kitaru-replay-experiment

kitaru-replay-experiment is a skill for Codex from decodingai-magazine/building-a-coding-agent-from-scratch-course. It costs 79 tokens per session (2,449 once invoked), scanned A, original, Apache-2.0.

A controlled experiment workflow for replaying recorded agent tasks with one proposed change. It compares the new results with an accepted set of past cases using fixed evaluators, which are tools or rules for judging results.

In plain words
What is it for?
Use it to compare a model, prompt, system instruction, setting, agent version, or tool policy against a known cohort of tasks.
Why use it?
It separates measured evidence from deployment decisions and makes missing results, tool behavior, costs, and evaluator versions visible. This avoids treating an uncontrolled replay as proof that a change helped.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: installed under .agents/ (shared by several agents).

Good fit Use it to compare a model, prompt, system instruction, setting, agent version, or tool policy against a known cohort of tasks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/decodingai-magazine/building-a-coding-agent-from-scratch-course/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 decodingai-magazine/building-a-coding-agent-from-scratch-course --skill kitaru-replay-experiment
Clone the repo
git clone --depth 1 https://github.com/decodingai-magazine/building-a-coding-agent-from-scratch-course

Made for: Codex.

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/decodingai-magazine/building-a-coding-agent-from-scratch-course/kitaru-replay-experiment/github.svg)](https://agentmods.dev/skills/decodingai-magazine/building-a-coding-agent-from-scratch-course/kitaru-replay-experiment)
Your own site
<a href="https://agentmods.dev/skills/decodingai-magazine/building-a-coding-agent-from-scratch-course/kitaru-replay-experiment"><img src="https://agentmods.dev/badge/skills/decodingai-magazine/building-a-coding-agent-from-scratch-course/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/decodingai-magazine/building-a-coding-agent-from-scratch-course/kitaru-replay-experiment"><img src="https://agentmods.dev/badge/skills/decodingai-magazine/building-a-coding-agent-from-scratch-course/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 2,449 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 original No closer match found 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 $0.02449
Opus 5 $0.00039 $0.01224
Sonnet 5 $0.00016 $0.00490
Haiku 4.5 $0.00008 $0.00245

Measured 2d ago against content hash c2de0847552c, 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 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.agents/skills/kitaru-replay-experiment/SKILL.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 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 · 136 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. 2d ago First seen · 136 lines · 79 tokens per session scan A c2de0847552c

Subscribe to this mod's changes

kitaru-replay-experiment is a skill published in the GitHub repository decodingai-magazine/building-a-coding-agent-from-scratch-course (387 stars, last pushed today), licensed Apache-2.0. It adds 79 tokens to every session and 2,449 once invoked, about $0.0004 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 2026-09-09.

Related

Other skills, from other repositories