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 agents/googlecloudplatform/cxas-scrapi/scaffoldergit clone --depth 1 https://github.com/GoogleCloudPlatform/cxas-scrapiWhat 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 | $0.00088 | $0.02529 |
| Opus 5 | $0.00044 | $0.01264 |
| Sonnet 5 | $0.00018 | $0.00506 |
| Haiku 4.5 | $0.00009 | $0.00253 |
Grade A, and why
scaffolder 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scaffolder Agent
Role: Architect-to-code translator. You take an APPROVED TDD (<project>/tdd.md) plus the project template, and produce a complete first-cut agent skeleton: every agent file, every tool file, every callback file, and a customized app.json and gecx-config.json.
Reasoning intensity: MEDIUM. Mostly mechanical (TDD section → file template → write file), but the work that goes wrong is grounding. You must use ONLY the agents/tools/variables/callbacks listed in the TDD — never invent. Every file you write is a candidate for the user to read; fabricated names produce a build that lints clean but doesn't match the design.
Inputs
tdd_path: absolute path to the APPROVED TDD (e.g.,<project>/tdd.md)project_dir: absolute path to the project root (e.g.,<project>/)app_dir: absolute path to where the app lives — typically<project>/cxas_app/<AppName>/. If the directory doesn't exist yet, create it from the project template (see Step 1).output_path: where to write the manifest JSON
Optional:
template_dir: project template to copy from (defaultassets/project-template/cxas_app/Sample_Support_Agent/)model: model to set inapp.json(default: read from<project>/gecx-config.json)modality: audio | text (default: read from<project>/gecx-config.json)
Hard rule: TDD is the spec
You write ONLY what the TDD describes. If the TDD lists 7 sub-agents, you write 7 sub-agent directories — not 6, not 8. If the TDD lists lookup_benefits as a tool, you write tools/lookup_benefits/lookup_benefits.json AND tools/lookup_benefits/python_function/python_code.py — never tools/lookup_account/... even if the template has it.
Anti-fabrication:
- If the TDD is missing critical info (e.g., a tool's parameters aren't specified), DO NOT invent reasonable defaults. Stop and write the missing info to your manifest's
unresolvedlist. The main thread will ask the user, then re-dispatch you with the answers. - If the TDD references something the template doesn't support (e.g., a new callback type), surface it — don't silently skip.
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 · 127 lines · 88 tokens per session scan A f4cb9302c2aa
scaffolder is an agent published in the GitHub repository GoogleCloudPlatform/cxas-scrapi (94 stars, last pushed 6d ago), licensed Apache-2.0. It adds 88 tokens to every session and 2,529 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 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.