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 askmarcel/AskMarcel-MCP --skill hvac-harnais-sessiongit clone --depth 1 https://github.com/askmarcel/AskMarcel-MCPWrote 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/askmarcel/askmarcel-mcp/hvac-harnais-session)<a href="https://agentmods.dev/skills/askmarcel/askmarcel-mcp/hvac-harnais-session"><img src="https://agentmods.dev/badge/skills/askmarcel/askmarcel-mcp/hvac-harnais-session/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/askmarcel/askmarcel-mcp/hvac-harnais-session"><img src="https://agentmods.dev/badge/skills/askmarcel/askmarcel-mcp/hvac-harnais-session.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 | $0.00032 | $0.00579 |
| Opus 5 | $0.00016 | $0.00290 |
| Sonnet 5 | $0.00006 | $0.00116 |
| Haiku 4.5 | $0.00003 | $0.00058 |
Grade A, and why
hvac-harnais-session 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 9d 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Harness diagnostic session (Beta, LIVE)
Use the 5 session tools — not diagnose or diagnose_guided — for multi-turn field diagnostics on air-to-water or air-to-air heat pumps with manufacturer error-code lookup, hypotheses, and a discriminating next_action.
Families: pac_air_eau, pac_air_air · packs 0.0.1 · release_channel: beta.
When to use
| Prefer Harness session | Prefer instead |
|---|---|
| Full field loop with journal, hypotheses, technician assessment | diagnose_v2 for one-shot strict SKU lookup |
| Error code + next control step from pack | get_error_code for code meaning only |
| PAC Air/Air or PAC Air/Eau with exportable summary | diagnose_guided for legacy PAC Air/Eau guided loop (quota per turn) |
Loop
request_id is required on start_diagnostic, respond_to_diagnostic, and close_diagnostic (idempotency). Use a new request_id for each distinct write.
start_diagnostic({ brand, model, error_code or symptom, family, request_id })- If
fault_codeis present, explain manufacturer meaning and cite sources when returned. - If
next_actionis present, relay title, method, and warnings to the technician — do not invent measurements. respond_to_diagnostic({ session_id, session_version, request_id, response })with typed observation or assessment.- Repeat step 3–4 until
engine_stateis terminal, session is closed, or no compatible action exists (explain code and abstain from unsafe steps). close_diagnostic({ session_id, session_version, request_id })orget_diagnostic_summary({ session_id })for export.
Always pass the latest session_version from the previous response.
Abstention
If the manufacturer code is recognized but no safe pack action exists, do not treat the code as unknown. Explain the fault meaning and ask a precise clarification or abstain from proposing a manipulation.
Do not
- Skip
resolve_modellogic — if equipment is ambiguous, clarify plate reference before asserting model-specific values. - Invent causes, pressures, or resistances — use
next_action.expected_inputand pack ranges only. - Use Harness session tools for boilers, chillers, or unrelated equipment families.
- Replay the same
request_idwith a different payload expecting a new session.
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.
- 9d ago First seen · 43 lines · 32 tokens per session scan A 0a59a6847ce9
hvac-harnais-session is a skill published in the GitHub repository askmarcel/AskMarcel-MCP (0 stars, last pushed 15d ago), licensed MIT. It adds 32 tokens to every session and 579 once invoked, about $0.0002 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
gke-compute-classes
Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…
jetson-diagnostic
Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.
doca-socket-relay
Use this skill when the operator is driving the DOCA Socket Relay to bridge a socket-oriented host application onto a BlueField DPU peer without rewriting it — picking the deployment shape (in-process, sidecar, or BlueField service container), configuring the host-side socket and the DPU-side forwarding endpoint…
offensive-z-wave
Z-Wave attack methodology — sniffing with Z-Force / EZ-Wave / RTL-SDR + ZniffMobile, S0 (legacy) network-key derivation flaw and key reuse, S2 (modern) ECDH commissioning analysis, replay/injection on unauthenticated nodes, default-key brute-force on test deployments, and home-automation hub pivots. Use when targeting…
hsb-flash
Flash the FPGA on an HSB board connected to an NVIDIA devkit. Supports HSB Lattice boards (FPGA versions 2407, 2412, 2507, 2510) and Leopard Imaging VB1940 "all-in-one" cameras (FPGA versions 2507, 2510). Uses release-specific YAML manifests and board-type-specific program commands. Lattice and VB1940 commands must…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.