Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add ShivaeDev/pardes/plugin install onboardingWrote 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/shivaedev/pardes/onboarding)<a href="https://agentmods.dev/skills/shivaedev/pardes/onboarding"><img src="https://agentmods.dev/badge/skills/shivaedev/pardes/onboarding/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/shivaedev/pardes/onboarding"><img src="https://agentmods.dev/badge/skills/shivaedev/pardes/onboarding.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 | $0.00075 | $0.01575 |
| Opus 5.5 | $0.00030 | $0.00630 |
| Sonnet 5.5 | $0.00015 | $0.00315 |
| Haiku 4.5 | $0.00007 | $0.00158 |
Grade B, and why
onboarding 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 2mo 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.
The doctor is a dependency-free script that compares the user's `~/.claude/settings.json` against a manifest of **recommended** (never required) settings tuned for this marketplace's orchestration-heavy style. It is **ad How it starts
The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
onboarding
You are helping a user get oriented in the pardes marketplace and tune their Claude Code setup. This skill has two halves: orient (explain what's here and how it fits together) and doctor (check their config and, only if they say yes, apply recommended settings). Do the orientation first, then offer the doctor — don't run the doctor unprompted unless the user clearly asked for a config check.
Half 1 — Orient the user
Pardes is a small marketplace of focused Claude Code plugins. Most ship one skill; a few ship other artifacts instead (shared infrastructure, a status line, workflow scripts). Explain the pieces in plain terms and, importantly, how they compose — the value is in the combination:
- base — a foundational scaffold; shared hooks and core skills land here as the marketplace grows. Nothing else depends on it yet, so install it only if you want the scaffold present.
- orchestrate — plans one large multi-chunk PR through a short interview, then ships it by dispatching focused sub-agents one chunk at a time. Reach for it when a single PR is too big for one context but is sequenceable into discrete commits.
- shift-leader — the standing autonomous orchestrator above a single PR: it runs a multi-PR / multi-agent effort, dispatches file-disjoint work to parallel worktrees, gates dependent work on merges (never merging itself), opens and monitors each PR, and survives compaction via a durable state file. It uses
orchestrate(if present) to plan+ship each individual large PR. - shell-helpers — dependency-free shell helpers that the orchestration skills lean on: freshen a checkout to a clean baseline, prune merged branches, reap stale worktrees. Available both as PATH commands and as sourceable shell functions.
- pr-description — writes a tight PR description (Why / How / Decisions / Callouts, no filler). Pairs naturally with
orchestrateandshift-leaderwhen a PR is ready to open. - statusline — a rich multi-line status line: model, context-pressure bar, cost, git, PR, and rate limits on the main line, plus per-subagent gauges in the agent panel. Most useful precisely when
shift-leaderhas several sub-agents running — you can watch each one's context pressure. - workflows — a starter library of Workflow-tool scripts — writer→reviewer, read-only investigation, parallel-edit-then-serialized-verify — each callable as
workflows:<name>. They're the concrete orchestration moves the higher-level skills lean on, ready to run or fork.
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.
- 2mo ago First seen · 71 lines · 75 tokens per session scan B 3d4e64a27f21
onboarding is a skill published in the GitHub repository ShivaeDev/pardes (5 stars, last pushed 3mo ago), licensed MIT. It adds 75 tokens to every session and 1,575 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 2026-08-31.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…