baml-diagnose

baml-diagnose is a command for coding agents from Agentic-Insights/foundry. It costs 8 tokens per session (691 once invoked), scanned A, original, Apache-2.0.

A diagnostic command for BAML, a language and toolset for defining AI prompts, data formats, and model clients.

In plain words
What is it for?
Use it to investigate BAML project structure, generator and client settings, missing API keys, schema issues, parse failures, validation failures, and timeouts.
Why use it?
It checks project files, model settings, environment variables, schemas, generated code, and tests to help locate configuration problems.

Command

Part of the baml plugin — 1 skill, 4 commands, 3 agents shipped together

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-diagnose
Clone the repo
git clone --depth 1 https://github.com/Agentic-Insights/foundry

Or install baml, the plugin that ships this one along with the rest of its 1 skill, 4 commands, 3 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.

agentmods badge for baml-diagnose

README.md
[![agentmods](https://agentmods.dev/badge/commands/agentic-insights/foundry/baml-diagnose.svg)](https://agentmods.dev/commands/agentic-insights/foundry/baml-diagnose)
Your own site
<a href="https://agentmods.dev/commands/agentic-insights/foundry/baml-diagnose"><img src="https://agentmods.dev/badge/commands/agentic-insights/foundry/baml-diagnose.svg" alt="Measured on agentmods" height="20"></a>
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 691 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 $0.00008 $0.00691
Opus 5 $0.00004 $0.00345
Sonnet 5 $0.00002 $0.00138
Haiku 4.5 $0.00001 $0.00069

Measured 4d ago against content hash 4a241e2145e1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

baml-diagnose 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.

plugins/baml/commands/baml-diagnose.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Diagnose BAML Issues

Analyze BAML configuration and identify problems.

Diagnostic Checks

1. Project Structure

  • baml_src/ directory exists
  • generators.baml exists and is valid
  • clients.baml exists with at least one client
  • Generated baml_client/ exists

2. Generator Configuration

# Check generator version matches CLI
baml-cli --version

Compare with generators.baml version field.

3. Client Configuration

Verify clients have:

  • Valid provider (openai, anthropic, ollama, etc.)
  • API key reference (env.OPENAI_API_KEY)
  • Valid model name

4. Environment Variables

Check required env vars are set:

echo $OPENAI_API_KEY | head -c 10
echo $ANTHROPIC_API_KEY | head -c 10

5. Schema Validation

Look for common schema issues:

  • Missing {{ ctx.output_format }} in prompts
  • Deeply nested types (3+ levels)
  • Ambiguous field names without @description
  • @assert expressions that may fail unexpectedly

6. Test Health

baml-cli test --parallel 1

Check for:

  • Parse failures
  • Validation failures
  • Timeouts

Arguments

$ARGUMENTS can specify focus area:

  • schema - Check schema files only
  • clients - Check client configuration
  • tests - Run and analyze tests
  • env - Check environment variables
  • (empty) - Run all checks

Output

Provide:

  1. Status - Overall health (✓ OK, ⚠ Warnings, ✗ Issues)
  2. Findings - List of issues found
  3. Recommendations - How to fix each issue
  4. Next Steps - Suggested actions

Example Output

BAML Project Diagnosis
======================

✓ Project Structure
  - baml_src/ found
  - generators.baml valid
  - clients.baml valid

⚠ Client Configuration
  - GPT4 client uses deprecated model name
  - Recommendation: Change "gpt-4" to "gpt-4-turbo"

✗ Environment
  - ANTHROPIC_API_KEY not set
  - Recommendation: Set in .env or environment

⚠ Schema Issues
  - ExtractData function missing ctx.output_format
  - Location: baml_src/extract.baml:15

Tests: 8 passed, 2 failed
  - TestComplexExtraction: Parse error
  - TestImageReceipt: Timeout

Next Steps:
1. Fix ANTHROPIC_API_KEY if using Anthropic
2. Add {{ ctx.output_format }} to ExtractData prompt
3. Run /baml-test TestComplexExtraction to debug

Read the full file on GitHub · 114 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.

  1. 4d ago First seen · 114 lines · 8 tokens per session scan A 4a241e2145e1

Subscribe to this mod's changes

baml-diagnose is a command published in the GitHub repository Agentic-Insights/foundry (5 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 8 tokens to every session and 691 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.