kitaru-replay-experiment

kitaru-replay-experiment is a skill for Claude Code, Codex from zenml-io/kitaru-skills. It costs 79 tokens per session (2,791 once invoked), scanned A, a copy of kitaru-replay-experiment, Apache-2.0.

A controlled experiment tool for replaying past agent sessions with one changed condition. Kitaru is the system that stores the accepted cases, evaluators, and replay settings.

In plain words
What is it for?
Use it to compare one candidate change against a fixed set of known cases and review the run settings, tool rules, failures, costs, and missing results.
Why use it?
It provides structured evidence about whether a model, prompt, agent version, or tool policy improved results, made them worse, created trade-offs, or changed nothing clearly.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present.

Part of the kitaru plugin — 7 skills shipped together

Good fit Use it to compare one candidate change against a fixed set of known cases and review the run settings, tool rules, failures, costs, and missing results.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/zenml-io/kitaru-skills/kitaru-replay-experiment
Install

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.

Any agent
npx skills add zenml-io/kitaru-skills --skill kitaru-replay-experiment
Clone the repo
git clone --depth 1 https://github.com/zenml-io/kitaru-skills

Made for: Claude Code, Codex.

Or install kitaru, the plugin that ships this one along with the rest of its 7 skills.

Wrote 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.

agentmods badge for kitaru-replay-experiment

README.md
[![agentmods](https://agentmods.dev/badge/skills/zenml-io/kitaru-skills/kitaru-replay-experiment/github.svg)](https://agentmods.dev/skills/zenml-io/kitaru-skills/kitaru-replay-experiment)
Your own site
<a href="https://agentmods.dev/skills/zenml-io/kitaru-skills/kitaru-replay-experiment"><img src="https://agentmods.dev/badge/skills/zenml-io/kitaru-skills/kitaru-replay-experiment/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.

agentmods 80×15 button for kitaru-replay-experiment

Your own site · 80×15
<a href="https://agentmods.dev/skills/zenml-io/kitaru-skills/kitaru-replay-experiment"><img src="https://agentmods.dev/badge/skills/zenml-io/kitaru-skills/kitaru-replay-experiment.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,791 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 94% copy Near-identical to another mod in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00079 $0.02791
Opus 5 $0.00039 $0.01396
Sonnet 5 $0.00016 $0.00558
Haiku 4.5 $0.00008 $0.00279

Measured 7d ago against content hash bb4f2c6bc6ee, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

kitaru-replay-experiment 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.

Origin

This is a copy

94% identical to kitaru-replay-experiment — 19 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/kitaru-replay-experiment/SKILL.md · 147 lines

How it starts

The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Kitaru replay experiment

Test one candidate condition against known cases and explain whether the available evidence improved, regressed, traded off, or stayed inconclusive. Do not make the deployment decision.

Core contract

  • Start from an accepted behavior, exact cohort version, exact evaluator versions and parameters, and one candidate change. Suggest one bounded candidate only when asked.
  • Replay starts a fresh agent task from each historical session's stored top-level inputs after applying the override. It does not restore an arbitrary checkpoint, conversation, process memory, adapter instance state, filesystem, or external world state.
  • Resolve adapter support and its construction path before asking to run the experiment. A shared replay schema does not prove that an adapter supports a requested override or tool source.
  • Require an explicit tool policy for every tool-using run. Omission resolves to live passthrough on the current server and is unsafe as an implicit default.
  • Carry exact IDs, versions, evaluator parameters, run-spec evidence, tool policy, failures, and missing results forward.
  • Explain remote writes, model and worker compute, cost uncertainty, and possible live effects before execution. One approval after this explanation covers experiment creation and the run start; any tool path with external effects needs separate approval.
  • Use established Kitaru product terms only. Do not coin labels for summaries or steps, such as “run card,” “result card,” “agent fingerprint,” or “execution checksum.” Do not replace a Kitaru object with a friendly-sounding alias such as “accepted baseline”; explain the official term when necessary, then use it consistently. In user-facing text, describe what will happen and what the user must decide in ordinary language.
  • Prefer native Kitaru MCP operations. Use the structured CLI for built-in waiting or another capability MCP does not expose. Verify installed schemas when they differ from the references.
  • Run every Kitaru CLI command and SDK script with KITARU_ACTIVE_SKILL=kitaru-replay-experiment set so the server attributes the resulting activity to this skill.
  • Start or restart a user-controlled worker with --concurrency 10. Use KITARU_WORKER_CONCURRENCY=10 only when the launch surface exposes worker settings through environment variables instead of CLI options.
  • Never bypass a missing adapter, evidence, comparison, or product contract with direct REST calls or ad hoc local state.

Read the full file on GitHub · 147 lines

Files

What ships with it

3 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.

Changes

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.

  1. 7d ago Changed · +9 lines bb4f2c6bc6ee
  2. 12d ago First seen · 138 lines · 79 tokens per session scan A 2b4eb4cfb3cc

Subscribe to this mod's changes

kitaru-replay-experiment is a skill published in the GitHub repository zenml-io/kitaru-skills (4 stars, last pushed 2d ago), licensed Apache-2.0. It adds 79 tokens to every session and 2,791 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 94% identical to kitaru-replay-experiment, differing in 19 lines, and is treated as a copy.