tagging, Packagist propagation, GitHub releases, branch promotion, shared-library ordering, history rewrites. ALWAYS load when cutting, preparing, verifying, or debugging a plugin release: bumping a version, dating a changelog, creating or moving a git tag, or checking what Packagist…
release
BeeCount 全家桶发版流水线:App(BeeCount)与自建云(BeeCount-Cloud)打 tag 触发 CI 全自动构建,加上 changelog 双格式、官网文档同步、宣传视频与社媒文案的完整收尾。当用户说"发布新版本"、"发版"、"App 发 X.Y.Z"、"cloud 发个版本"、"打个 tag 发布"、"release 一下"、"准备上架"时必须使用本技能——哪怕只发一端、哪怕只是"先把 changelog 写了",也按本流水线对应步骤走。不适用于:日常 PR 合并(不发版)、honeycomb/video-studio 等其它仓的发布、商店审核被拒的申诉处理。.
git-for-research-code
When the user wants to version-control optimization research code - small commits per experiment change, tags for paper result snapshots, .gitignore for solver logs, linking result tables to commit hashes, and branch strategy for risky refactors. Also use when the user mentions "git workflow," "version control…
ship
현재 브랜치의 변경사항을 commit → push → PR 생성 → merge → 브랜치 정리까지 한 번에 처리한다. develop 브랜치가 있으면 git-flow(feature→develop→main), 없으면 GitHub Flow(feature→main)로 자동 적응하고, 머지 전 기능 게이트+보안 스캔+DB 검토+민감파일 차단을 실행한다. '/ship', 'ship', '배포해줘', '커밋하고 머지까지' 등 언급 시 호출.
git-workflow
Enforces the release-branch Git model: scaffold feature branches, open PRs with review checks, cut releases with tags, and view workflow reference.
changelog-generator
Generates a structured CHANGELOG.md following Keep a Changelog format from git history and ABD handoff artifacts. Prepends new version sections to existing changelogs.