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 wellwelwel/lagune --skill specializegit clone --depth 1 https://github.com/wellwelwel/laguneWrote 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/wellwelwel/lagune/specialize)<a href="https://agentmods.dev/skills/wellwelwel/lagune/specialize"><img src="https://agentmods.dev/badge/skills/wellwelwel/lagune/specialize/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/wellwelwel/lagune/specialize"><img src="https://agentmods.dev/badge/skills/wellwelwel/lagune/specialize.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 MCP Rug Pull · line 31 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00060 | $0.01639 |
| Opus 5.5 | $0.00024 | $0.00656 |
| Sonnet 5.5 | $0.00012 | $0.00328 |
| Haiku 4.5 | $0.00006 | $0.00164 |
Grade A, and why
specialize 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 1mo 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Authoring a built-in Lagune sub-skill (development workspace)
The end-user command @spec/commands/lagune.specialize.md writes into a scaffolded target project: .lagune/skills/<name>.md and .lagune/skills.json. Neither path exists here. This repo is the Lagune source, where built-in sub-skills live in spec/skills/<name>.md and the catalog is a hardcoded TypeScript array, not a runtime JSON file. There is also no "user" registry: a built-in is registered in code, compiled, scaffolded, and tested.
So you reuse the command's authoring discipline (terrain, defense-only gate, template, tags, reconcile-never-append) but override every output path to the native layout, and you update the registration points the end-user command never has to.
Step 1: Run the command's authoring steps, with redirected paths
Read and follow @spec/commands/lagune.specialize.md in full. Its authoring steps hold unchanged. The one thing that does not is where files are read and written, since the command targets a scaffolded project and you are in the source. Remap every path it names:
| Command path (end-user target) | Native path (use this instead) |
|---|---|
.lagune/skills/{regex,javascript,browser}.md (worked examples) |
every *.md already in spec/skills/ (list the directory, mirror the closest one) |
.lagune/templates/specialize-template.md |
spec/templates/specialize-template.md |
@.lagune/specializations.md (list what exists) |
read spec/skills/ and SKILLS_CATALOG in src/hooks/skills/catalog.ts |
.lagune/skills/<name>.md (the sub-skill file) |
spec/skills/<name>.md |
.lagune/skills.json (catalog entry) |
a BuiltinSkillEntry in src/hooks/skills/catalog.ts |
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.
- 1mo ago First seen · 79 lines · 60 tokens per session scan A e7a39d2049bd
specialize is a skill published in the GitHub repository wellwelwel/lagune (173 stars, last pushed 5d ago), licensed MIT. It adds 60 tokens to every session and 1,639 once invoked, about $0.0002 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
firebase-cloud-functions
Use when calling callable functions (httpsCallable), passing data to server-side logic, handling function errors/timeouts, configuring regions, or testing with the Emulator Suite.
octocode-roast
Use when code needs a blunt evidence-backed roast or memorable critique: smell inventory, debt ranking, hot-path autopsy, savage/diff review, security or performance sins, or practical redemption paths. Phrases like roast this, brutal review, top sins, cleanup debt. Polite evidence-first PR review → octocode-research.
sanity-singletons
Configure singleton documents in a Sanity Studio using the document.singletons registry. Use when a developer wants a fixed-id document (settings, navigation, footer) edited in place, hidden from the default content list, with no "create new" or "duplicate" affordances — or when migrating a userland singleton…
sanity-best-practices
Sanity development best practices for schema design, GROQ queries, TypeGen, Visual Editing, images, Portable Text, Studio structure, localization, migrations, Sanity Functions, webhooks, Blueprints, and framework integrations such as Next.js, Nuxt, Astro, Remix, SvelteKit, Angular, Hydrogen, the App SDK, and Studios…
110-java-maven-best-practices
Use when you need to review, improve, or troubleshoot a Maven pom.xml file — including dependency management with BOMs, plugin configuration, version centralization, multi-module project structure, build profiles, or any situation where you want to align your Maven setup with industry best practices. This should…
023-assumption-analysis
Use when a framed and root-caused problem needs its assumptions made explicit before design or planning begins — explicit Assumptions, Unknowns, and a Validation plan. This should trigger when an issue's Assumption Analysis point of view needs evaluation, or when a maintainer directly asks to surface hidden…