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/kardebadas/claude-plugin/setupnpx skills add kardebadas/claude-plugin --skill setupgit clone --depth 1 https://github.com/kardebadas/claude-pluginWrote 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/kardebadas/claude-plugin/setup)<a href="https://agentmods.dev/skills/kardebadas/claude-plugin/setup"><img src="https://agentmods.dev/badge/skills/kardebadas/claude-plugin/setup.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 | $0.00064 | $0.01241 |
| Opus 5 | $0.00032 | $0.00620 |
| Sonnet 5 | $0.00013 | $0.00248 |
| Haiku 4.5 | $0.00006 | $0.00124 |
Grade B, and why
setup 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 today.
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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
**Never write to `~/.codex/config.toml`**, or anywhere else under a user's How it starts
The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Setup
Overview
Gets superb's dependencies in place, and says plainly what it could not do.
superb:craft needs nothing. superb:pipeline and superb:bug-fix both
compose superpowers and do not run
without it.
Step 1 — Run the check. Always, first.
Run ./check-deps.sh from this skill's directory. It reports one fact per
line, and its exit code is the instruction:
| Exit | Meaning | What you do |
|---|---|---|
0 |
Everything required is satisfied | Report it. Stop. |
1 |
Something is MISSING or DISABLED |
Run the ACTION lines, then re-check. |
2 |
The state could not be determined | Do not install anything. Report what it said. |
HARNESS claude | codex | unknown
REQUIRED <name> OK | MISSING | DISABLED | ERROR | UNKNOWN <detail>
OPTIONAL <name> OK | MISSING <detail>
MARKET <name> OK | MISSING
ACTION <the command that fixes the line above it>
NOTE <something you need to know that is not actionable>
If check was passed as the argument, report and stop regardless of the exit
code. With no argument, continue to Step 2.
Exit 2 is not a soft failure. ERROR means the query failed, not that the
dependency is absent — a failed claude plugin list says nothing about what is
installed. Installing on an ERROR is how a present, working dependency gets
reinstalled over the top of itself. UNKNOWN means the same for a different
reason: nothing could look. In both cases report the NOTE lines and stop.
Step 2 — Act, where you can
Only on exit 1, and only on Claude Code. Run the ACTION lines in the
order they were printed — a marketplace has to exist before a plugin installs
from it.
DISABLED is not MISSING. An installed-but-disabled plugin looks present
to anything matching on the name, and its skills never load. The action is
claude plugin enable superpowers; reinstalling is not the fix.
What ships with it
2 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.
- today First seen · 110 lines · 64 tokens per session scan B 8fc788359145
setup is a skill published in the GitHub repository kardebadas/claude-plugin (2 stars, last pushed 3d ago), licensed Apache-2.0. It adds 64 tokens to every session and 1,241 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-05.
Other skills, from other repositories
structure-swift-sources
Organize Swift source trees and oversized Swift files by feature, layer, and declaration group; split large files, normalize // MARK: sections, enforce plain-language block-comment file headers, and move TODO and FIXME text into ledger files. Use after format-swift-sources has established a clean formatting baseline.
tips-helpviewer-workflow
Discover local user-guide topics for installed Apple Mac apps through the Tips HelpViewer catalog, with app matching, installed-version capture, result verification, and authoritative fallback routing. Use when Codex needs task-specific help for an installed Apple app, needs to find a menu command through local Help…
mix-compression
Reduce mix output noise (5-15% token savings) by installing rtk filters that compress mix test/credo/dialyzer/compile output before it reaches Claude. Use when long mix output floods context.
phx-mix-compression
Reduce mix output noise (5-15% token savings) by installing rtk filters that compress mix test/credo/dialyzer/compile output before it reaches Claude. Use when long mix output floods context.
quick
Implement small Phoenix changes without planning — add validations, update routes, fix components, create migrations. Use for single-file edits under 50 lines.
phx-freeze
Apply an advisory edit scope in this session. Use for read-only or directory-scoped work; no enforcement hook is installed.