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/sshadows/tree-sitter-al/releasegit clone --depth 1 https://github.com/SShadowS/tree-sitter-alWhat 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 | $0.03375 |
| Opus 5 | $0.00000 | $0.01688 |
| Sonnet 5 | $0.00000 | $0.00675 |
| Haiku 4.5 | $0.00000 | $0.00337 |
Grade A, and why
release 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.
How it starts
The opening of the file, as written. The whole thing — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release tree-sitter-al
Execute the full release process for tree-sitter-al. This publishes to GitHub Releases, npm, PyPI, and crates.io.
All three registries authenticate with OIDC trusted publishing. There are no publish tokens stored in the repository.
Pre-flight Checks
Before starting, verify:
-
All tests pass:
tree-sitter test -
Production validation:
./parse-al-parallel.sh ./BC.History/ .(0 errors) -
No unexpected ERROR/MISSING nodes in any test — this must print nothing:
grep -rn "(ERROR\b\|(MISSING\b" test/corpus/ --include="*.txt" \ | grep -v "ERROR(" \ | grep -vE "(^|/)(option_members_tabledata_keyword_test|pragma_whitespace_tolerance_test|preproc_if_elif_whitespace_tolerance_test|preproc_region_whitespace_audit_test|scanner_var_attribute_token_span_test|directive_word_boundary_test|scanner_unicode_identifier_negative_test|range_not_an_expression_negative_test|preproc_split_operator_negative_test|interface_access_negative_test|missing_separator_negative_test)\.txt:"The
(^|/)…\.txt:anchoring is load-bearing.grep -rnemitspath:lineno:content, so an unanchored name matches anywhere in the line — including the matched source text — and would silently exempt any future fixture whose content happens to mention one of these names. Anchored, the name must be the file's own basename, which is exactly the comparisonvalidate-grammar.shmakes.Both alternatives need the opening paren. This search previously read
MISSING\bwithout it, whileERRORrequired(ERROR\b. Expected trees write these as(MISSING xyz)and(ERROR), so the bare form matched the word anywhere on a line — a fixture title or a prose comment containing "MISSING" failed the release.validate-grammar.shStep 3 anchors its equivalent search to line starts and was never affected, so the two gates disagreed on what counts as a hit. Found by writing a fixture titled with the bare word.
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 · 249 lines · 0 tokens per session scan A 576f4fd7d0d9
release 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 3,375 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.
Other commands, from other repositories
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.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.