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 skills add web-casa/pkgseek-skills --skill pkgseek-linuxgit clone --depth 1 https://github.com/web-casa/pkgseek-skillsWrote 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/web-casa/pkgseek-skills/pkgseek-linux)<a href="https://agentmods.dev/skills/web-casa/pkgseek-skills/pkgseek-linux"><img src="https://agentmods.dev/badge/skills/web-casa/pkgseek-skills/pkgseek-linux/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/web-casa/pkgseek-skills/pkgseek-linux"><img src="https://agentmods.dev/badge/skills/web-casa/pkgseek-skills/pkgseek-linux.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00120 | $0.01132 |
| Opus 5.5 | $0.00048 | $0.00453 |
| Sonnet 5.5 | $0.00024 | $0.00226 |
| Haiku 4.5 | $0.00012 | $0.00113 |
Grade A, and why
pkgseek-linux 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 1mo 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PkgSeek Linux Package and Compatibility Investigator
Use one installed Skill to route Linux package troubleshooting, security checks, migrations, ELF/ABI diagnostics, command portability, and container reviews to focused reference workflows.
Route the task
Read the matching reference file completely before investigating. Read more than one only when the request genuinely crosses capabilities; do not load all references by default.
| User need | Read this reference | Primary PkgSeek MCP tools |
|---|---|---|
Missing command, package, header, library, .pc file, or build dependency |
references/fix-linux-build-error.md |
diagnose_linux_error, query_file_provides, resolve_install, get_package |
| Distribution upgrade, package mapping, release comparison, or EOL migration | references/migrate-linux-distribution.md |
check_release_lifecycle, compare_distro_releases, plan_distro_migration |
| CVE/CNNVD exposure, vendor advisory, false positive, or backported fix | references/audit-linux-vulnerabilities.md |
search_vulnerabilities, get_vulnerability, get_package |
ELF loader, missing .so, undefined reference, GLIBC/GLIBCXX, symbol version, or ABI failure |
references/debug-elf-abi.md |
query_file_provides, compare_package_versions, get_package_history |
| GNU/BSD/BusyBox flags, shell portability, or command/package-name differences | references/port-linux-command.md |
lint_command, suggest_fix, compare_distros, resolve_install |
| Dockerfile, base-image lifecycle, package availability, or reproducibility review | references/review-linux-container.md |
check_release_lifecycle, get_repository_health, get_package_history |
Core workflow
- Establish the exact Linux distribution, release, architecture, repository source, package build, and failure stage. Ask only for facts that materially change the conclusion.
- Select and read the relevant reference workflow above.
- Prefer the read-only PkgSeek MCP endpoint at
https://api.pkgseek.com/mcp. Usehttps://api.pkgseek.comas a REST fallback only when MCP is unavailable. - Prefer exact distro/release evidence over naming convention, upstream version guesses, or nearest-release matches. Separate fact, inference, and unknowns.
- Return the diagnosis, evidence chain, smallest supported remedy, non-mutating verification, and remaining uncertainty.
What ships with it
7 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.
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.
- 1mo ago First seen · 56 lines · 120 tokens per session scan A 0c65fbbc6b22
pkgseek-linux is a skill published in the GitHub repository web-casa/pkgseek-skills (5 stars, last pushed 2mo ago), licensed MIT. It adds 120 tokens to every session and 1,132 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
agentsight-bugfix
A five-stage workflow for fixing bugs in AgentSight: understand the report, reproduce the problem, find its cause, make a small code change, and verify the result. AgentSight is a system that observes and analyses agent activity.
Z.A.E.B.A.L.: profanity-triggered self-audit for agents
Use when the agent loops on the same mistake and the user is visibly frustrated. Z.A.E.B.A.L. treats profanity as an audit signal: stop, disprove the wrong belief, escalate repeated failures to an external auditor. Also use for requested hook setup on Linux or Windows. Select the target process OS and install only the…
gearsystem-debugging
Debug and trace Sega Master System, Game Gear, and SG-1000 games using the Gearsystem emulator MCP server. Provides workflows for Z80 CPU debugging, breakpoint management, VDP/PSG/YM2413 hardware inspection, disassembly analysis, execution tracing, and rewind/time-travel debugging. Use when the user wants to debug an…
geargrafx-debugging
Debug and trace TurboGrafx-16 / PC Engine / SuperGrafx games using the Geargrafx emulator MCP server. Provides workflows for HuC6280 CPU debugging, breakpoint management, hardware inspection, disassembly analysis, and execution tracing. Use when the user wants to debug a PC Engine game, trace code execution, inspect…
readmd-code-analysis
Use when source code or a configuration file needs a factual logic and risk analysis.
gearcoleco-debugging
Debug and trace ColecoVision and Super Game Module games using the Gearcoleco emulator MCP server. Provides workflows for Z80 CPU debugging, breakpoint management, TMS9918A VDP/SN76489/AY-3-8910 hardware inspection, disassembly analysis, execution tracing, and rewind/time-travel debugging. Use when the user wants to…