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 instructions/yamaru-eu/hardware-probe/claude-mdgit clone --depth 1 https://github.com/yamaru-eu/hardware-probeWrote 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/instructions/yamaru-eu/hardware-probe/claude-md)<a href="https://agentmods.dev/instructions/yamaru-eu/hardware-probe/claude-md"><img src="https://agentmods.dev/badge/instructions/yamaru-eu/hardware-probe/claude-md.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 | $0.01202 | $0.01202 |
| Opus 5 | $0.00601 | $0.00601 |
| Sonnet 5 | $0.00240 | $0.00240 |
| Haiku 4.5 | $0.00120 | $0.00120 |
Grade A, and why
hardware-probe CLAUDE.md 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
hardware-probe
Sonde matérielle locale exposée via un serveur MCP (Model Context Protocol). Elle lit les specs matérielles locales via systeminformation et relaie les demandes de recommandation vers le remote-affiliate-api.
Stack
- Runtime : Node.js >= 18
- Langage : TypeScript (ESM)
- Dépendance principale :
@modelcontextprotocol/sdk,systeminformation - Transport : stdio (protocole MCP)
Commandes
npm install # Installer les dépendances
npm run build # Compiler TypeScript → dist/
npm run dev # Lancer sans compilation (tsx)
npm start # Lancer depuis dist/ (après build)
Variables d'environnement
| Variable | Défaut | Description |
|---|---|---|
REMOTE_API_URL |
http://localhost:3000/api/recommend |
URL de l'API distante de recommandation |
Outils MCP exposés
| Outil | Description |
|---|---|
analyze_local_system |
Retourne CPU, RAM, carte mère et OS en JSON structuré. Aucun argument. |
get_hardware_recommendation |
Collecte les specs locales et appelle REMOTE_API_URL avec query + budget. |
analyze_ram_pressure |
Mémoire + swap + top 10 processus par RSS. Faits bruts uniquement. |
check_storage_health |
Par disque : type, taille, température, statut SMART, firmware. Faits bruts. |
thermal_profile |
Températures CPU/GPU, fréquences courantes, utilisation/VRAM GPU. Faits bruts. |
monitor_system_health |
Mesure CPU, RAM et température sur une fenêtre de temps configurable (1-600s). Retourne min/max/avg. Params : duration_seconds (défaut 10), interval_seconds (défaut 2). |
diagnose_antivirus_impact |
AV/EDR détectés + règles d'exclusion existantes (Windows/macOS/Linux/WSL2) + couverture des chemins dev chauds (node_modules, .git, …). Faits bruts. |
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 · 65 lines · 1,202 tokens per session scan A 84e75afc1d1f
hardware-probe CLAUDE.md is an instructions file published in the GitHub repository yamaru-eu/hardware-probe (7 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,202 tokens to every session, about $0.0060 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 instructions, from other repositories
RocketSmith GEMINI.md
Gemini CLI instructions for ppak10/RocketSmith: @./skills/stability-analysis/SKILL.md @./skills/motor-selection/SKILL.md @./skills/design-for-additive-manufacturing/SKILL.md @./skills/generate-structures/SKILL.md @./skills/modify-structures/SKILL.md @./skills/print-preparation/SKILL.md…
brilliant_sdk AGENTS.md
Instructions for brilliantlabsAR/brilliant_sdk, covering brilliant sdk — agent guide, how an app works (the pattern behind everything), minimal reading paths, verify without hardware and testing.
NeoMind CLAUDE.md
Claude Code instructions for camthink-ai/NeoMind, covering neomind — edge ai platform for iot, development commands, ecosystem repositories, extension package contract (.nep) and device type template contract (json).
cad-cae-copilot copilot-instructions.md
Copilot instructions for armpro24-blip/cad-cae-copilot, covering github copilot — aieng workspace and essentials.
phone-mcp CLAUDE.md
Claude Code instructions for premex-ab/phone-mcp, covering claude.md, project overview, build commands, architecture and module layout.
AMD-BC-250-Windows-Driver AGENTS.md
AGENTS.md instructions for Keshas-dev/AMD-BC-250-Windows-Driver, covering amd bc-250 windows driver — agent notes, host machine, ⚠️ historical-data caution (2026-08-21, strengthened), fresh re-verifications (current build, 2026-08-21) and workspace boundary.