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/cosgroveb/debian-packaging-agent-skill/debian-packagingnpx skills add cosgroveb/debian-packaging-agent-skill --skill debian-packaginggit clone --depth 1 https://github.com/cosgroveb/debian-packaging-agent-skillWrote 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/cosgroveb/debian-packaging-agent-skill/debian-packaging)<a href="https://agentmods.dev/skills/cosgroveb/debian-packaging-agent-skill/debian-packaging"><img src="https://agentmods.dev/badge/skills/cosgroveb/debian-packaging-agent-skill/debian-packaging.svg" alt="Measured on agentmods" 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 | $0.00039 | $0.03340 |
| Opus 5 | $0.00019 | $0.01670 |
| Sonnet 5 | $0.00008 | $0.00668 |
| Haiku 4.5 | $0.00004 | $0.00334 |
Grade B, and why
debian-packaging 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 6d 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.
13. Test installation with `sudo dpkg -i` How it starts
The opening of the file, as written. The whole thing — 391 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
You are a Debian package maintainer. You prioritize policy compliance, maintainability, and integration with Debian over quick hacks.
Before starting any Debian packaging work
Execute these steps in order:
-
Always start with core packaging knowledge: Read doc/debian-packaging-main.md first to understand Debian Policy, debhelper, package structure, and quality standards.
-
Identify the language and consult specific documentation: Detect the language from project files, then read the relevant doc:
- Ruby gems (Gemfile, *.gemspec present): doc/debian-packaging-ruby.md
- Python packages (setup.py, pyproject.toml, requirements.txt present): doc/debian-packaging-python.md
- Rust crates (Cargo.toml present): doc/debian-packaging-rust.md
- Go modules (go.mod present): doc/debian-packaging-golang.md
-
Progressively consult documentation as needed: Don't read all docs upfront. Instead, read specific knowledge when you encounter relevant situations:
- When working with debian/rules: Already have main summary
- When handling dependencies: Consult language-specific doc
- When dealing with multi-binary packages: Review main doc sections on package splits
- When fixing lintian issues: Check main doc for lintian standards
- When managing patches: Review main doc patch management section
- When debugging build failures: Read doc/systematic-debugging.md
-
Confirm packaging approach: Ask: "Are we creating a new package from scratch, updating an existing package, or fixing a packaging issue?"
Progressive knowledge application
Follow this pattern throughout your work:
- Initial phase: Use main doc for structure and policy
- Language-specific phase: Use language doc when writing debian/rules, handling build system
- Problem-solving phase: Re-consult relevant sections when issues arise
- Quality phase: Use main doc for lintian, testing, verification
What ships with it
6 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.
- 6d ago First seen · 391 lines · 39 tokens per session scan B f3fccd317d6f
debian-packaging is a skill published in the GitHub repository cosgroveb/debian-packaging-agent-skill (4 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 39 tokens to every session and 3,340 once invoked, about $0.0002 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
analyzing-apt-group-with-mitre-navigator
Analyze advanced persistent threat (APT) group techniques using MITRE ATT&CK Navigator to create layered heatmaps of adversary TTPs for detection gap analysis and threat-informed defense.
analyzing-threat-actor-ttps-with-mitre-navigator
Map advanced persistent threat (APT) group tactics, techniques, and procedures (TTPs) to the MITRE ATT&CK framework using the ATT&CK Navigator and attackcti Python library. The analyst queries STIX/TAXII data for group-technique associations, generates Navigator layer files for visualization, and compares defensive…
rulesync
Generates and syncs AI rule configuration files (.cursorrules, CLAUDE.md, copilot-instructions.md) across 20+ coding tools from a single source. Use when syncing AI rules, running rulesync commands, importing or generating rule files, or managing shared AI coding configurations.
autoprompt
Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.
gitnexus
将 GitNexus 作为受控可选代码智能能力接入，用于 brownfield MCP 查询、影响面分析、 detectchanges、多仓分析和更深代码图谱证据。输出必须回落到 /team- 主链和 artifacts。.