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 pamela-0/boot-doctor-mcp --skill skillgit clone --depth 1 https://github.com/pamela-0/boot-doctor-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/pamela-0/boot-doctor-mcp/skill)<a href="https://agentmods.dev/skills/pamela-0/boot-doctor-mcp/skill"><img src="https://agentmods.dev/badge/skills/pamela-0/boot-doctor-mcp/skill/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/pamela-0/boot-doctor-mcp/skill"><img src="https://agentmods.dev/badge/skills/pamela-0/boot-doctor-mcp/skill.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 | $0.00111 | $0.00520 |
| Opus 5.5 | $0.00044 | $0.00208 |
| Sonnet 5.5 | $0.00022 | $0.00104 |
| Haiku 4.5 | $0.00011 | $0.00052 |
Grade A, and why
boot-doctor-mcp 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.
What it actually says
boot-doctor-mcp
Real, sourced, deterministic hardware diagnostics. If the user describes beep patterns or no-boot symptoms, use these tools instead of reasoning about the likely cause from training data — hardware advice where being wrong costs real money and time deserves a fixed, auditable rule set, not a plausible-sounding guess.
When to use each tool
lookup_beep_code(bios_type, pattern) — call this first if the user mentions any beep pattern at all:
- Ask which BIOS type if they don't know:
ami_legacy(classic AMIBIOS),ami_aptio(modern AMI UEFI), oraward_phoenix. These genuinely use different codes for the same beep counts — never guess one to save a question. patternis a plain description like"10 short","1 long, 2 short", or"continuous".- A "no match" result is real information, not a failure — many modern boards have no speaker at all and use debug LEDs instead. Report it as such.
diagnose_symptoms(...) — call this for a general no-boot/no-display case, with or without a beep code:
- Pass along what the user has already told you (powers on?, fans spinning?, display output?) and what they've already tried (CMOS reset, minimal config test, swapped cable/monitor).
- Returns ranked next steps ordered cheapest-to-rule-out-first, not a single "your part X is broken" verdict.
- If it recommends a swap test against known-good parts, say so plainly — symptom-matching alone can't replace an actual swap test.
What not to do
Don't state a specific broken component as fact from symptoms alone — these tools give ranked next steps and sourced beep-code lookups, not a diagnosis of the exact failed part. If the user asks something these tools don't cover, say so rather than reasoning about the hardware cause yourself.
What ships with it
1 file 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.
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 · 25 lines · 111 tokens per session scan A 38bca0accea1
boot-doctor-mcp is a skill published in the GitHub repository pamela-0/boot-doctor-mcp (1 stars, last pushed 2mo ago), licensed MIT. It adds 111 tokens to every session and 520 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
hardware-health-check
Out-of-band hardware health via Redfish BMC (read-only) — power state, component health, thermal and power readings, firmware inventory, SEL log triage. Use when determining whether a host is powered off versus unreachable, checking hardware faults, reviewing thermal or PSU state, or triaging BMC event logs.
rtl-bug-repro
Reproduce an RTL bug with a minimal TB and isolate root cause via waveform diff — 'reproduce this bug', 'minimal repro TB', regression failure isolation.
rtl-p4s-bugfix-policy
Internal reference: rtl p4s bugfix policy (agent-loaded; do not invoke).
rtl-p4s-bugfix
P4 RTL bug fix enforcing full cycle through TB update and functional simulation; lint-only is never complete. Use for 'fix RTL bug' or Phase 5-to-4 feedback.
lint-tool-profiles
Internal reference: lint tool profiles (agent-loaded; do not invoke).
gke-ai-troubleshooting-tpu-dynamic-slices-monitoring
Monitors, troubleshoots, and manages GKE TPU Dynamic Slices custom resources. Use when checking TPU slice lifecycle states, troubleshooting slice provisioning failures, validating single-slice or multi-slice (JobSet) workload manifests, or safely patching stuck finalizers and disabling the slice controller. Don't use…