Agent skill · AI & Agents

kyoko-instrument

Wire an AI agent's telemetry into Kyoko and prove one real run shows up.

kayba-aigithub.com/kayba-aiGitHub ↗
claude-codeApache-2.0
Install
npx skills add kayba-ai/Kyoko --skill kyoko-instrument --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 1
SKILL.md size: 8 KB
Bundled scripts: none
Path: kyoko/assets/skills/kyoko-instrument/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 92
Language: Python

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

You are helping instrument an AI agent so its next meaningful run shows up in Kyoko. Kyoko is a local-first repair loop: the user's agent runs the workflow, a recorder captures the run/spans, and Kyoko ingests that telemetry so it can be inspected, diagnosed, and improved. Kyoko does not run the agent. Your job is to get **one real run** into Kyoko with the smallest safe change, verify it actually landed, and only then enrich it. Use Kyoko's documented ingest paths. Do not invent endpoints or SDK calls. ## Core Rules - Give visible progress. Say what phase you are in, what you found, and what you are about to edit. One or two sentences per update. - Before editing any file, tell the user the intended change and how risky it is. - Instrument one real agent entry point first. If several are plausible, ask which one should appear in Kyoko. - Get a minimal run in first, then enrich. Do not trace every helper before a basic run lands. - Prefer the offline file path for the first run (see below). It needs no running server, so it is the most reliable way to prove the pipe works. - Verification is required. Success means Kyoko shows a real run, not just that the SDK imported. ## Mental Mo

What's inside
Steps it walks through
  1. Core Rules
  2. Mental Model: How A Run Gets Into Kyoko
  3. Phase 0: Orient
  4. Phase 1: Get One Real Run In (Offline)
  5. Phase 2: Enrich
  6. Choosing The Path
  7. Just Exploring?
  8. Verification
  9. Handoff
Commands it runs
kyoko ingest --db /tmp/kyoko.db kyoko-run.json --json
kyoko runs --db /tmp/kyoko.db --json
kyoko serve --db /tmp/kyoko.db   # then open http://127.0.0.1:8765
kyoko demo --db /tmp/kyoko-demo.db --json
kyoko serve --db /tmp/kyoko-demo.db   # open http://127.0.0.1:8765
About this skill
What does the kyoko-instrument skill do?

Wire an AI agent's telemetry into Kyoko and prove one real run shows up.

How do I install it?

Run `npx skills add kayba-ai/Kyoko --skill kyoko-instrument --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From kayba-ai/Kyoko, a repository with 92 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going