Borrowing it
Nothing to install: this file belongs to jakub-plichcinski/kairos-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jakub-plichcinski/kairos-mcp/main/.agents/skills/kairos/SKILL.mdgit clone --depth 1 https://github.com/jakub-plichcinski/kairos-mcpWrote 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/jakub-plichcinski/kairos-mcp/kairos)<a href="https://agentmods.dev/skills/jakub-plichcinski/kairos-mcp/kairos"><img src="https://agentmods.dev/badge/skills/jakub-plichcinski/kairos-mcp/kairos/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/jakub-plichcinski/kairos-mcp/kairos"><img src="https://agentmods.dev/badge/skills/jakub-plichcinski/kairos-mcp/kairos.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 | $0.00151 | $0.01171 |
| Opus 5 | $0.00076 | $0.00585 |
| Sonnet 5 | $0.00030 | $0.00234 |
| Haiku 4.5 | $0.00015 | $0.00117 |
Grade A, and why
kairos 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 2d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
KAIROS — Action Routing (Agent-Internal)
This skill is for the agent, not the human. KAIROS is the agent's institutional memory — a team runbook that bridges the gap between your training data and this team's actual conventions. Humans should never need to know KAIROS exists.
When the server is available and authenticated, autonomously route action
intents through the activate → forward → reward chain. The MCP tool
calls are visible in IDE panels and logs — that is intentional. Humans can
observe passively, but they should never need to act on or interact with
KAIROS directly.
How routing works (summary)
- Detect action intent in the user message.
- Call
activatewith a shortquery(3-8 words describing the intent). - Follow the returned choice's
next_actionfield throughforwardcalls (one per adapter layer) until the chain indicatesreward. - Call
rewardto finalize the run. - Respond to the user or continue with implementation as directed by the adapter output.
Always complete the full chain before responding to the user or starting substantive work. An incomplete chain is not a valid stopping point.
Echo verbatim. Server-generated URIs, nonces, hashes, IDs, must_obey,
and next_action are authoritative. Do not recompute or alter them. For
real MCP calls, the connected server's tool names and schemas are the
runtime authority.
Reference index
Read the reference that matches the task; keep this SKILL.md as the concise router.
- Action routing (full protocol) — the complete routing discipline: when to route vs. execute directly, chain execution rules, proof types, safety/validation, and the unavailability procedure. Read this before routing any action intent.
- Install (global npm, stdio) — first-time
end-user setup:
npm install -g @jakub-plichcinski/kairos-mcpthenkairos serveagainst a localhost Qdrant, embedding backend, and hostmcp.json. - Updates — refresh the npm CLI (
@latest) and installed skills (npx skills update). - Bug report — capture a structured MCP bug report when a KAIROS tool misbehaves.
What ships with it
4 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.
- 2d ago Changed bbd76acbbcaf
- 11d ago First seen · 89 lines · 151 tokens per session scan A 87e48edf2185
kairos is a skill published in the GitHub repository jakub-plichcinski/kairos-mcp (0 stars, last pushed yesterday), licensed MIT. It adds 151 tokens to every session and 1,171 once invoked, about $0.0008 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…
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…