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 anthillnet/sinain-hud --skill sinain-hud-plugingit clone --depth 1 https://github.com/anthillnet/sinain-hudWrote 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/anthillnet/sinain-hud/sinain-hud-plugin)<a href="https://agentmods.dev/skills/anthillnet/sinain-hud/sinain-hud-plugin"><img src="https://agentmods.dev/badge/skills/anthillnet/sinain-hud/sinain-hud-plugin.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 5.1 | $0.00000 | $0.03251 |
| Opus 5 | $0.00000 | $0.01625 |
| Sonnet 5 | $0.00000 | $0.00650 |
| Haiku 4.5 | $0.00000 | $0.00325 |
Grade A, and why
sinain-hud-plugin 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 7d 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.
The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
What ships with it
60 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.
- __tests__/platform-blocker.test.js 2.4 KB runs code
- .env.example 15 B
- .npmignore 172 B
- cli.js 15 KB runs code
- config-shared.js 28 KB runs code
- config.js 6.1 KB runs code
- encrypted-store.js 8.8 KB runs code
- HEARTBEAT.md 2.0 KB
- index.ts 40 KB runs code
- install.js 17 KB runs code
- launcher.js 40 KB runs code
- LICENSE 4.0 KB
- mcp-register.js 20 KB runs code
- onboard.js 26 KB runs code
- openclaw.plugin.json 2.0 KB
- pack-prepare.js 1.8 KB runs code
- package-lock.json 1.5 KB
- package.json 2.1 KB
- packages 11 B
- README.md 19 KB
- self-update.js 4.8 KB runs code
- sense_client 15 B
- setup-embedding.js 6.3 KB runs code
- setup-frpc.js 5.4 KB runs code
- setup-overlay.js 9.6 KB runs code
- setup-sck-capture.js 6.4 KB runs code
- sinain-agent-runner 22 B
- sinain-chat-agent 20 B
- sinain-core 14 B
- sinain-knowledge/adapters/generic/adapter.ts 3.2 KB runs code
- sinain-knowledge/adapters/interface.ts 2.6 KB runs code
- sinain-knowledge/adapters/openclaw/adapter.ts 8.1 KB runs code
- sinain-knowledge/curation/engine.ts 21 KB runs code
- sinain-knowledge/curation/resilience.ts 13 KB runs code
- sinain-knowledge/data/git-store.ts 12 KB runs code
- sinain-knowledge/data/schema.ts 2.4 KB runs code
- sinain-knowledge/data/snapshot.ts 7.6 KB runs code
- sinain-knowledge/data/store.ts 21 KB runs code
- sinain-knowledge/deploy/cli.ts 7.7 KB runs code
- sinain-knowledge/deploy/manifest.ts 2.0 KB runs code
- sinain-knowledge/protocol/bindings/generic.md 116 B
- sinain-knowledge/protocol/bindings/openclaw.md 144 B
- sinain-knowledge/protocol/heartbeat.md 2.0 KB
- sinain-knowledge/protocol/renderer.ts 1.7 KB runs code
- sinain-knowledge/protocol/skill.md 14 KB
- sinain-mcp-server 20 B
- sinain-memory/asr_nec.py 16 KB runs code
- sinain-memory/category_enrichment.py 19 KB runs code
- sinain-memory/common.py 14 KB runs code
- sinain-memory/concept_export.py 13 KB runs code
- sinain-memory/concept_import.py 9.6 KB runs code
- sinain-memory/coreference.py 8.2 KB runs code
- sinain-memory/demo_knowledge_transfer.sh 3.0 KB runs code
- sinain-memory/durability.py 2.0 KB runs code
- sinain-memory/embed_client.py 4.9 KB runs code
- sinain-memory/embedder.py 9.2 KB runs code
- sinain-memory/entity_canonicalizer.py 5.1 KB runs code
- sinain-memory/eval_delta.py 3.9 KB runs code
- sinain-memory/eval_reporter.py 25 KB runs code
- sinain-memory/feedback_analyzer.py 7.1 KB runs code
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.
- 7d ago First seen · 336 lines · 0 tokens per session scan A 26b99f260c0a
sinain-hud-plugin is a skill published in the GitHub repository anthillnet/sinain-hud (9 stars, last pushed 24d ago), with no licence file. It costs nothing until one of its globs matches a file; then it loads 3,251 tokens. 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
macos-harness
Control a whole Mac from one persistent Python session with screenshots, PID-targeted input, an animated virtual pointer, targeted Apple Accessibility, Apple Events, Browser Harness CDP, and filesystem access. Use for native, Electron, browser, dialog, file, or cross-app tasks without moving the physical cursor or…
host-computer-use
Beta desktop control through the connected A0 CLI host. Use for the user's host/local computer screenshots, screen inspection, menus, native app UI, OS-level clicking, scrolling, typing, or checking computeruseremote status. Use instead of linux-desktop for host/local machine control. Do not use for ordinary browser…
macos-computer-use
Skill "macos-computer-use" from furkangonel/cowrangler, covering macos computer use (arka plan, model bağımsız), standart i̇ş akışı, capture modları, aksiyonlar and arka plan kuralları.
findmy
Apple cihazlarını ve AirTag'leri FindMy.app ile takip et.
apple-reminders
Apple Reminders'ı remindctl ile yönet — ekle, listele, tamamla.
imessage
Skill "imessage" from furkangonel/cowrangler, covering imessage, ön koşullar, ne zaman kullan, ne zaman kullanma and hızlı referans.