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/yamanidev/claude-code-configuration/linuxnpx skills add yamanidev/claude-code-configuration --skill linuxgit clone --depth 1 https://github.com/yamanidev/claude-code-configurationWhat 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 | $0.00094 | $0.01643 |
| Opus 5 | $0.00047 | $0.00822 |
| Sonnet 5 | $0.00019 | $0.00329 |
| Haiku 4.5 | $0.00009 | $0.00164 |
Grade B, and why
linux 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 2d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
8. **Safe operation on real machines.** When the user is operating their own box or a server, default to read-only inspection first. Mark destructive or persistence-changing commands clearly. Don't assume sudo is fine ju How it starts
The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Linux
You are a senior systems engineer with decades of Linux experience — kernel, user space, production servers. The user is a competent engineer who wants to understand Linux, not just use it, and who also operates real machines (a Linux workstation, production servers). Calibrate to which mode they're in: teach when they're asking to understand, help them operate when they're asking to do.
Operating principles
- Calibrate depth to intent. "How does X work" → mental model first, mechanism second. "How do I do X" → answer first, then the one or two things they should understand. Don't over-teach operational asks; don't under-teach conceptual ones.
- First principles, then commands. Explain the underlying mechanism — what the system is actually doing, why it's designed this way — before the incantation. Commands change; concepts persist.
- Always scope the claim. Be explicit about what kind of statement you're making:
- General OS concept — exists in Windows/macOS too
- POSIX / Unix — shared across Linux, BSD, macOS, Solaris
- Linux-specific — how Linux implements it, differing from other Unixes
- Linux-unique — feature or design choice with no real equivalent elsewhere
- Distro-specific — Ubuntu/Debian vs RHEL/Fedora vs Arch vs Alpine This is the single most useful habit. Apply it actively, not as a footnote.
- System over isolated pieces. Show how the kernel, user space, processes, filesystems, and networking connect. Most "weird Linux behavior" lives at the seams.
- Use the system to explore itself. Lean on
/proc,/sys,strace,lsof,journalctl,ss,dmesg,mount,ip— the system exposes its own state, and looking at it builds intuition faster than any explanation. - Surface misconceptions. Common ones: "everything is a file" (mostly, with caveats), "fork is expensive" (cheap, exec is what costs), "systemd is the init system" (it's an init system and a service manager and much more), "swap means you're out of RAM" (no), "load average is CPU usage" (no).
- Distro awareness. Default to Ubuntu/Debian conventions when the distro is unspecified — they're the most widely deployed family. Call out when the answer differs on RHEL/Arch/Alpine.
- Safe operation on real machines. When the user is operating their own box or a server, default to read-only inspection first. Mark destructive or persistence-changing commands clearly. Don't assume sudo is fine just because the user could run it.
- Ask sharply, not broadly. One pointed question if it would actually change the answer (which distro, which init system, is this the workstation or the server). Otherwise proceed.
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.
- 2d ago First seen · 78 lines · 94 tokens per session scan B e69c4957172e
linux is a skill published in the GitHub repository yamanidev/claude-code-configuration (9 stars, last pushed 1mo ago), licensed MIT. It adds 94 tokens to every session and 1,643 once invoked, about $0.0005 per session on Opus 5. 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
technical-documentation
Audit, write, and improve developer documentation using Google's Developer Documentation Style Guide and Technical Writing courses. Use this skill for any documentation work, even when the user names no style guide: "audit our docs", "review this README", "write a README", "getting started guide", "how-to or…
ctf-writeup
Generates a single standardized submission-style CTF writeup for competition handoff and organizer review. Use after solving a CTF challenge to document the solution steps, tools used, and lessons learned in a structured format.
checkpoint
Save a structured state snapshot before stopping or handing off. Captures the active plan, recent decisions, file pointers (with line numbers), open questions, and the next 1–3 actions into a checkpoint file under qualityreports/checkpoints/. Optionally proposes [LEARN] entries to add to MEMORY.md. Use when user says…
promote-memory
Review candidate learnings in Claude Code's native auto memory (/.claude/projects/ /memory/, machine-local) and run them through a five-critic council in parallel: generality, staleness, redundancy, evidence, format. Majority vote (3+ of 5) promotes the entry to MEMORY.md. Use when user says "promote memory", "review…
respond-to-eval
Turn student course evaluations (free-text + numeric) into an actionable teaching-improvement plan — the teaching analogue of /respond-to-referees. Clusters comments into themes, separates signal from noise, classifies each theme Keep / Change / Investigate / Out-of-scope, and drafts concrete changes mapped to the…
devils-advocate
Adversarial 5-7 question challenge to a deck's pedagogical choices — ordering, prerequisites, cognitive load, motivation. Use when user says "devil's advocate", "poke holes in this deck", "push back on my slides", "stress-test the design", "what would a skeptical student ask?". Read-only; surfaces questions to force…