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 skills/layzeedk/angular-typechecker/spike-findings-angular-typecheckernpx skills add LayZeeDK/angular-typechecker --skill spike-findings-angular-typecheckergit clone --depth 1 https://github.com/LayZeeDK/angular-typecheckerWrote 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/layzeedk/angular-typechecker/spike-findings-angular-typechecker)<a href="https://agentmods.dev/skills/layzeedk/angular-typechecker/spike-findings-angular-typechecker"><img src="https://agentmods.dev/badge/skills/layzeedk/angular-typechecker/spike-findings-angular-typechecker.svg" alt="Measured on agentmods" 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 | $0.00140 | $0.01495 |
| Opus 5 | $0.00070 | $0.00747 |
| Sonnet 5 | $0.00028 | $0.00299 |
| Haiku 4.5 | $0.00014 | $0.00150 |
Grade A, and why
spike-findings-angular-typechecker 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 5d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
An Nx plugin that runs the COMPLETE Angular type-check (TypeScript + template type-check + extended NG8xxx diagnostics), no-emit, decoupled from build/test, per project. Two spike ideas are packaged here: (1) the SHIPPED v0.1.0 solution-tsconfig reference-walk engine, and (2) the v0.1.2 Storybook type-check gate -- one boundary-filter correctness fix (directory-containment -> compiler input-set membership) whose motivating case is the centralized Storybook host.
Spike sessions wrapped: 2026-07-01 (001-005), 2026-07-05 (006-008), 2026-07-07 (009-010).
v0.1.2 Storybook boundary (Phase 16 gate = GO)
- Charter: never a silent false pass; over-report (false FAIL) is the safe direction.
- Replace directory-containment with a pure
keep(diagnostic, inputSet, options) -> booleankeyed on compiler input-set membership; route BOTH the walk and the direct single-leaf path through it; ZERO ngtsc/component-registry internals (structuralgit grepgate). - Key
inputTson the DECLAREDreadConfiguration(leaf).rootNames(NOTprogram.getRootFileNames(), which adds.ngtypecheck.tsshims -- spike 006). - External-template branch = 4a (spike 008: G1 = html, G5 = PASS): map the
.htmldiagnostic to its owning component.tsvia publicts.Diagnostic.relatedInformation; keep iff that.tsis ininputTs; default-KEEP the unmappable edge (fail-safe). - Split the suppressed counter into
suppressedThirdParty+suppressedInGraph; surface both loudly in stdout AND the structured result;suppressedInGraph > 0=> non-clean coverage-incomplete. - Check the WHOLE tsconfig-declared set, never a
*.stories.tsallowlist. No Storybook-specific machinery (no version gate/selector/option).@storybook/angular@10peer incompatibility is docs-only (D4).
v0.1.0 reference-walk engine (shipped)
- Union-then-single-
finalize; dedupe identity =ts.sortAndDeduplicateDiagnostics; counts explicit by category; walk skips out-of-project refs (skip-with-notice); D-03a three-way split atrootNames === 0; walk Nx inputs use thedefaultnamed input; benchmark with Vitestbench.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 87 lines · 0 tokens per session scan A e22cc689a51e
spike-findings-angular-typechecker is a skill published in the GitHub repository LayZeeDK/angular-typechecker (11 stars, last pushed 27d ago), licensed MIT. It adds 140 tokens to every session and 1,495 once invoked, about $0.0007 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…