app-eval

A command that runs repeatable evaluations from written test cases called manifests.

In plain words
What is it for?
Use it to run role, policy, workflow, or long-running behavior evaluations and reject missing or malformed test definitions.
Why use it?
It makes agent checks reproducible by defining the command to run, the expected exit code, and evidence that must appear.

Command

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 commands/vmobifystudio/app-dev-team/app-eval
Clone the repo
git clone --depth 1 https://github.com/vmobifystudio/app-dev-team
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 99 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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00099
Opus 5 $0.00000 $0.00049
Sonnet 5 $0.00000 $0.00020
Haiku 4.5 $0.00000 $0.00010

Measured yesterday against content hash dc65bec1192f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

app-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 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.

commands/app-eval.md · 12 lines

What it actually says

/app-eval — run deterministic agent evaluations

Evaluation manifests define reproducible cases with an executable command, expected exit code, and required evidence text:

node "${CLAUDE_PLUGIN_ROOT}/scripts/eval-lab.mjs" --manifest eval/manifest.json

Add role, policy, workflow, and long-horizon fixtures as the team grows. A missing manifest or malformed case is CANNOT EVALUATE, never a passing empty suite.

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.

  1. yesterday First seen · 12 lines · 0 tokens per session scan A dc65bec1192f

Subscribe to this mod's changes

app-eval is a command published in the GitHub repository vmobifystudio/app-dev-team (4 stars, last pushed 22d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 99 tokens. 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.