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/lucasnad27/claude-plugins/setupnpx skills add lucasnad27/claude-plugins --skill setupgit clone --depth 1 https://github.com/lucasnad27/claude-pluginsWrote 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/lucasnad27/claude-plugins/setup)<a href="https://agentmods.dev/skills/lucasnad27/claude-plugins/setup"><img src="https://agentmods.dev/badge/skills/lucasnad27/claude-plugins/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 | $0.00020 | $0.02154 |
| Opus 5 | $0.00010 | $0.01077 |
| Sonnet 5 | $0.00004 | $0.00431 |
| Haiku 4.5 | $0.00002 | $0.00215 |
Grade A, and why
setup scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Setup Research-Plan-Implement Workflow
This skill analyzes a project's language, framework, and tooling, then adapts the reference templates into customized skills and agents in the project's .claude/ directory.
Supporting references in this skill's directory (${CLAUDE_SKILL_DIR}) — read each when you reach the step that needs it, not upfront:
detection.md— what to read, what to extract, how to fill gaps (Steps 1-2)adaptation.md— how to adapt each template: what must survive, what register to write in, where to use judgment (Step 5)upgrade.md— upgrading an existing install: telling a user's customizations apart from stale template, and the migration paths
Before You Start
Recommend the user create a branch first, so they can review the generated files as a diff:
Tip: I recommend creating a branch before we set up the workflow — that way
you can review the generated files as a diff before merging them into your project.
git checkout -b setup-rpi-workflow
If they're already on a feature branch, that's fine — just make sure they know setup will create files in .claude/.
Step 1: Analyze the project
Read detection.md, then inspect the project: language, framework, package manager, test/lint/format/build/typecheck commands, database tooling, issue tracker, and where workflow artifacts should live.
Present what you found, marking anything you couldn't determine.
Then check for an existing installation (see detection.md). If one exists, switch to upgrade.md instead of continuing here.
Step 2: Fill in the gaps
Ask for whatever you couldn't detect, batched into as few turns as possible — see detection.md for the batching approach. Then present the complete configuration and confirm it before generating anything.
Step 3: Ask preferences
- Artifacts directory — where research, designs, plans, and review metadata get written. Default to
.rpi/; state it rather than asking an open question, and let them name a different root if they want one. It's flat: the type is the filename's last segment (-research,-design,-plan,-review), so nothing nests. Don't offer to customize the naming. - Additional commands — any custom verification commands or project-specific testing notes to fold in?
- Gitignore — recommend ignoring the artifacts root: these are working notes, not source, and keeping them out of git keeps PRs clean. One line,
.rpi/. If artifacts are already tracked, offergit rm --cached -r .rpi/to untrack without deleting. - Confirm — ready to generate?
What ships with it
24 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.
- adaptation.md 8.5 KB
- detection.md 4.9 KB
- reference/agents/artifact-analyzer.md 5.3 KB
- reference/agents/artifact-locator.md 3.4 KB
- reference/agents/branch-ticket-detector.md 5.9 KB
- reference/agents/codebase-analyzer.md 4.1 KB
- reference/agents/codebase-locator.md 3.2 KB
- reference/agents/codebase-pattern-finder.md 4.0 KB
- reference/agents/query-planner.md 2.6 KB
- reference/agents/web-search-researcher.md 4.7 KB
- reference/scripts/herdr-phase.sh 2.4 KB runs code
- reference/skills/create-plan/SKILL.md 9.3 KB
- reference/skills/create-plan/template.md 2.1 KB
- reference/skills/design-doc/SKILL.md 5.0 KB
- reference/skills/design-doc/template.md 2.7 KB
- reference/skills/guide/SKILL.md 2.9 KB
- reference/skills/guide/topics.md 16 KB
- reference/skills/implement-plan/review-metadata-template.md 1.0 KB
- reference/skills/implement-plan/SKILL.md 13 KB
- reference/skills/iterate-plan/SKILL.md 5.1 KB
- reference/skills/prepare-pr/SKILL.md 15 KB
- reference/skills/prepare-pr/tuicr-walkthrough.md 13 KB
- reference/skills/research-codebase/SKILL.md 11 KB
- upgrade.md 18 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.
- 4d ago First seen · 205 lines · 20 tokens per session scan A 7f80d2079a59
setup is a skill published in the GitHub repository lucasnad27/claude-plugins (3 stars, last pushed 6d ago), licensed MIT. It adds 20 tokens to every session and 2,154 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…