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/geoffjay/claude-plugins/cli-distributionnpx skills add geoffjay/claude-plugins --skill cli-distributiongit clone --depth 1 https://github.com/geoffjay/claude-pluginsWhat 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 | $0.00032 | $0.03177 |
| Opus 5 | $0.00016 | $0.01588 |
| Sonnet 5 | $0.00006 | $0.00635 |
| Haiku 4.5 | $0.00003 | $0.00318 |
Grade D, and why
cli-distribution scanned grade D with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo cp target/man/myapp.1 /usr/local/share/man/man1/ Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
RUN apt-get update && apt-get install -y ca-certificates && rm -rf /var/lib/apt/lists/* How it starts
The opening of the file, as written. The whole thing — 551 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLI Distribution Skill
Patterns and best practices for distributing Rust CLI applications to users.
Shell Completion Generation
Using clap_complete
use clap::{CommandFactory, Parser};
use clap_complete::{generate, Generator, Shell};
use std::io;
#[derive(Parser)]
struct Cli {
/// Generate shell completions
#[arg(long = "generate", value_enum)]
generator: Option<Shell>,
// ... other fields
}
fn print_completions<G: Generator>(gen: G, cmd: &mut clap::Command) {
generate(gen, cmd, cmd.get_name().to_string(), &mut io::stdout());
}
fn main() {
let cli = Cli::parse();
if let Some(generator) = cli.generator {
let mut cmd = Cli::command();
print_completions(generator, &mut cmd);
return;
}
// ... rest of application
}
Installation Instructions by Shell
Bash:
# Generate and save
myapp --generate bash > /etc/bash_completion.d/myapp
# Or add to ~/.bashrc
eval "$(myapp --generate bash)"
Zsh:
# Generate and save
myapp --generate zsh > ~/.zfunc/_myapp
# Add to ~/.zshrc
fpath=(~/.zfunc $fpath)
autoload -Uz compinit && compinit
Fish:
# Generate and save
myapp --generate fish > ~/.config/fish/completions/myapp.fish
# Or load directly
myapp --generate fish | source
PowerShell:
# Add to $PROFILE
Invoke-Expression (& myapp --generate powershell)
Dynamic Completions
For commands with dynamic values (like listing resources):
use clap::CommandFactory;
use clap_complete::{generate, Generator};
pub fn generate_with_values<G: Generator>(
gen: G,
resources: &[String],
) -> String {
let mut cmd = Cli::command();
// Add dynamic values to completion
if let Some(subcommand) = cmd.find_subcommand_mut("get") {
for resource in resources {
subcommand = subcommand.arg(
clap::Arg::new("resource")
.value_parser(clap::builder::PossibleValuesParser::new(resource))
);
}
}
let mut buf = Vec::new();
generate(gen, &mut cmd, "myapp", &mut buf);
String::from_utf8(buf).unwrap()
}
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 · 551 lines · 32 tokens per session scan D 7f2c1e39bacc
cli-distribution is a skill published in the GitHub repository geoffjay/claude-plugins (8 stars, last pushed 10mo ago), licensed MIT. It adds 32 tokens to every session and 3,177 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it D with 2 findings (asks for root, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…