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 Kestral-Team/kestral-plugins --skill kestral-setupgit clone --depth 1 https://github.com/Kestral-Team/kestral-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/kestral-team/kestral-plugins/kestral-setup)<a href="https://agentmods.dev/skills/kestral-team/kestral-plugins/kestral-setup"><img src="https://agentmods.dev/badge/skills/kestral-team/kestral-plugins/kestral-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 5.1 | $0.00060 | $0.01294 |
| Opus 5 | $0.00030 | $0.00647 |
| Sonnet 5 | $0.00012 | $0.00259 |
| Haiku 4.5 | $0.00006 | $0.00129 |
Grade A, and why
kestral-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 7d 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Setup
Walk a connected (or about-to-connect) session through Authorize, ask what work they want to plan, then run
multiphase-plan in this conversation.
Entrypoint
This skill is kestral-setup. Hosts may surface it as /kestral:kestral-setup, $kestral-setup, or kestral-setup.
Also match "Connect Kestral", "Authorize Kestral", "get me onto Kestral", or "onboard".
Workflow
0. Identify the host before giving connection steps
When running in Claude, classify the current host as desktop or cli before checking tools or writing any
connection instructions:
- If the app or session metadata identifies Claude Desktop, Claude Cowork, or a Desktop playground, classify it as
desktop. - Otherwise, if a shell is available, follow this instruction exactly:
First detect whether you're running in Desktop or CLI. Check your shell's process ancestry using whatever method is native to your OS, walking up a bounded number of levels and stopping immediately on an empty, missing, or repeated parent PID. If any ancestor is a Claude.app (or equivalent packaged desktop app) process, output exactly desktop; otherwise output exactly cli.
- If neither signal is available, ask whether the user is in Claude Desktop or Claude Code CLI and stop until they answer.
Lack of a TTY, a non-interactive session, or inability to open OAuth from the current chat does not mean cli.
Never default to CLI, tell a Desktop user to open an "interactive Claude session," or recommend /mcp until the host
has been classified.
1. Connect if Kestral tools are missing
Look for Kestral MCP tools in this session (whoami, execute_operation, or entity_lookup).
If they are present: go to step 2.
If they are missing: the plugin is installed but its connector is unavailable in this conversation. Use exactly one matching entry below. Do not combine hosts or synthesize generic "interactive session" instructions.
Connect first. Cursor loads plugin skills in this session after install.
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.
- 7d ago First seen · 104 lines · 60 tokens per session scan A 492b3b2e6f88
kestral-setup is a skill published in the GitHub repository Kestral-Team/kestral-plugins (4 stars, last pushed 19d ago), licensed Apache-2.0. It adds 60 tokens to every session and 1,294 once invoked, about $0.0003 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.
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…
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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
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…