Afm

What it does

When your agent uses it

• Working on AFM CLI commands (afm
• OpenAI /v1/chat/completions and /v1/models behavior
• Structured outputs
• Reasoning extraction

Example prompts

• “/afm”

Workflow steps

7 steps, taken from the step headings in SKILL.md.

1. 1Overview and Triggers
2. 2Key File Reference
3. 3Core Rules
4. 4Quick Start Commands
5. 5Primary Workflow
6. 6Reference Links
7. 7Validation Checklist

What it can do on your machine

Read from SKILL.md and the folder at commit 138ca5d. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • make
  • curl

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md. Its commands use curl, which can reach the network depending on how they are called.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Afm loads about 1.2k tokens when it runs, and up to ~5.5k if it reads all its reference files. Until then it costs about 111 tokens; SKILL.md has 364 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~111

When it runs · the whole SKILL.md, loaded when a task matches

~1.2k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~5.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from scouzi1966/maclocal-api at commit 138ca5d, republished under its MIT licence (© scouzi1966). 364 words, ~1,246 tokens.

name

afm

description

Maintain and extend AFM (maclocal-api), a Swift OpenAI-compatible local LLM server and CLI for Apple Foundation Models, MLX models, API gateway proxying, and Vision OCR. Use when working on AFM CLI commands (`afm`, `afm mlx`, `afm vision`), OpenAI `/v1/chat/completions` and `/v1/models` behavior, streaming SSE, tool-calling, structured outputs, reasoning extraction, AFMKit integration, WebUI packaging, or AFM build/test/release scripts.

# Build against the exact AFMKit release
make build

# Debug build
make debug

# Full bootstrap build
./Scripts/build-from-scratch.sh

# Provider boundary
./Scripts/check-afmkit-consumer-boundary.sh

# Run Foundation server
./.build/debug/afm -p 9999 -v

# Run MLX server
./.build/debug/afm mlx -m mlx-community/Qwen3-0.6B-4bit -p 9999 -v

# Single prompt
./.build/debug/afm mlx -m mlx-community/Qwen3-0.6B-4bit -s "hello"

# Vision OCR
./.build/debug/afm vision -f media/ocr.png

© scouzi1966, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 10 other files (references) in skills/afm of scouzi1966/maclocal-api.

• SKILL.md
• references/api-contract.md
• references/architecture.md
• references/cli-and-modes.md
• references/gateway-discovery-and-proxy.md
• references/mlx-inference-and-tool-calling.md
• references/patch-build-test.md
• test-reports/mlx-model-report-20260226_212226.html
• test-reports/mlx-model-report-20260226_212226.jsonl
• test-reports/mlx-model-report-20260226_232519.html
• test-reports/mlx-model-report-20260226_232519.jsonl

Open the folder on GitHubat commit 138ca5d