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/ch-bas/kibana-plugin-helper/fast-devgit clone --depth 1 https://github.com/ch-bas/kibana-plugin-helperWhat 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 | $0.00031 | $0.01027 |
| Opus 5 | $0.00015 | $0.00513 |
| Sonnet 5 | $0.00006 | $0.00205 |
| Haiku 4.5 | $0.00003 | $0.00103 |
Grade A, and why
fast-dev scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl http://localhost:3000/api/your_plugin/items How it starts
The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Set Up Fast Development Environment
Configure your plugin for maximum development speed. Ask the user:
-
What's your biggest bottleneck?
- Waiting for Kibana to start
- Route changes requiring restarts
- Testing UI components
- Running integration tests
- All of the above
-
Do you have Elasticsearch running locally?
- Yes (we'll connect the mock server to it)
- No (we'll use fully mocked ES)
-
Which parts of your plugin are you actively developing?
- Server routes
- React components
- Saved object types
- Embeddables
- All of the above
Generation Steps
Based on answers, generate the appropriate setup:
For Route Development: Mock Server
Create dev/mock-server/ with the mock server that simulates Kibana's core APIs:
# Start mock server (< 1 second startup)
cd dev/mock-server && npm install && npm start
Routes are available at http://localhost:3000/api/your_plugin/... with hot reload.
For UI Development: Storybook
Create .storybook/ config and example stories:
# Run Storybook (no Kibana needed)
yarn storybook your-plugin
For Unit Tests: Jest with Mocks
Create test/mocks/ with pre-configured Kibana core mocks:
# Run tests in watch mode (instant feedback)
yarn jest plugins/your-plugin --watch
For Faster Kibana Startup: Optimized Config
Create kibana.dev.yml with disabled plugins and optimized settings:
# Start Kibana with minimal plugins
yarn start --config kibana.dev.yml
For Integration Tests: Functional Test Config
Create test/api_integration/config.ts for lighter-weight API testing.
Files to Generate
Depending on selections, create:
your-plugin/
├── dev/
│ └── mock-server/ # Standalone route testing
│ ├── mock-server.mjs
│ ├── package.json
│ └── README.md
├── .storybook/ # UI component development
│ ├── main.ts
│ └── preview.tsx
├── test/
│ ├── mocks/ # Kibana core mocks for Jest
│ │ ├── core_mocks.ts
│ │ ├── es_client_mock.ts
│ │ └── saved_objects_mock.ts
│ └── api_integration/ # Lightweight integration tests
│ └── config.ts
├── kibana.dev.yml # Fast Kibana startup config
└── scripts/
└── dev.sh # One-command dev environment
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 · 160 lines · 31 tokens per session scan A b6eccac022ec
fast-dev is a command published in the GitHub repository ch-bas/kibana-plugin-helper (3 stars, last pushed 6mo ago), licensed MIT. It adds 31 tokens to every session and 1,027 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
status
Show tlive daemon, channel, and Codex companion status.
url
Print the tlive web terminal/dashboard link + QR code.
dead-code-scan
Scan for dead code, unused imports, duplicates, and zombie code across the project.
esp-teach
One-time project setup -- discover hardware, find datasheets, persist context to CLAUDE.md.
dead-code-clean
Actively find and remove dead code, unused imports, duplicates, and zombie code.
swift-critique
Critique SwiftUI code for patterns, design, clean code, accessibility, and performance.