Borrowing it
Nothing to install: this file belongs to SShadowS/tree-sitter-al. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/SShadowS/tree-sitter-al/main/.claude/skills/al-file-validation/SKILL.mdgit clone --depth 1 https://github.com/SShadowS/tree-sitter-alWrote 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.
[](https://agentmods.dev/skills/sshadows/tree-sitter-al/al-file-validation)<a href="https://agentmods.dev/skills/sshadows/tree-sitter-al/al-file-validation"><img src="https://agentmods.dev/badge/skills/sshadows/tree-sitter-al/al-file-validation/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/sshadows/tree-sitter-al/al-file-validation"><img src="https://agentmods.dev/badge/skills/sshadows/tree-sitter-al/al-file-validation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 131 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 5.1 | $0.00088 | $0.02384 |
| Opus 5.5 | $0.00035 | $0.00954 |
| Sonnet 5.5 | $0.00018 | $0.00477 |
| Haiku 4.5 | $0.00009 | $0.00238 |
Grade A, and why
AL File Total Validation 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 2mo 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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AL File Total Validation
tree-sitter parse file.al answering "no errors" says almost nothing. Every
defect found in 4.0.0 — 574,694 dropped bytes, three inverted precedence
levels, two node types shipping two shapes each, an omitted list separator
silently absorbed as an extra element — produced a clean error count. An
error count can only see what the parser noticed going wrong. It cannot see
what the parser lexed and threw away, or attached to the wrong parent, or
grouped the wrong way round.
This skill answers the two questions that actually matter, separately:
| question | fails when | |
|---|---|---|
| Completeness | does everything in the source reach the tree? | a token is lexed and dropped; a construct produces no node; a node is unreachable by any query |
| Soundness | is everything the tree claims true of the source? | a required field is empty; a captured span disagrees with the file |
Run it
./tools/ts-lock.sh python tools/validate_al_file.py path/to/File.al
./tools/ts-lock.sh python tools/validate_al_file.py path/to/File.al --json
./tools/ts-lock.sh python tools/validate_al_file.py --self-test
Wrap in tools/ts-lock.sh — it builds the shared al.dll that every worktree
of this repo shares by grammar name, and a concurrent build corrupts it
without either run erroring.
Exit 0 all gating checks passed · 1 a gating check failed · 2 could not
run. --strict-reachability promotes the reachability NOTE to a gating check.
The seven checks
Each is written so it CAN fail, and --self-test proves each one does by
breaking something on purpose and requiring the right check — not merely
some check — to report it.
-
parse-integrity — ERROR and MISSING nodes with positions. Deliberately first and deliberately the weakest: it is the check every other tool in the repo already performs, and it is the one that missed every 4.0.0 defect.
-
byte-roundtrip (completeness) — reconstructs the file from its leaf nodes and the gaps between them, and requires the result to be byte-identical to the source. A gap holding anything but whitespace is a byte the parser lexed and dropped. This is the check that would have caught the 574,694, and no error count can substitute for it, because a dropped token leaves no ERROR behind.
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.
- 2mo ago First seen · 189 lines · 88 tokens per session scan A 66cd5351563b
AL File Total Validation is a skill published in the GitHub repository SShadowS/tree-sitter-al (24 stars, last pushed 4d ago), licensed MIT. It adds 88 tokens to every session and 2,384 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.