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 skills add fubits1/svelte-skills --skill validate-filegit clone --depth 1 https://github.com/fubits1/svelte-skillsWrote 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/fubits1/svelte-skills/validate-file)<a href="https://agentmods.dev/skills/fubits1/svelte-skills/validate-file"><img src="https://agentmods.dev/badge/skills/fubits1/svelte-skills/validate-file/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/fubits1/svelte-skills/validate-file"><img src="https://agentmods.dev/badge/skills/fubits1/svelte-skills/validate-file.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00044 | $0.01348 |
| Opus 5 | $0.00022 | $0.00674 |
| Sonnet 5 | $0.00009 | $0.00270 |
| Haiku 4.5 | $0.00004 | $0.00135 |
Grade A, and why
validate-file 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 9d 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Validate File
Run the correct validation for every file you edited OR have been prompted to review. No exceptions.
Code style compliance
Before and during validation, apply the rules from these skills:
frontend:code-style: applies to ALL files (variable naming, braces, data attributes)svelte-5:code-style-svelte: applies to.svelteand.svelte.ts/.svelte.jsfiles
Hard rules
- NEVER use
any. Type it properly. If the type doesn't exist, create a local type or import the right one. - NEVER add
eslint-disablewithout a FIXME or TODO. Every disable must explain what needs to be fixed and why it can't be fixed now. Bare disables are cheating. - Fix ALL lint errors in the file: not just the ones you introduced. If you touch a file and lint reports errors, fix them. No "pre-existing" excuses.
When to run
After EVERY file edit. Not at the end of a batch, after EACH edit. If you edited 3 files, you validate 3 times (or group by tool).
What to run
Batch-lint multiple files
To lint every file currently staged in git, use pnpm lint:staged.
To also include commits ahead of the upstream branch (or, when no upstream is set, commits not yet on any remote), use pnpm lint:staged --committed — useful right before pushing.
lint:staged calls into the same lint-file chain documented below, so all the per-file rules still apply.
Lint single files
| File type | Command | Notes |
|---|---|---|
.svelte, .ts, .js |
pnpm lint:file <path> [path2...] |
Runs eslint + oxlint + tsgo + svelte-check + knip |
.stories.svelte |
pnpm lint:file <path> AND pnpm test:story <Pattern> |
Both. Lint AND test. |
.test.ts, .spec.ts |
pnpm lint:tests |
Lints all test files |
.md |
npx markdownlint-cli <path> |
Fix all errors before done |
.yml/.yaml (CI) |
Simulate with CI=true GITHUB_ACTIONS=true locally |
Never guess at CI behavior |
vite.config.ts |
npx tsgo -p tsconfig.node.json --noEmit |
Separate tsconfig, pnpm check won't catch it |
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.
- 9d ago First seen · 127 lines · 44 tokens per session scan A 7c0d82b1199c
validate-file is a skill published in the GitHub repository fubits1/svelte-skills (10 stars, last pushed 1mo ago), licensed MIT. It adds 44 tokens to every session and 1,348 once invoked, about $0.0002 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 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".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
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.