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 sailingnaturali/claude-skills --skill signalk-registrygit clone --depth 1 https://github.com/sailingnaturali/claude-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/sailingnaturali/claude-skills/signalk-registry)<a href="https://agentmods.dev/skills/sailingnaturali/claude-skills/signalk-registry"><img src="https://agentmods.dev/badge/skills/sailingnaturali/claude-skills/signalk-registry/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/sailingnaturali/claude-skills/signalk-registry"><img src="https://agentmods.dev/badge/skills/sailingnaturali/claude-skills/signalk-registry.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 | $0.00082 | $0.04466 |
| Opus 5 | $0.00041 | $0.02233 |
| Sonnet 5 | $0.00016 | $0.00893 |
| Haiku 4.5 | $0.00008 | $0.00447 |
Grade A, and why
signalk-registry scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s "https://signalk.org/signalk-plugin-registry/plugins/$SLUG.json" -o /tmp/sk-reg.json How it starts
The opening of the file, as written. The whole thing — 335 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SignalK Registry Score
The SignalK plugin registry scores every plugin on a 100-point scale and re-tests nightly. This skill does two things:
- Reads the actual published score for the plugin (the ground truth — don't guess it).
- Previews the criteria you can act on locally before the next nightly run, and shows the point cost of each gap.
Our bar: we publish/maintain to 100. Anything below means a gap below is open.
Scoring rubric
The 0–100 score is test-harness/score.ts (base, max 100) minus a plugin-CI penalty applied
in build-api.ts. So without plugin-CI the ceiling is 90, not 100.
| Category | Points | Evaluated |
|---|---|---|
| Installs | 20 | Registry harness only |
| Loads | 15 | Registry harness only |
| Activates | 15 | Registry harness only |
| Schema | 5 | Registry harness only |
| Tests pass | 25 | Registry harness only |
| Security audit | 0–20 | Locally checkable |
| Changelog | −5 if missing | Locally checkable |
| Screenshots | −5 if missing | Locally checkable |
| Plugin-CI | −10 if missing | Locally checkable (workflow file) |
Install / load / activate / schema / tests (80 pts) run in the registry's own harness against a live SignalK server — you can't reproduce them locally, but the published JSON (Check 0) reports their booleans. The rest you can fix in the repo before the next nightly.
Check 0 — actual published score (do this first)
The registry serves each plugin's results as JSON. The slug is the npm name with @ stripped and
/ → __.
PKG=$(node -p "require('./package.json').name") # @sailingnaturali/signalk-currents
SLUG=$(printf '%s' "$PKG" | sed 's/^@//; s#/#__#') # sailingnaturali__signalk-currents
curl -s "https://signalk.org/signalk-plugin-registry/plugins/$SLUG.json" -o /tmp/sk-reg.json
python3 - <<'PY'
import json
d = json.load(open('/tmp/sk-reg.json'))
vers = d.get('versions', {})
latest = max(vers, key=lambda v: [int(x) for x in v.split('.') if x.isdigit()]) if vers else None
slot = (vers.get(latest, {}) or {}).get('server@stable', {}) if latest else {}
print(f"latest tested version: {latest}")
print(f" composite: {slot.get('composite')}")
print(f" badges: {slot.get('badges')}")
print(f" installs/loads/activates: {slot.get('installs')}/{slot.get('loads')}/{slot.get('activates')}")
print(f" tests: {slot.get('test_status')} audit C/H/M: {slot.get('audit_critical')}/{slot.get('audit_high')}/{slot.get('audit_moderate')}")
print(f" plugin_ci: {d.get('plugin_ci', {}).get('status')}")
PY
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 Changed · +8 lines · +21 tokens per session c2473a493f88
- 12d ago First seen · 327 lines · 61 tokens per session scan A 05cb2af0ed05
signalk-registry is a skill published in the GitHub repository sailingnaturali/claude-skills (2 stars, last pushed 7d ago), licensed MIT. It adds 82 tokens to every session and 4,466 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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…