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/l3digitalnet/claude-code-plugins/scaffold-integrationgit clone --depth 1 https://github.com/L3DigitalNet/Claude-Code-PluginsWhat 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 | $0.00016 | $0.01229 |
| Opus 5 | $0.00008 | $0.00615 |
| Sonnet 5 | $0.00003 | $0.00246 |
| Haiku 4.5 | $0.00002 | $0.00123 |
Grade A, and why
scaffold-integration 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 2d 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scaffold Home Assistant Integration
Create a new Home Assistant integration with all required files following 2025 best practices.
Step 1: Collect Integration Details
Ask for the domain name and integration name as a single open-ended question:
"What is the domain name (lowercase, underscores only — e.g.
my_device) and the human-readable name (e.g. "My Device") for this integration?"
Then use AskUserQuestion for the bounded choices:
AskUserQuestion:
"What type of integration is this?"
header: "Integration type"
options:
- label: "Hub"
description: "A gateway that connects multiple devices (e.g. Hue bridge, Z-Wave stick)"
- label: "Device"
description: "A single standalone device (e.g. one smart plug, one sensor)"
- label: "Service"
description: "A cloud or network service (e.g. weather API, notification service)"
AskUserQuestion:
"How does this integration communicate with the device/service?"
header: "IoT class"
options:
- label: "local_polling — query device on a schedule (Recommended)"
description: "Your code calls the device/API periodically to fetch state"
- label: "local_push — device sends updates to HA"
description: "Device pushes state changes via webhook, socket, or event"
- label: "cloud_polling — query cloud API on a schedule"
description: "Your code calls a remote API periodically"
- label: "cloud_push — cloud sends updates to HA"
description: "Remote service pushes state changes via webhook or SSE"
AskUserQuestion:
"Which entity platforms does this integration expose? (select all that apply)"
header: "Platforms"
multiSelect: true
options:
- label: "sensor"
description: "Read-only state values (temperature, power usage, status)"
- label: "switch / binary_sensor"
description: "On/off controls or binary state readings"
- label: "light"
description: "Dimmable or colour-controllable lights"
- label: "climate / other"
description: "Thermostats, covers, fans, media players, or other platforms"
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.
- 2d ago First seen · 137 lines · 16 tokens per session scan A cea818c52771
scaffold-integration is a command published in the GitHub repository L3DigitalNet/Claude-Code-Plugins (6 stars, last pushed 2d ago), licensed MIT. It adds 16 tokens to every session and 1,229 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 2026-08-31.
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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.
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.