baml-test

A command for running tests in a BAML project. BAML tests check whether AI-based extraction functions produce the expected structured results.

In plain words
What is it for?
Use it to run the full BAML test suite, filter tests by name, run tests in parallel, inspect verbose results, and review failures.
Why use it?
It gives one repeatable way to run all tests or focus on selected tests, with optional parallel execution and detailed output.

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/agentic-insights/foundry/baml-test
Clone the repo
git clone --depth 1 https://github.com/Agentic-Insights/foundry
Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 435 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 $0.00007 $0.00435
Opus 5 $0.00003 $0.00217
Sonnet 5 $0.00001 $0.00087
Haiku 4.5 $0.00001 $0.00044

Measured 2d ago against content hash 85be083e86e1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

baml-test 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 2d 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.

plugins/baml/commands/baml-test.md · 77 lines

What it actually says

Run BAML Tests

Execute BAML test suite with options.

Quick Usage

# Run all tests
baml-cli test

# Filter by name
baml-cli test --filter "$ARGUMENTS"

# Parallel execution
baml-cli test --parallel 5

# Verbose output
baml-cli test --verbose

Default Behavior

If $ARGUMENTS is empty, run all tests:

baml-cli test

If $ARGUMENTS contains a filter pattern:

baml-cli test --filter "$ARGUMENTS"

Options Parsing

Parse $ARGUMENTS for:

  • -p N or --parallel N: Run with N parallel workers
  • -v or --verbose: Show detailed output
  • -f PATTERN or --filter PATTERN: Filter test names
  • Any other text: Use as filter pattern

Example Commands

/baml-test                    → baml-cli test
/baml-test Receipt            → baml-cli test --filter "Receipt"
/baml-test -p 5               → baml-cli test --parallel 5
/baml-test Receipt -v         → baml-cli test --filter "Receipt" --verbose
/baml-test -p 3 -f Extract    → baml-cli test --parallel 3 --filter "Extract"

Output Format

Report:

  1. Command executed
  2. Test results (pass/fail counts)
  3. Failure details if any
  4. Suggestions for failures

On Failure

If tests fail:

  1. Show which tests failed
  2. Show assertion that failed
  3. Show expected vs actual (if available)
  4. Suggest using /baml-diagnose for deeper analysis

Prerequisites

  • baml_src/ directory exists
  • baml-cli is installed
  • Environment variables are set
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. 2d ago First seen · 77 lines · 0 tokens per session scan A 85be083e86e1

Subscribe to this mod's changes

baml-test is a command published in the GitHub repository Agentic-Insights/foundry (5 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 7 tokens to every session and 435 once invoked, about $0.0000 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.