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/zigrivers/scaffold/scaffold-runnernpx skills add zigrivers/scaffold --skill scaffold-runnergit clone --depth 1 https://github.com/zigrivers/scaffoldWhat 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 | $0.00073 | $0.10455 |
| Opus 5 | $0.00036 | $0.05228 |
| Sonnet 5 | $0.00015 | $0.02091 |
| Haiku 4.5 | $0.00007 | $0.01046 |
Grade A, and why
scaffold-runner 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 3d 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 — 747 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scaffold Runner
An interactive layer over the scaffold CLI: when the user asks to run a
pipeline step, surface the step's decision points to the user before
executing, then run it.
Activates when the user says "run scaffold <step>", "scaffold
<step>", "what's next?", "scaffold status", "start building", is working
in a project with a .scaffold/ directory, or asks to set scaffold up in a
project that has none yet.
Before .scaffold/ exists, pick the bootstrap command from the directory
rather than asking:
- Empty or brand-new directory →
scaffold init. - Already has source code or docs →
scaffold adopt, which initializes the config and state itself and selects thebrownfieldmethodology. It renders a plan and writes nothing until you pass--applywith the approved--plan-key.
Never run scaffold init before scaffold adopt on an existing codebase:
init would select the deep methodology and adopt would then replace it.
Core loop: check scaffold next for what's eligible; before running a step,
surface its decision points (depth, strictness, optional sections) to the user;
then run it. For stateful pipeline steps, record completion with
scaffold complete <step> — build steps (e.g. single-agent-start) are
stateless and have no completion to record. Key commands: scaffold list,
scaffold status, scaffold next, scaffold run <step>, scaffold complete <step>.
For the full command surface, run scaffold guides cli (every command grouped
by purpose) and scaffold guides pipeline; scaffold next shows what's eligible
now.
This skill provides an intelligent interactive layer between the user and the scaffold CLI. It ensures that decision points embedded in scaffold prompts are surfaced to the user before execution, and manages the full step lifecycle.
When This Skill Activates
- User says "run scaffold ", "scaffold ", or "run the next scaffold step"
- User asks "what's next?", "where am I in the pipeline?", or "scaffold status"
- User asks to run any pipeline step by name (e.g., "create the PRD", "set up testing")
- User asks to run multiple steps: "run all reviews", "run phases 5-8", "finish the pipeline", "run the next 5 steps"
- User asks to re-run groups: "re-run all reviews", "redo quality gates", "re-run from user-stories onward"
- User says "start building", "begin implementation", "run agent", "start agent"
- User asks about tools: "bump version", "create a release", "show version"
- User says "what can I build?" or "what tools are available?"
- Working in a project with a
.scaffold/directory
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.
- 3d ago First seen · 747 lines · 73 tokens per session scan A ccf280884abe
scaffold-runner is a skill published in the GitHub repository zigrivers/scaffold (5 stars, last pushed 3d ago), licensed MIT. It adds 73 tokens to every session and 10,455 once invoked, about $0.0004 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
drogon-create-controller
生成 drogon 控制器代码（.h + .cc），支持 HttpSimpleController、HttpController、WebSocketController 三种类型。.
drogon-gen-advice
生成 drogon AOP Advice 代码（11 个内建切面之一），区分拦截型/观察型，含 SyncAdvice 短路。.
drogon-gen-cmake
生成 drogon 项目的 CMakeLists.txt，支持 ORM、Redis、WebSocket、C++20、协程等特性。.
drogon-gen-coroutine-handler
生成 drogon 协程 handler / 协程中间件 / 协程 ORM 调用，正确区分 Task/AsyncTask，强制裸 handler 参数按值传递。.
drogon-gen-lambda-handler
生成 drogon 现代 lambda 路由代码（app().registerHandler），含 {N} 路径参数绑定与 constraints 混传。.
drogon-gen-orm-crud
生成符合 drogon 约定的 ORM CRUD 代码，支持回调式和协程式，覆盖 PostgreSQL、MySQL、SQLite3。.