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 commands/datathings/marketplace/scaffoldgit clone --depth 1 https://github.com/datathings/marketplaceWrote 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/commands/datathings/marketplace/scaffold)<a href="https://agentmods.dev/commands/datathings/marketplace/scaffold"><img src="https://agentmods.dev/badge/commands/datathings/marketplace/scaffold.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 | $0.03666 |
| Opus 5 | $0.00009 | $0.01833 |
| Sonnet 5 | $0.00003 | $0.00733 |
| Haiku 4.5 | $0.00002 | $0.00367 |
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 5d 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 — 372 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GreyCat Scaffold Generator
Purpose: Generate model + service + API + tests for an entity — plus a matching Lit UI component when frontend/ exists.
Generated files:
src/<feature>/<feature>.gcl— type + indices + servicesrc/<feature>/<feature>_api.gcl—@expose+@volatileviewstest/<feature>_test.gcl— testsfrontend/components/<feature>-table.ts— Lit component (only iffrontend/exists)
Templates: CRUD | Time-series collector | Graph traversal | Custom
Frontend stack (for the UI component): VitePlus (vp) + Lit (shadow DOM) + TypeScript + Web Awesome (@awesome.me/webawesome, or an equivalent web-component UI kit) + @greycat/web/sdk + lucide-static (self-hosted inline SVG), pnpm. Pin exact latest versions; keep content accessible for LLM-friendly SEO. Lighthouse tuning is optional.
One entity = sequential (model → api → test → frontend; each step depends on the prior file) — this is the default flow. To scaffold several entities at once, fan out one subagent (Task) per entity — they are independent.
Step 1: Ask template (AskUserQuestion)
- CRUD Service (Recommended) — create/read/update/delete + indices
- Time-series Collector —
nodeTimeindex for temporal data - Graph Traversal — relationships + traversal queries
- Custom (guided)
Step 2: Detect project structure
[ ! -f "project.gcl" ] && { echo "ERROR: not a GreyCat project root"; exit 1; }
mkdir -p src test
Step 3: Gather entity details (AskUserQuestion)
- Entity name (PascalCase:
Device,User,Order) - Fields (one per line:
name: String,email: String,age: int?,created_at: time) - Indices (multiSelect):
- By ID:
nodeIndex<int, node<T>> - By unique field:
nodeIndex<String, node<T>> - List:
nodeList<node<T>> - Time-series:
nodeTime<T>(primitive or node) - Geo:
nodeGeo<node<T>>
- By ID:
Step 4: Detect project style
find src -name "*.gcl" | head -3 # check existing patterns
Match sibling .gcl files (indentation, error-handling style); run greycat fmt — the formatter owns width/layout.
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.
- 5d ago First seen · 372 lines · 17 tokens per session scan A a3b37c764564
scaffold is a command published in the GitHub repository datathings/marketplace (11 stars, last pushed 8d ago), licensed Apache-2.0. It adds 17 tokens to every session and 3,666 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.