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 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/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/kardebadas/claude-plugin/setup"><img src="https://agentmods.dev/badge/skills/kardebadas/claude-plugin/setup.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 | $0.00064 | $0.01334 |
| Opus 5.5 | $0.00026 | $0.00534 |
| Sonnet 5.5 | $0.00013 | $0.00267 |
| Haiku 4.5 | $0.00006 | $0.00133 |
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 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.
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 — 117 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 unless its optional browser UI is used.
superb:pipeline and superb:bug-fix both compose
superpowers and do not run without it.
Pipeline's standard-library state helper also requires Python 3.11+; Craft's
browser UI remains separately compatible with Python 3.9+.
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.
REQUIRED pipeline-python MISSING is deliberately not followed by an
ACTION: report that Pipeline needs Python 3.11+ and stop. Never install or
upgrade a language runtime on the user's behalf.
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.
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.
- 1mo ago Changed · +7 lines 4e917418f593
- 1mo ago First seen · 110 lines · 64 tokens per session scan B 8fc788359145
setup is a skill published in the GitHub repository kardebadas/claude-plugin (3 stars, last pushed 22d ago), licensed Apache-2.0. It adds 64 tokens to every session and 1,334 once invoked, about $0.0003 per session on Opus 5.5. 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…
collaboration-platform-administration
Administers the email, chat, meeting and file-sharing platform the organization runs on — tenant and domain configuration, mail authentication and routing, phishing and spam controls, shared mailboxes and distribution groups, external sharing and guest access, permission sprawl in file storage, and retention and legal…
service-desk
Runs the IT service desk — intake, triage, prioritization, escalation, knowledge, and the metrics that improve service rather than distort it. Use this to set up or fix a service desk, design ticket priority and escalation, reduce repeat contacts, structure a knowledge base, or work out why a desk hitting its targets…
onboarding-and-offboarding
Designs the joining and leaving experience — first-day readiness, ramp to productivity, knowledge capture, and clean exits. Use this to design or fix onboarding, shorten time to productivity, structure a leaver process, capture knowledge before someone leaves, or coordinate the access and asset steps around a joiner…
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.