Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/mohitmishra786/low-level-dev-skillsnpx agentmods add skills/mohitmishra786/low-level-dev-skills/linux-kernel-architectureWrote 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/mohitmishra786/low-level-dev-skills/linux-kernel-architecture)<a href="https://agentmods.dev/skills/mohitmishra786/low-level-dev-skills/linux-kernel-architecture"><img src="https://agentmods.dev/badge/skills/mohitmishra786/low-level-dev-skills/linux-kernel-architecture/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/mohitmishra786/low-level-dev-skills/linux-kernel-architecture"><img src="https://agentmods.dev/badge/skills/mohitmishra786/low-level-dev-skills/linux-kernel-architecture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00065 | $0.00780 |
| Opus 5 | $0.00032 | $0.00390 |
| Sonnet 5 | $0.00013 | $0.00156 |
| Haiku 4.5 | $0.00006 | $0.00078 |
Grade A, and why
linux-kernel-architecture 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 8d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Linux Kernel Architecture
Purpose
Provide a mental map of the Linux kernel: boot sequence, major subsystems, key data structures, and where to look in source — complementing skills/kernel/kernel-internals with architecture-level navigation for driver and subsystem work.
When to Use
- First time exploring
linux.gitfor a feature or bug - Understanding how boot reaches
initand driverprobe - Tracing a syscall or interrupt through subsystems
- Onboarding before
skills/kernel-dev/platform-device-modelor driver skills
Workflow
1. Boot flow (x86/ARM64 simplified)
firmware/UEFI
├── arch/*/boot — decompress kernel, early setup
├── start_kernel() — mm, scheduler, timers, IRQ subsys
├── rest_init() → kernel_init → run_init_process
└── userspace init (systemd)
Driver module_init / device_initcall run during start_kernel before init.
2. Major subsystems
| Subsystem | Path (typical) | Key structs |
|---|---|---|
| Scheduler | kernel/sched/ |
task_struct, sched_entity |
| Memory | mm/ |
struct page, mm_struct, vm_area_struct |
| VFS | fs/ |
inode, dentry, file, super_block |
| Block | block/ |
request_queue, gendisk |
| Net | net/ |
sk_buff, net_device |
| Drivers | drivers/ |
device, device_driver |
| Syscalls | kernel/, fs/, mm/ |
SYSCALL_DEFINE* |
3. Initcall levels
/* include/linux/init.h — order matters */
early_initcall → core_initcall → postcore_initcall
→ arch_initcall → subsys_initcall → fs_initcall
→ device_initcall → late_initcall
Platform drivers usually register at subsys_initcall or via module_init.
4. Finding code
# Locate symbol
grep -rn "platform_driver_register" drivers/
# Trace config
./scripts/config --state CONFIG_FOO
# File hierarchy docs
ls Documentation/admin-guide/
5. Agent usage
/linux-kernel-architecture Where does page fault handling live and what calls it?
Common Problems
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.
- 8d ago First seen · 90 lines · 65 tokens per session scan A 8b8fad4d4356
linux-kernel-architecture is a skill published in the GitHub repository mohitmishra786/low-level-dev-skills (203 stars, last pushed 2mo ago), licensed MIT. It adds 65 tokens to every session and 780 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
build-your-ai-common-sense-habit
Build a repeatable prompting habit around clear goals, relevant context, verification, and human review.
dont-trust-ai-medical-diagnoses
Use AI for medical vocabulary and appointment preparation while directing diagnosis and treatment questions to qualified clinicians.
act-as-a-personal-tutor
Explain a subject step by step, assess prior knowledge, and use short exercises to check understanding before advancing.
sop-training
Hotel SOP and training documentation generator. Use when the user asks to 'create an SOP', 'write training materials', 'onboarding checklist', 'department procedures', 'brand standards documentation', 'housekeeping standards', 'front desk procedures', or any hotel operations documentation.
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
deck-course-module
A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.