A grammar-checking command for tree-sitter-al, a parser that turns AL source code into a structured syntax tree. It generates the parser, runs tests, checks grammar health, and looks for suspicious definitions and test errors.

Use it after changing the grammar or before committing parser work to run the project's full validation checks.

It helps catch broken grammar changes, regressions, unused rules, duplicate rule names, and parser errors in one review.

validate — Command by SShadowS

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/sshadows/tree-sitter-al/validate

Clone the repo

git clone --depth 1 https://github.com/SShadowS/tree-sitter-al

Made for: Claude Code.

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 530 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	$0.00000	$0.00530
Opus 5	$0.00000	$0.00265
Sonnet 5	$0.00000	$0.00106
Haiku 4.5	$0.00000	$0.00053

Measured 2d ago against content hash 31f4e366f2f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

validate 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.

.claude/commands/validate.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Grammar Validation Agent

You are a grammar validation agent for tree-sitter-al. Run comprehensive validation and report results clearly.

Validation Steps

Run these steps in order, collecting results:

Step 1: Generate Parser

tree-sitter generate 2>&1

Check for warnings about unnecessary conflicts
Report any generation errors

Step 2: Run Test Suite

tree-sitter test 2>&1

Count passed and failed tests
List any failing test names

Step 3: Health Check (Regression Detection)

python3 tools/check_grammar_health.py 2>&1

Compare current state to baseline
Report any regressions or improvements

Step 4: Unused Definitions

python3 tools/find_unused_definitions.py 2>&1

Report unused rules (potential dead code)
Report low-usage rules that may need review

Step 5: Duplicate Rule Keys

python3 tools/analyze_duplicates.py 2>&1

Report grammar.js rule keys defined more than once in rules: { ... }
Distinguishes byte-identical duplicates (dead weight) from differing ones (a live bug: JavaScript silently discards the earlier definition)

Step 6: ERROR/MISSING Nodes in Tests

grep -r -l "^\s*(ERROR\|^\s*(MISSING" test/corpus/*.txt 2>/dev/null || echo "None found"

List test files containing ERROR or MISSING nodes
These indicate parsing issues

Output Format

Provide a clear summary in this format:

## Grammar Validation Report

### Generation: ✅/❌
- [details]

### Tests: ✅/⚠️/❌
- Passed: X
- Failed: Y
- [list failing tests if any]

### Health Check: ✅/⚠️/❌
- [regressions or improvements]

### Code Quality: ✅/⚠️
- Unused rules: X
- Duplicate rule keys: Y

### Action Items
1. [prioritized list of issues to fix]

After Validation

If all checks pass, suggest:

Running python3 tools/check_grammar_health.py --save-baseline if changes were made

If checks fail, prioritize:

Fix test failures first
Then address health check regressions
Finally clean up unused rules

Read the full file on GitHub · 87 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.

2d ago First seen · 87 lines · 0 tokens per session scan A 31f4e366f2f9

Subscribe to this mod's changes

validate is a command published in the GitHub repository SShadowS/tree-sitter-al (24 stars, last pushed 20d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 530 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 2026-08-30.

Testing

validate

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Grammar Validation Agent

Validation Steps

Step 1: Generate Parser

Step 2: Run Test Suite

Step 3: Health Check (Regression Detection)

Step 4: Unused Definitions

Step 5: Duplicate Rule Keys

Step 6: ERROR/MISSING Nodes in Tests

Output Format

After Validation

What this file has done since we first saw it

Other commands, from other repositories

checklist

clarify

specify

analyze

converge

implement