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/shangyankeji/super-dev/super-dev-corenpx skills add shangyankeji/super-dev --skill super-dev-coregit clone --depth 1 https://github.com/shangyankeji/super-devWrote 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/shangyankeji/super-dev/super-dev-core)<a href="https://agentmods.dev/skills/shangyankeji/super-dev/super-dev-core"><img src="https://agentmods.dev/badge/skills/shangyankeji/super-dev/super-dev-core.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 | $0.00017 | $0.00683 |
| Opus 5 | $0.00009 | $0.00342 |
| Sonnet 5 | $0.00003 | $0.00137 |
| Haiku 4.5 | $0.00002 | $0.00068 |
Grade A, and why
super-dev-core 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.
What it actually says
super-dev-core - Super Dev AI Coding Skill
定位边界（强制）
- 当前宿主负责调用模型、工具、终端与实际代码修改。
- Super Dev 不是大模型平台，也不提供自己的代码生成 API。
- 你的职责是利用宿主现有能力，严格执行 Super Dev 的流程规范、设计约束、质量门禁与交付标准。
触发方式（强制）
- 支持 slash 的宿主：
/super-dev <需求描述>。 - 非 slash 宿主：
super-dev: <需求描述>与super-dev：<需求描述>等效。
首轮响应契约（强制）
- 第一轮回复必须明确说明当前阶段是
research。 - 如果仓库里已经存在 Super Dev 上下文，新会话里的第一次自然语言需求也必须继续当前流程，而不是退回普通聊天。
- 第一轮回复必须说明会先读取
knowledge/与output/knowledge-cache/*-knowledge-bundle.json。 - 三份核心文档完成后会暂停等待用户确认；未经确认不得创建
.super-dev/changes/*或开始编码。
本地知识库契约（强制）
- 先读
knowledge/。 - 若存在
output/knowledge-cache/*-knowledge-bundle.json，必须先读取并把命中的本地知识带入三文档、Spec 与实现。 - research、PRD、架构、UIUX、Spec、质量报告等要求中的产物，必须真实写入项目文件，不能只在聊天里口头描述。
- 用户要求 UI 改版时，先更新
output/*-uiux.md，再重做前端并重新执行 frontend runtime 与 UI review。 - 用户要求架构返工时，先更新
output/*-architecture.md，再同步调整 Spec / tasks 与实现方案。 - 用户要求质量整改时，先修复问题，再重新执行 quality gate 与
super-dev release proof-pack。 - 若当前项目启用了 policy / 强治理策略，不得默认建议关闭红队、降低质量阈值或跳过门禁；只有在用户明确要求降级治理强度时，才可说明风险后调整 policy。
- 完成每轮代码修改后，必须先做一次最小 diff review，再汇报“已完成”。
- 必须运行项目原生 build / compile / type-check / test / runtime smoke；若不存在某项，要说明原因。
- 本轮新增函数、方法、字段、模块、日志埋点必须接入真实调用链；未接入则删除，不允许只定义不使用。
- 不允许留下新增 unused code、只定义不调用的 helper、无效日志或无效兜底分支。
Super Dev System Flow Contract
- SUPER_DEV_FLOW_CONTRACT_V1
- PHASE_CHAIN: research>docs>docs_confirm>spec>frontend>preview_confirm>backend>quality>delivery
- DOC_CONFIRM_GATE: required
- PREVIEW_CONFIRM_GATE: required
- HOST_PARITY: required
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 · 41 lines · 17 tokens per session scan A 20a6f2a66a75
super-dev-core is a skill published in the GitHub repository shangyankeji/super-dev (274 stars, last pushed 2mo ago), licensed MIT. It adds 17 tokens to every session and 683 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
design-review
Designer's eye QA: finds visual inconsistency, spacing issues, hierarchy problems, AI slop patterns, and slow interactions — then fixes them. Iteratively fixes issues in source code, committing each fix atomically and re-verifying with before/after screenshots. For plan-mode design review (before implementation), use…
plan-eng-review
Eng manager-mode plan review. Lock in the execution plan — architecture, data flow, diagrams, edge cases, test coverage, performance. Walks through issues interactively with opinionated recommendations. Use when asked to "review the architecture", "engineering review", or "lock in the plan". Proactively suggest when…
autoplan
Auto-review pipeline — reads the full CEO, design, eng, and DX review skills from disk and runs them sequentially with auto-decisions using 6 decision principles. Surfaces taste decisions (close approaches, borderline scope, codex disagreements) at a final approval gate. One command, fully reviewed plan out. Use when…
pre-landing-review
Pre-landing PR review. Analyzes diff against the base branch for SQL safety, LLM trust boundary violations, conditional side effects, and other structural issues. Use when explicitly asked for the specialized pre-landing workflow. Product /review requests are handled by BitFun's unified Review mechanism instead.…
miniapp-dev
Develops, maintains, and generates BitFun MiniApps (Zero-Dialect Runtime). Use when (1) working on miniapp framework code under src/crates/assembly/core/src/miniapp/ or src/web-ui/src/app/scenes/miniapps/; or (2) generating / creating / designing a NEW MiniApp for the user — including any request like "做一个小应用 / 生成…
agent-eval-canvas
Create a BitFun Canvas for single-case agent evaluation and trajectory diagnosis. Use when the user asks to analyze one agent run, trace, case, benchmark item, failure trajectory, eval result, or critical failure step, and wants an incident-review style report covering verdict, step timeline, root cause, error…