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 skills add sjarmak/coding-agent-workflows --skill scaffoldgit clone --depth 1 https://github.com/sjarmak/coding-agent-workflowsWrote 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/sjarmak/coding-agent-workflows/scaffold)<a href="https://agentmods.dev/skills/sjarmak/coding-agent-workflows/scaffold"><img src="https://agentmods.dev/badge/skills/sjarmak/coding-agent-workflows/scaffold/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/sjarmak/coding-agent-workflows/scaffold"><img src="https://agentmods.dev/badge/skills/sjarmak/coding-agent-workflows/scaffold.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00037 | $0.01910 |
| Opus 5.5 | $0.00015 | $0.00764 |
| Sonnet 5.5 | $0.00007 | $0.00382 |
| Haiku 4.5 | $0.00004 | $0.00191 |
Grade A, and why
scaffold 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 1mo 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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scaffold: Build-Order Planning
Take a chosen design (from diverge-prototype or any architecture decision) and
spawn N independent agents, each proposing a different build-order strategy. Each
produces a sequenced implementation plan with milestones, dependencies, and a
risk assessment; the results synthesize into one recommended build plan.
Arguments
[N] [path/to/design.md | inline description]
- N is the number of strategies (default 4, min 2, max 6).
- Input is a path to a design doc/prototype/PRD, or an inline description of what needs to be built. Missing or unclear: ask the user to clarify before starting.
Phase 1: Understand the Design
Read the design doc, prototype, or PRD provided. Extract the following:
- Components to build: every distinct module, service, or subsystem
- Dependencies between them: what requires what
- External integrations: third-party APIs, databases, services
- Testing requirements: what needs testing and at what level
- Deployment needs: infrastructure, environments, CI/CD
Prepare a build brief that summarizes:
- What needs to be built
- What exists already (if working within an existing codebase)
- What the constraints are (technical, timeline, team)
Present the build brief to the user and confirm before proceeding. Adjust if the user gives feedback.
Phase 2: Spawn Sequencing Agents
Launch all N agents in parallel using the Agent tool. Each agent receives the build brief plus a unique sequencing strategy drawn from this pool (assign strategies 1 through N):
- "Riskiest-First": Start with the highest-uncertainty components. Front-load risk to learn early whether the approach works. Motto: "fail fast on the hard stuff."
- "Demo-able First": Start with the components that produce visible, testable output. Build stakeholder confidence early. Motto: "something to show every sprint."
- "Dependency-Topological": Strict dependency order. Build foundations first, layers on top. Nothing starts until its dependencies are complete. Motto: "no stubs, no mocks, each piece works when built."
- "Vertical Slice": Build one thin end-to-end path through the entire system first. Proves integration works before widening. Motto: "narrow and deep before wide."
- "Test Infrastructure First": Start with test harness, CI/CD, monitoring, observability. Build the ability to verify before building things to verify. Motto: "confidence before velocity."
- "Parallel Tracks": Identify independent work streams that can proceed simultaneously. Optimize for team throughput. Motto: "max parallelism, defined interfaces."
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.
- 1mo ago First seen · 189 lines · 37 tokens per session scan A 510846ff9da6
scaffold is a skill published in the GitHub repository sjarmak/coding-agent-workflows (6 stars, last pushed 17d ago), licensed MIT. It adds 37 tokens to every session and 1,910 once invoked, about $0.0001 per session on Opus 5.5. 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
browser-trace
Capture a full DevTools-protocol trace of any browser automation — CDP firehose, screenshots, and DOM dumps — then bisect the stream into per-page searchable buckets. Use when the user wants to debug a failed run, audit network/console/DOM activity, attach a trace to an in-progress session, or feed structured per-page…
planning-with-files
Persistent file-based planning for multi-step AI-agent work. Keeps taskplan.md, findings.md, and progress.md on disk; lifecycle hooks inject selected project planning context. Automatic recovery reads project planning files only. Explicit session-catchup.py --metadata reads same-project local agent session records and…
ai-elements
Build AI chat interfaces using ai-elements components — conversations, messages, tool displays, prompt inputs, and more. Use when the user wants to build a chatbot, AI assistant UI, or any AI-powered chat interface.
exa-search
Use Exa MCP for current web, code/docs, company, people, and page-fetch research. Prefer current hosted tool schemas and note deprecated tools.
ontoly-software-graph
Use Ontoly's deterministic Software Graph and MCP capabilities for repository architecture, request tracing, dependency analysis, configuration lookup, and impact analysis before falling back to source search.
kimi-webbridge
A way for an AI agent to control the user's real web browser, including pages where the user is already signed in. It can navigate, click, type, read page content, and take screenshots.