What is codex-promptfoo-agentic-eval?

A Promptfoo-based test workflow for AFM, the system being evaluated for structured output, tool calls, grammar constraints, streaming, concurrency, and agent tasks. It separates AFM bugs, model-quality problems, and test-harness bugs, and records where each test came from.

Use it to choose and run evaluation areas such as tool calling, structured output, agent behavior, frameworks, or OpenCode. It supports different test profiles, serial or concurrent runs, and reviewing existing reports.

It provides a structured way to run or review agent tests instead of judging failures informally. It also makes clear whether a result is functional testing, model evaluation, or both.

codex-promptfoo-agentic-eval — Skill for Claude Code and Codex by scouzi1966: A Promptfoo-based test workflow for AFM, the system being…

Install

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.

agentmods

npx agentmods add skills/scouzi1966/maclocal-api/codex-promptfoo-agentic-eval

Any agent

npx skills add scouzi1966/maclocal-api --skill codex-promptfoo-agentic-eval

Clone the repo

git clone --depth 1 https://github.com/scouzi1966/maclocal-api

Made for: Claude Code, Codex.

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/scouzi1966/maclocal-api/codex-promptfoo-agentic-eval.svg)](https://agentmods.dev/skills/scouzi1966/maclocal-api/codex-promptfoo-agentic-eval)

Your own site

<a href="https://agentmods.dev/skills/scouzi1966/maclocal-api/codex-promptfoo-agentic-eval"><img src="https://agentmods.dev/badge/skills/scouzi1966/maclocal-api/codex-promptfoo-agentic-eval.svg" alt="Measured on agentmods" height="20"></a>

Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,836 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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	$0.00067	$0.01836
Opus 5	$0.00034	$0.00918
Sonnet 5	$0.00013	$0.00367
Haiku 4.5	$0.00007	$0.00184

Measured 4d ago against content hash 72ad070d6678, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codex-promptfoo-agentic-eval 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 4d 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.

.codex/skills/codex-promptfoo-agentic-eval/SKILL.md · 237 lines

How it starts

The opening of the file, as written. The whole thing — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Promptfoo Agentic Eval

Use this skill when the user wants to run, expand, or interpret the Promptfoo agentic suite for AFM.

This skill is for two linked goals:

AFM functional validation
model-quality evaluation for agentic use

Always distinguish:

afm_bug
model_quality
harness_bug

Always report provenance for the suite you run:

afm_internal
primary_source
public_benchmark_inspired
synthetic

Never present a benchmark-inspired or synthetic suite as if it were a public benchmark import.

First questions to ask

Before running the suite, ask the user the minimum needed questions:

Which model should be tested?
Which scope should be run?
- structured
- structured-stress
- toolcall
- toolcall-quality
- agentic
- frameworks
- opencode
- all
- one profile only: default, adaptive-xml, adaptive-xml-grammar
Is the goal:
- AFM functional QA
- model quality
- both
Should the run stay serial/safe, or include concurrency cases?
Should you only review existing reports, or also execute the harness?
Should the run prefer:
- primary-source-only cases
- public-benchmark-inspired cases
- synthetic representative cases
- mixed

If the user does not specify, assume:

model: the repo's current primary MLX model under test
scope: all
goal: both
run mode: serial/safe first
action: execute and then review
provenance preference: mixed, but explicitly labeled

Working directory

Run from:

cd /Volumes/edata/codex/dev/git/maclocal-api/NEXT/maclocal-api

Main assets

Read only what is needed:

Scripts/feature-promptfoo-agentic/README.md
Scripts/feature-promptfoo-agentic/run-promptfoo-agentic.sh
Scripts/feature-promptfoo-agentic/providers/afm_provider.mjs
Scripts/feature-promptfoo-agentic/matrix/functional-matrix.yaml
Scripts/feature-promptfoo-agentic/matrix/failure-classification.yaml
docs/roadmap/promptfoo-agentic-matrix.md

Read the full file on GitHub · 237 lines

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.

4d ago First seen · 237 lines · 67 tokens per session scan A 72ad070d6678

Subscribe to this mod's changes

codex-promptfoo-agentic-eval is a skill published in the GitHub repository scouzi1966/maclocal-api (337 stars, last pushed today), licensed MIT. It adds 67 tokens to every session and 1,836 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 2026-08-30.

Code review Testing ai apple-foundation-models apple-intelligence local-llm macos-app macos-swift

codex-promptfoo-agentic-eval

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

Promptfoo Agentic Eval

First questions to ask

Working directory

Main assets

What this file has done since we first saw it

Other skills, from other repositories

apple-foundation-models-app-patterns

apple-foundation-models-conversation-context-builder

apple-foundation-models-custom-tools

apple-foundation-models-dynamic-schemas

apple-foundation-models-error-recovery

apple-foundation-models-feedback-sentiment-api