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 zenml-io/kitaru-skills --skill kitaru-replay-experimentgit clone --depth 1 https://github.com/zenml-io/kitaru-skillsWrote 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/zenml-io/kitaru-skills/kitaru-replay-experiment)<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.
<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>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 | $0.00079 | $0.02791 |
| Opus 5 | $0.00039 | $0.01396 |
| Sonnet 5 | $0.00016 | $0.00558 |
| Haiku 4.5 | $0.00008 | $0.00279 |
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.
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.
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-experimentset so the server attributes the resulting activity to this skill. - Start or restart a user-controlled worker with
--concurrency 10. UseKITARU_WORKER_CONCURRENCY=10only 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.
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.
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 Changed · +9 lines bb4f2c6bc6ee
- 12d ago First seen · 138 lines · 79 tokens per session scan A 2b4eb4cfb3cc
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.
Other skills, from other repositories
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.
validate-album
Validates album directory structure, file locations, and content integrity. Use before release or whenever the user wants to check an album's structural health.
brooks-sweep
Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user…
api-testing
HTTP API testing for TypeScript (Supertest) and Python (httpx, pytest). Test REST APIs, GraphQL, request/response validation, authentication, and error handling.
bun-jest-migration
Use when migrating from Jest to Bun's test runner, import compatibility, mocks, and config.
bun-test-mocking
Use for mock functions in Bun tests, spyOn, mock.module, implementations, and test doubles.