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/riscv-privilegedWrote 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/riscv-privileged)<a href="https://agentmods.dev/skills/mohitmishra786/low-level-dev-skills/riscv-privileged"><img src="https://agentmods.dev/badge/skills/mohitmishra786/low-level-dev-skills/riscv-privileged/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/riscv-privileged"><img src="https://agentmods.dev/badge/skills/mohitmishra786/low-level-dev-skills/riscv-privileged.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 | $0.00086 | $0.02013 |
| Opus 5 | $0.00043 | $0.01007 |
| Sonnet 5 | $0.00017 | $0.00403 |
| Haiku 4.5 | $0.00009 | $0.00201 |
Grade A, and why
riscv-privileged 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 — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RISC-V Privileged Architecture
Purpose
Guide agents through the RISC-V privileged specification: M/S/U privilege modes, CSR registers, trap handling, PLIC and CLINT interrupt controllers, OpenSBI firmware integration, Sv39/Sv48 page tables, and QEMU virt machine testing.
When to Use
- Writing an OS kernel or hypervisor for RISC-V
- Implementing trap handlers and context switch
- Integrating OpenSBI for S-mode firmware services
- Configuring interrupt controllers on QEMU virt or hardware
- Setting up virtual memory with Sv39 or Sv48
- Porting xv6-RISC-V or bare-metal firmware
Workflow
1. Privilege levels
RISC-V privilege stack
├── M-mode (Machine) — firmware, OpenSBI, most privileged
├── S-mode (Supervisor) — OS kernel
└── U-mode (User) — applications
Embedded (no S-mode): M + U only
2. Key CSRs
| CSR | Mode | Purpose |
|---|---|---|
mstatus / sstatus |
M/S | Interrupt enable, privilege state |
mtvec / stvec |
M/S | Trap vector base address |
mepc / sepc |
M/S | Exception PC |
mcause / scause |
M/S | Trap cause code |
mtval / stval |
M/S | Faulting address/instruction |
satp |
S | Page table root (mode + PPN) |
mie / sie |
M/S | Interrupt enable bits |
mip / sip |
M/S | Interrupt pending bits |
// Read CSR (GCC extended asm)
static inline uint64_t read_csr_satp(void) {
uint64_t val;
asm volatile("csrr %0, satp" : "=r"(val));
return val;
}
// Write CSR
static inline void write_csr_stvec(void *handler) {
asm volatile("csrw stvec, %0" :: "r"(handler));
}
3. Trap handling
Trap types
├── Synchronous exceptions — ecall, page fault, illegal insn
└── Asynchronous interrupts — timer, external, software
// scause encoding (top bit: 1=interrupt, 0=exception)
void handle_trap(uint64_t scause, uint64_t sepc, uint64_t stval) {
if (scause & (1UL << 63)) {
// Interrupt
switch (scause & 0xff) {
case 5: // Supervisor timer interrupt
timer_interrupt();
break;
case 9: // Supervisor external interrupt
external_interrupt();
break;
}
} else {
// Exception
switch (scause) {
case 8: // ecall from U-mode
handle_syscall();
break;
case 12: // Instruction page fault
case 13: // Load page fault
case 15: // Store page fault
handle_page_fault(stval, scause);
break;
}
}
}
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 · 240 lines · 86 tokens per session scan A ac8af49dca34
riscv-privileged is a skill published in the GitHub repository mohitmishra786/low-level-dev-skills (203 stars, last pushed 2mo ago), licensed MIT. It adds 86 tokens to every session and 2,013 once invoked, about $0.0004 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
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…
gke-ai-troubleshooting-tpu-vbar-oom
Diagnoses and prevents vbarcontrolagent segfaults, out-of-memory (OOM) errors, and TPU device initialization failures on TPU v6e nodes in GKE caused by race conditions during TPU device resets or high-frequency metrics polling. Use when troubleshooting vbarcontrolagent crashes, memory cgroup OOMs in serial console…
doca-flow
Build and debug DOCA Flow applications on supported NVIDIA NICs/DPUs: define match/action pipes, initialize ports and representors, choose forwarding targets, validate pipes before hardware programming, read counters, match the Flow version to the installed DOCA release, and diagnose Flow API errors. Trigger on DOCA…
diagnose-driver-install
Diagnose NVIDIA driver installation failures on DeepOps-managed nodes — nvidia-smi errors, "No devices were found", DKMS build failures, or GPU pods crash-looping. Use before reinstalling anything.
ipfabric
Skill: /ipfabric MCP Server: ipfabric-mcp (remote HTTP via mcp-remote) Tools: 10 (health, path lookups, diagrams, API discovery).
gtrace-path-analysis
Network path tracing and monitoring — traceroute with MPLS/ECMP/NAT detection, continuous MTR monitoring, and distributed GlobalPing probes from 500+ worldwide locations. Use when tracing the path to a destination, diagnosing slow network routes, detecting MPLS or ECMP load balancing, running MTR for intermittent…