Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/JinLee794/agent-framework-skillsnpx agentmods add skills/jinlee794/agent-framework-skills/maf-agent-configWrote 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/jinlee794/agent-framework-skills/maf-agent-config)<a href="https://agentmods.dev/skills/jinlee794/agent-framework-skills/maf-agent-config"><img src="https://agentmods.dev/badge/skills/jinlee794/agent-framework-skills/maf-agent-config/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/jinlee794/agent-framework-skills/maf-agent-config"><img src="https://agentmods.dev/badge/skills/jinlee794/agent-framework-skills/maf-agent-config.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00057 | $0.04318 |
| Opus 5 | $0.00028 | $0.02159 |
| Sonnet 5 | $0.00011 | $0.00864 |
| Haiku 4.5 | $0.00006 | $0.00432 |
Grade A, and why
maf-agent-config 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 10d 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 — 370 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent & Voice Configuration — YAML Contract
Behaviour lives in YAML. Python is wiring.
If changing a value would change what the agent says or does — instructions, model, temperature, which tools are attached, the voice, VAD thresholds, interim phrases — it is a YAML value. Python may only load, validate, and construct.
Use the shipped schema, do not invent one
Agent behaviour is written in MAF's own declarative agent schema (kind: Prompt) and
loaded by the shipped AgentFactory from agent-framework-declarative. Do not hand-roll a
private YAML dialect with bespoke pydantic models — that is a reimplementation of
AgentFactory that no other tool, sample, or language runtime can read.
from agent_framework.declarative import AgentFactory
What this buys, and what inventing a dialect costs:
- The same document loads in Python and .NET (
ChatClientPromptAgentFactory). create_agent_from_yaml_path/..._asyncare maintained upstream, including the provider and connection resolution you would otherwise write by hand.- A
kind: Workflowdocument can reference the agent file directly — see maf-multi-agent-workflows.
Declarative agents are experimental upstream (ExperimentalFeature.DECLARATIVE_AGENTS) and
emit an ExperimentalWarning on first use. Filter that warning at the entry point; do not fork
the schema to avoid it.
What goes where
Three homes, no overlap. Most config bugs are a value in the wrong one.
| Value | Home |
|---|---|
| Instructions, model deployment, temperature, tool list, voice, VAD, interim responses | config/**.yaml |
| Endpoints, resource names, credentials, connection strings | env → settings.py |
| Tool implementations, event loop, audio I/O, orchestration | src/ |
settings.py is the only reader of os.environ in src/. Inside a kind: Prompt
document, environment values are referenced with PowerFx =Env.NAME, which AgentFactory
resolves — see Placeholders.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 370 lines · 57 tokens per session scan A f94569f96a8c
maf-agent-config is a skill published in the GitHub repository JinLee794/agent-framework-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 57 tokens to every session and 4,318 once invoked, about $0.0003 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 skills, from other repositories
claude-on-foundry
End-to-end assistant skill for the Claude on Foundry Starter Kit (Azure-Samples/claude). Walks customers through deploying, verifying, modifying, debugging, and tearing down a Claude model deployment on Microsoft Foundry using either the Bicep or Terraform IaC variant in this repo, with one-command guidance via azd…
aspire-deployment
WORKFLOW SKILL — Deploy Aspire apps from AppHost models to Docker Compose, Kubernetes, Azure, or AWS. WHEN: "deploy Aspire app", "publish Aspire artifacts", "deploy to Azure Container Apps", "generate Kubernetes artifacts", "tear down Aspire deployment". INVOKES: aspire CLI, Aspire docs, target cloud/container CLIs.…
aspire-monitoring
ANALYSIS SKILL - Observe Aspire apps: logs, traces, metrics, resource state, telemetry export, browser telemetry, and the standalone dashboard. Routes between local Aspire CLI, AKS workload diagnostics, and deployed Azure resource health. USE FOR: aspire logs, aspire otel logs, aspire otel traces, aspire otel spans…
entra-a2a-mcp-obo
Best practices, tips, and gotchas for Entra ID, Entra Agent ID, A2A protocol, MCP protocol, and agentgateway-based OBO token exchange — distilled from loop-runtime's entraagentid.md docs. Use when setting up, wiring, or debugging Entra app registrations, Entra Agent ID blueprints, OBO chains, A2A/MCP auth, app-code…
harness-engineering
Adopt repository-level harness engineering for coding agents. Use when a user wants to prevent repeated AI coding-agent mistakes by turning failures into durable instructions, drift checks, regression tests, failure memory, and adoption reports tailored to the target repository.
get-api-docs
Use this skill when you need documentation for a third-party library, SDK, or API before writing code that uses it — for example, "use the OpenAI API", "call the Stripe API", "use the Anthropic SDK", "query Pinecone", or any time the user asks you to write code against an external service and you need current API…