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.
npx agentmods add commands/agentic-insights/foundry/baml-testgit clone --depth 1 https://github.com/Agentic-Insights/foundryWhat 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 | $0.00007 | $0.00435 |
| Opus 5 | $0.00003 | $0.00217 |
| Sonnet 5 | $0.00001 | $0.00087 |
| Haiku 4.5 | $0.00001 | $0.00044 |
Grade A, and why
baml-test scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Run BAML Tests
Execute BAML test suite with options.
Quick Usage
# Run all tests
baml-cli test
# Filter by name
baml-cli test --filter "$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 Nor--parallel N: Run with N parallel workers-vor--verbose: Show detailed output-f PATTERNor--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:
- Command executed
- Test results (pass/fail counts)
- Failure details if any
- Suggestions for failures
On Failure
If tests fail:
- Show which tests failed
- Show assertion that failed
- Show expected vs actual (if available)
- Suggest using
/baml-diagnosefor deeper analysis
Prerequisites
baml_src/directory existsbaml-cliis installed- Environment variables are set
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.
- 2d ago First seen · 77 lines · 0 tokens per session scan A 85be083e86e1
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.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.