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/fmind/dot/genkitnpx skills add fmind/dot --skill genkitgit clone --depth 1 https://github.com/fmind/dotWrote 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/fmind/dot/genkit)<a href="https://agentmods.dev/skills/fmind/dot/genkit"><img src="https://agentmods.dev/badge/skills/fmind/dot/genkit.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 | $0.00045 | $0.00850 |
| Opus 5 | $0.00023 | $0.00425 |
| Sonnet 5 | $0.00009 | $0.00170 |
| Haiku 4.5 | $0.00005 | $0.00085 |
Grade A, and why
genkit 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 yesterday.
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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Genkit
Genkit is Firebase's framework for AI features inside an application: flows, tools, Dotprompt files, RAG, and a developer UI with traces. Agents that need multi-agent trees, A2A, or Agent Runtime stay on google-adk; Genkit fits TypeScript apps that already run on Firebase or Cloud Run.
1. Setup
- CLI:
genkitfrom mise (npm:genkit-cli); the upstream skill states the minimum CLI version it expects. - Packages: TypeScript
genkitand@genkit-ai/google-genai(googleAI()plugin); Gogithub.com/firebase/genkit/go/{genkit,ai,plugins/googlegenai}; Pythongenkit. - Docs:
genkit docs:search "<topic>" <language>answers API questions from the current documentation, not memory.
2. Development Loop
genkit start -- pnpm exec tsx --watch src/index.ts # TypeScript: dev UI on http://localhost:4000 with traces
genkit start -- go run . # Go
genkit flow:run <flowName> '{"input": "..."}' -- pnpm exec tsx src/index.ts # non-interactive run for tests and CI
genkit trace:list && genkit trace:get <id> --format json # inspect what the model and tools did
- Run flows through
genkit startorflow:run; a plainnode/go runskips trace capture and debugs blind. genkit startdoes not exit; automation usesflow:run.- Wrap the loop in the canonical tasks:
watchstarts the dev UI,testcallsflow:runagainst fixtures, per mise.
3. Rules
- Typed flows: Zod (TypeScript) or struct (Go) schemas on every flow input and output; the schema is the contract the UI and tests use.
- Prompts as files:
.prompt(Dotprompt) files beside the code, versioned and reviewed like code per prompt-design. - Model pins: name the model generation explicitly; keep the plugin config in the typed project config, keys in env or Secret Manager.
- Deploy: Cloud Functions for Firebase (
@genkit-ai/firebase) per firebase, or a container per cloud-run. - Evaluate:
genkit eval:flowdatasets before shipping a prompt change; compare against a baseline per agent-evaluation.
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.
- yesterday First seen · 56 lines · 45 tokens per session scan A 69d382838a07
genkit is a skill published in the GitHub repository fmind/dot (4 stars, last pushed today), licensed MIT. It adds 45 tokens to every session and 850 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
prompt-design
Design production LLM or agent prompt stacks: instructions, tool contracts, examples, outputs, and runtime context. Use for precedence, conflicts, dynamic or untrusted context; prove behavior with agent-evaluation.
agent-evaluation
Evaluate stochastic LLM/RAG/model/retrieval/tool agents in trials. Compare baseline/candidate on development/sealed holdouts with calibrated deterministic/model/trace graders; measure reliability, variance, leakage, safety, and cost.
prompt-engineering
Draft, review, or improve a prompt for an LLM or agent against a research-backed rubric — explicit instructions, instruction/data separation, output contracts, reasoning scaffolds, grounding, verification, and evals. Use when writing a prompt, auditing one that misbehaves, or explaining a prompting principle.
go-stack
Build Go projects, libraries, CLIs, TUIs, web apps, or ADK agents with the standard package layout and pinned tooling.
python-stack
Build typed Python projects with uv, Ruff, ty, pytest, Litestar, and Typer. Use for packages, CLIs, web apps, tests, typing, or API verification.
k8s-local
Create and manage local Kubernetes clusters (k3d or kind) and deploy to them with kubectl, helm, helmfile, and skaffold. Use for local k8s cluster setup, dev loops, and debugging.