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 ithinkihaveacat/dotfiles --skill jetpackgit clone --depth 1 https://github.com/ithinkihaveacat/dotfilesWrote 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/ithinkihaveacat/dotfiles/jetpack)<a href="https://agentmods.dev/skills/ithinkihaveacat/dotfiles/jetpack"><img src="https://agentmods.dev/badge/skills/ithinkihaveacat/dotfiles/jetpack/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/ithinkihaveacat/dotfiles/jetpack"><img src="https://agentmods.dev/badge/skills/ithinkihaveacat/dotfiles/jetpack.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00098 | $0.02534 |
| Opus 5.5 | $0.00039 | $0.01014 |
| Sonnet 5.5 | $0.00020 | $0.00507 |
| Haiku 4.5 | $0.00010 | $0.00253 |
Grade A, and why
jetpack scanned grade A 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 19d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Requires curl, xmllint (libxml2-utils), jar (JDK), jq, perl. Needs network How it starts
The opening of the file, as written. The whole thing — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Jetpack Library Utilities
Using the Jetpack Script vs. Raw Maven Queries
Use scripts/jetpack as the primary interface for resolving AndroidX and
Jetpack library coordinates, versions, and source locations. References to
scripts/... in this skill are relative to this skill directory. The script
handles complex resolution logic that manual queries miss:
- Package-to-coordinate resolution with a comprehensive exceptions table
- Code search integration for finding artifacts by class name
- Version type filtering (ALPHA, BETA, STABLE, SNAPSHOT)
- Kotlin Multiplatform platform-specific source detection
- Build ID resolution for pinned snapshots
The cache is the script's storage, not an interface. curl and xmllint
against dl.google.com are the obvious way to bypass the script, but reaching
into $JETPACK_CACHE_DIR with jq, unzip, jar, find, or grep bypasses
it just as completely — and offline, where the script is answering from that
same cache, it looks like the shortest path. It is not: the index and the cached
responses are raw upstream data, so reading them by hand skips the version-type
filtering, the exceptions table, and the platform-source detection listed above,
and returns something plausible with no sign that those steps were missed. Ask
the script the question, offline or not; browse the cache only to diagnose the
script itself.
When to read the script source: If the script doesn't do exactly what you need, or fails due to missing dependencies, read the script source. It encodes Maven repository URL patterns, version filtering logic, and package naming heuristics—use it as reference when building similar functionality.
If the script fails, say so. A nonzero exit means the answer has not been verified against live Maven data. Do not silently fall back to a remembered version number or coordinate and present it as current — Jetpack versions change often enough that a memorized answer can be confidently wrong. Report the failure (missing dependency, network error, unresolved package) to the user, including the script's own error message, and consult references/troubleshooting.md before retrying.
What ships with it
20 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.
- completions/jetpack.fish 3.4 KB
- evals/fixtures/history/remember-one-handed-gesture-configuration.json 430 B
- evals/oracles/answer-names-added-symbols 4.0 KB
- evals/oracles/answer-source-history 4.4 KB
- evals/README.md 11 KB
- evals/shared-benchmark.json 11 KB
- references/command-index.md 10 KB
- references/troubleshooting.md 3.4 KB
- scripts/jetpack 71 KB
- scripts/jetpack-samples 14 KB
- tests/fixtures/jetpack-history-stub 899 B
- tests/test-jetpack 8.1 KB
- tests/test-jetpack-dependencies 1.1 KB
- tests/test-jetpack-eval-oracles 5.6 KB
- tests/test-jetpack-inspect 3.8 KB
- tests/test-jetpack-offline 15 KB
- tests/test-jetpack-samples 9.4 KB
- tests/test-jetpack-search 7.4 KB
- tests/test-jetpack-skill-md 1.8 KB
- tests/test-jetpack-version 3.7 KB
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.
- 19d ago Changed · +4 lines 19958427782a
- 1mo ago Changed 2f761547d2ad
- 1mo ago First seen · 261 lines · 98 tokens per session scan A 30d7134dbfcb
jetpack is a skill published in the GitHub repository ithinkihaveacat/dotfiles (48 stars, last pushed today), licensed Apache-2.0. It adds 98 tokens to every session and 2,534 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
aish-add-skills
Create new skills from documents, tutorials, or examples. Use when user wants to create a skill from learning materials or existing content.
diagnose_system_lag
A read-only Linux troubleshooting guide for computers that feel slow, freeze, run out of memory, restart unexpectedly, or have storage or local-network delays. It chooses checks based on the reported symptom.
devops-docker-patterns
Docker containerization expert specializing in multi-stage builds, image optimization, Docker Compose patterns, and production container security. Use for Dockerfile optimization, compose configurations, and container best practices.
devops-platform-engineering
Platform engineering expert specializing in internal developer platforms, self-service infrastructure, Backstage service catalogs, GitOps with ArgoCD, and golden path templates. Use for building developer portals and platform-as-a-product.
dns-diagnose
A read-only tool for finding problems with domain-name resolution, the system that turns names such as example.com into server addresses. It checks local resolvers and DNS records for failures, wrong answers, or changes that are not visible yet.
network-path-diagnose
A read-only tool for checking the network route from this computer to a chosen server or website. It uses standard connection tests to examine reachability, delay, packet loss, and variation in delay.