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/jonaslejon/linux-security-audit-plugin/linux-security-auditnpx skills add jonaslejon/linux-security-audit-plugin --skill linux-security-auditgit clone --depth 1 https://github.com/jonaslejon/linux-security-audit-pluginWhat 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 | $0.00149 | $0.05851 |
| Opus 5 | $0.00075 | $0.02926 |
| Sonnet 5 | $0.00030 | $0.01170 |
| Haiku 4.5 | $0.00015 | $0.00585 |
Grade B, and why
linux-security-audit scanned grade B with 4 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootlowPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
Establish: which host(s), is root/sudo available, is it production, and is there a baseline to Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Reads agent configuration directorieslowAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
SK="$(find -L "${CLAUDE_PLUGIN_ROOT:-$HOME/.claude}" "$HOME/.claude/plugins" "$HOME/.claude/skills" \ Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Enumerates other installed skillslowAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
SK="$(find -L "${CLAUDE_PLUGIN_ROOT:-$HOME/.claude}" "$HOME/.claude/plugins" "$HOME/.claude/skills" \ Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`proxy_ssl_verify` left at its off default, or a `curl -k` in a cron job are all "TLS is on" and How it starts
The opening of the file, as written. The whole thing — 349 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Linux Security Audit
Audits how hardened a Linux system is and reports what to fix, in risk order, with the exact change and its blast radius. Auditing is the default; changing the system is a separate, explicitly approved step.
What this does to the system
Designed to be run against production, so here is the precise inventory rather than a blanket warning: an overstated caution just gets ignored.
scripts/lsa-collect.sh writes nothing by default. No config is modified, no service is
started, stopped or reloaded, no package is installed. Two side effects worth knowing:
- Active checks open loopback connections: a TLS ClientHello to each listening port and an
HTTP HEAD to
127.0.0.1, plus NTP peer queries. Harmless, but they appear in the audited service's own logs as connections from localhost.--passiveremoves them entirely. --apt-updateis opt-in and off by default. It is the only thing that writes anything (refreshing/var/lib/apt/lists), and it exists only because verifying that every repo is signed requires it.
Load, not risk, is the real production consideration: the whole-filesystem walks (SUID,
world-writable, secrets) and package checksum verification (dpkg --verify, rpm -Va) do read I/O
proportional to disk size, and on a large host the package pass alone can run for minutes. Use
--quick to skip both on large or slow storage. The output header reports total elapsed time and
the slowest sections, so quote those rather than guessing.
scripts/lsa-trace.sh is different and is deliberately kept separate. --live is read-only,
but --unit restarts a service and --boot arm writes audit rules and needs a reboot. Every mode
runs --preflight first, prints exactly what it will do, and requires --yes. It refuses outright
rather than half-working when hardening blocks it.
So: run the collector on production. Run the tracer on a staging clone unless you have a specific reason not to.
Rules of engagement
What ships with it
11 files 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.
- assets/report-template.md 5.1 KB
- references/boot-and-modules.md 9.0 KB
- references/checklist.md 63 KB
- references/remediation.md 11 KB
- references/services-ssh-logging.md 12 KB
- references/sysctl.md 11 KB
- references/tls-and-mtls.md 8.1 KB
- references/tooling-and-scope.md 3.1 KB
- references/webserver-and-ports.md 19 KB
- scripts/lsa-collect.sh 395 KB runs code
- scripts/lsa-trace.sh 18 KB runs code
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 · 349 lines · 149 tokens per session scan B 72a4d6a53cc5
linux-security-audit is a skill published in the GitHub repository jonaslejon/linux-security-audit-plugin (13 stars, last pushed 19d ago), licensed MIT. It adds 149 tokens to every session and 5,851 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it B with 4 findings (asks for root, reads agent configuration directories, enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…