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 skills/alonf/mcppythondemo/linux-proc-diagnosticsnpx skills add alonf/MCPPythonDemo --skill linux-proc-diagnosticsgit clone --depth 1 https://github.com/alonf/MCPPythonDemoWhat 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 | $0.00000 | $0.02528 |
| Opus 5 | $0.00000 | $0.01264 |
| Sonnet 5 | $0.00000 | $0.00506 |
| Haiku 4.5 | $0.00000 | $0.00253 |
Grade B, and why
linux-proc-diagnostics scanned grade B with 1 finding 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 yesterday.
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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo python3 -c " How it starts
The opening of the file, as written. The whole thing — 289 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Linux /proc Diagnostics Parsing Skill
Author: Dallas (Linux Diagnostics Expert)
Date: 2026-04-14
Purpose: Reliable parsing of Linux /proc interfaces for diagnostics tools, MCP servers, and system monitoring.
Overview
Linux /proc and /sys are the primary sources of system diagnostics data. Unlike Windows WMI (object-oriented),
these are raw, ephemeral, text-based kernel interfaces. This skill documents the patterns for safe, robust parsing.
Core Principle
/proc is the truth layer. Always read fresh. Cache strategically. Handle races gracefully.
Key Files & Formats
System-Level Diagnostics
/proc/meminfo - Memory usage (read-only, always available)
MemTotal: 8167848 kB
MemFree: 2048576 kB
MemAvailable: 3145728 kB
Buffers: 102400 kB
Cached: 1024000 kB
...
Pattern: Key-value pairs, values in kB. Safe for non-root.
/proc/cpuinfo - CPU info (read-only, always available)
processor : 0
vendor_id : GenuineIntel
cpu family : 6
...
Pattern: Colon-separated; processor lines repeat per core.
/proc/loadavg - Load average (read-only, always available)
0.45 0.52 0.48 2/412 12345
Pattern: 5 fields: 1m avg, 5m avg, 15m avg, tasks running/total, last pid. Always safe.
Process-Level Diagnostics
/proc/[pid]/stat - Process CPU/memory snapshot (ephemeral, permission-guarded)
12345 (bash) S 1 12345 12345 0 -1 4218880 15234 0 0 0 234 12 0 0 20 0 1 0 123456789 45678912 1234
Pattern: Space-separated fields; #1=pid, #2=comm, #3=state (S=sleeping, R=running, Z=zombie).
- Fields 13,14: utime, stime (jiffies)
- Field 23: vss (virtual set size)
- Field 24: rss (resident set size, in pages)
Race condition: PID may exit between listing /proc and reading /proc/[pid]/stat. Wrap in try/except.
Permission: Non-root can read own process; cannot read others' by default (depends on ptrace_scope).
/proc/[pid]/status - Process metadata (human-readable alternative to stat)
Name: bash
State: S (sleeping)
Tgid: 12345
Pid: 12345
PPid: 1
VmPeak: 45678 kB
VmSize: 40960 kB
VmRSS: 8192 kB
...
Pattern: Human-readable format. Same data as stat but easier to parse selectively.
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.
- yesterday First seen · 289 lines · 0 tokens per session scan B df61db30211f
linux-proc-diagnostics is a skill published in the GitHub repository alonf/MCPPythonDemo (0 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,528 tokens. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…