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/rbah31/claude-code-workflow/scaffoldingnpx skills add rbah31/claude-code-workflow --skill scaffoldinggit clone --depth 1 https://github.com/rbah31/claude-code-workflowWrote 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/rbah31/claude-code-workflow/scaffolding)<a href="https://agentmods.dev/skills/rbah31/claude-code-workflow/scaffolding"><img src="https://agentmods.dev/badge/skills/rbah31/claude-code-workflow/scaffolding.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 | $0.00122 | $0.00910 |
| Opus 5 | $0.00061 | $0.00455 |
| Sonnet 5 | $0.00024 | $0.00182 |
| Haiku 4.5 | $0.00012 | $0.00091 |
Grade A, and why
scaffolding 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Scaffolding
You generate new structural units (endpoints, commands, components, migrations, etc.) that follow the project's established patterns. The goal is consistency — every new unit looks like the existing ones, with nothing forgotten.
Read config.json in this skill directory for project-specific scaffolding
config. If it doesn't exist, analyze the codebase to discover patterns, then
save what you find for next time.
How it works
When asked to scaffold something new:
-
Identify the pattern. Look at 2-3 existing examples of the same kind of unit in the codebase. Note the file structure, naming, imports, boilerplate, tests, and registration steps.
-
Check templates. Look in
templates/for pre-built scaffolds. If a matching template exists, use it. If not, create one from the pattern you discovered for next time. -
Generate all pieces. A new endpoint isn't just a handler — it's the handler + route registration + validation + tests + docs update. Generate everything the pattern requires.
-
Verify completeness. Check that the new unit is registered/imported where it needs to be. A handler that exists but isn't routed is invisible.
Template format
Templates in templates/ use simple placeholder syntax:
# templates/api-endpoint.md
Files to create:
- src/routes/{{name}}.py — handler
- tests/test_{{name}}.py — tests
Pattern to follow: see src/routes/health.py as reference.
Registration: add route in src/app.py
Don't forget:
- Input validation at the boundary
- Auth middleware (unless public)
- Error response shape: { data, error, meta }
- At least one happy-path test
Templates are reference docs, not rigid code generators. They tell you what to create and what not to forget, not exactly how to write it.
Setup
Create config.json after analyzing the project:
{
"patterns_discovered": {
"api_endpoint": {
"example": "src/routes/health.py",
"files": ["src/routes/{name}.py", "tests/test_{name}.py"],
"registration": "src/app.py",
"checklist": ["validation", "auth middleware", "error shape", "test"]
},
"bot_command": {
"example": "src/bot/cogs/help.py",
"files": ["src/bot/cogs/{name}.py", "tests/test_{name}.py"],
"registration": "src/bot/main.py",
"checklist": ["slash command decorator", "permissions", "error handling", "test"]
}
}
}
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 · 106 lines · 122 tokens per session scan A 9ef4e2b30604
scaffolding is a skill published in the GitHub repository rbah31/claude-code-workflow (5 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 122 tokens to every session and 910 once invoked, about $0.0006 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
agent-code-analyzer
Agent skill for code-analyzer - invoke with $agent-code-analyzer.
agui-dotnet-sample-step
Add a GettingStarted sample Step (a Server/Client pair) to the AG-UI .NET SDK that demonstrates one protocol feature the way we want users to write it. USE FOR: adding a new samples/GettingStarted/StepNN Server+Client pair, wiring it into AGUI.slnx and the integration-test project, giving it a deterministic…
agui-dotnet-protobuf
Use the protobuf wire transport (instead of the default Server-Sent Events) for an AG-UI connection with the AG-UI .NET SDK — a compact binary event stream negotiated via the Accept header. USE FOR: making an AGUIChatClient prefer protobuf by wiring an AGUIEventStreamHandler with ProtobufEventStreamFormatter (then…
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
nw-ddd-eventsourcing
Event Sourcing and CQRS as DDD implementation patterns — when to use, aggregate event streams, projections, snapshots, sagas, upcasting, conflict resolution.
nw-fp-clojure
Clojure language-specific patterns, data-first modeling, REPL-driven development, and spec.