An adapter for running and checking Markdown-based agent skills inside Microsoft's Agent Framework, a platform for building software agents. It includes a local simulator and checks whether plugin files match the framework's expected structure.

Use it to simulate a skill locally, validate plugin manifests, check command targets, and verify required frontmatter fields.

It helps identify invalid manifests, missing command files, and malformed skill instructions before loading them into the framework.

maf-adapter — Skill for Claude Code by richfrem/agent-plugins-skills

Install

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.

Clone the repo

git clone --depth 1 https://github.com/richfrem/agent-plugins-skills

agentmods

npx agentmods add skills/richfrem/agent-plugins-skills/maf-adapter

Made for: Claude Code.

Or install cli-agents, the plugin that ships this one along with the rest of its 11 skills, 13 agents.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/maf-adapter/github.svg)](https://agentmods.dev/skills/richfrem/agent-plugins-skills/maf-adapter)

Your own site

<a href="https://agentmods.dev/skills/richfrem/agent-plugins-skills/maf-adapter"><img src="https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/maf-adapter/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/richfrem/agent-plugins-skills/maf-adapter"><img src="https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/maf-adapter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 563 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00028	$0.00563
Opus 5.5	$0.00011	$0.00225
Sonnet 5.5	$0.00006	$0.00113
Haiku 4.5	$0.00003	$0.00056

Measured 18d ago against content hash 09e921e750f4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

maf-adapter 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 18d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/test_harness.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/cli-agents/skills/maf-adapter/SKILL.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Microsoft Agent Framework Adapter (maf-adapter)

Validates plugin manifests and simulates agent skill execution within the Microsoft Agent Framework (MAF v1.6/v1.7+).

Critical Constraints
Quick start
Workflow
Verification
References

Critical Constraints

Manifest Hygiene: Manifests loaded into MAF must omit banned/unsupported fields (skills, agents, hooks).
Frontmatter Requirement: All skills must include valid YAML frontmatter blocks delimited by --- with name and allowed-tools.
Local Simulation First: Test and simulate skills locally via test_harness.py before deploying to Azure Agent Service.
Read-Only Test Frame: The simulation harness must execute in read-only mode without mutating the target skill or plugin files.

Quick start

# Validate plugin manifest for MAF compatibility
python3 plugins/cli-agents/scripts/test_harness.py --validate --plugin plugins/<plugin>

# Simulate skill execution locally under MAF
python3 plugins/cli-agents/scripts/test_harness.py \
  --skill plugins/<plugin>/skills/<skill-name> \
  --instruction "Analyze workspace"

Workflow

Phase 1: Manifest Validation: Run test_harness.py --validate against the target plugin directory to verify schema compatibility and absence of banned root keys.
Phase 2: Frontmatter Verification: Verify that the target skill's SKILL.md contains valid frontmatter declaring allowed tools and clean descriptions.
Phase 3: Execution Simulation: Execute test_harness.py --skill with mock input context to assemble and verify the MAF execution frame.
Phase 4: Output Inspection: Review the generated execution frame to verify clean parameter passing and tool bounds.

Verification

# Validate plugin manifest
python3 plugins/cli-agents/scripts/test_harness.py --validate --plugin plugins/cli-agents

# Audit skill compliance
python3 plugins/agent-scaffolders/scripts/audit_skill.py plugins/cli-agents/skills/maf-adapter --mode source

Read the full file on GitHub · 58 lines

Files

What ships with it

4 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.

Changes

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.

18d ago Changed · +19 lines · -1 tokens per session 09e921e750f4
1mo ago First seen · 39 lines · 29 tokens per session scan A bbf507eb7138

Subscribe to this mod's changes

maf-adapter is a skill published in the GitHub repository richfrem/agent-plugins-skills (7 stars, last pushed yesterday), licensed MIT. It adds 28 tokens to every session and 563 once invoked, about $0.0001 per session on Opus 5.5. 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.

Building agents Testing agent-evaluation agent-orchestration agentic-control-plane agentic-os agentic-workflows ai-agent-governance

qa

Run scalable, isolated live QA for nac development. The top-level local orchestrator must parse n (default 4), dispatch one setup worker with this skill, copy its n assignment contracts verbatim into exactly n parallel test workers with this skill, then dispatch one aggregate worker with this skill using all test…

arcee-ai/nac · 100 tokens

maf-adapter

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Microsoft Agent Framework Adapter (maf-adapter)

Contents

Critical Constraints

Quick start

Workflow

Verification

What ships with it

What this file has done since we first saw it

Other skills, from other repositories

qa

ap-independent-checker

ap-execharness-resolver

ap-implementer

ap-verifier

codew-release-qa-sweep