kitaru-investigation

kitaru-investigation is a skill for Claude Code from zenml-io/kitaru-skills. It costs 163 tokens per session (5,139 once invoked), scanned A, a copy of kitaru-investigation, Apache-2.0.

A guided process for investigating an AI agent by reviewing its code or recorded sessions, then defining an observed behavior and preparing a controlled experiment. Kitaru is the system this process uses to organize agents, traces, reviews, and evaluations.

In plain words
What is it for?
Use it to connect or inspect an agent, import or record sessions, review traces, create a versioned test group, choose an evaluator, and hand one bounded change to a replay experiment.
Why use it?
It keeps recorded behavior separate from desired behavior and requires a person to judge the evidence before a change is tested.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the kitaru plugin — 7 skills shipped together

Good fit Use it to connect or inspect an agent, import or record sessions, review traces, create a versioned test group, choose an evaluator, and hand one bounded change to a replay experiment.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/zenml-io/kitaru-skills/kitaru-investigation
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-investigation
Clone the repo
git clone --depth 1 https://github.com/zenml-io/kitaru-skills

Made for: Claude Code.

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-investigation

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/zenml-io/kitaru-skills/kitaru-investigation"><img src="https://agentmods.dev/badge/skills/zenml-io/kitaru-skills/kitaru-investigation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 163 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,139 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 95% 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 $0.00163 $0.05139
Opus 5 $0.00081 $0.02570
Sonnet 5 $0.00033 $0.01028
Haiku 4.5 $0.00016 $0.00514

Measured yesterday against content hash 45d37af678f3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

kitaru-investigation 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 yesterday.

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

95% identical to kitaru-investigation — 75 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-investigation/SKILL.md · 477 lines

How it starts

The opening of the file, as written. The whole thing — 477 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Kitaru investigation

Treat this skill as Kitaru's evidence-led front door for real agents and traces. Guide one continuous journey from the evidence the user has to a reviewed behavior and, when they want to test a change, the kitaru-replay-experiment skill.

Core contract

  • Treat the human as the judge. Select, summarize, organize, and compile evidence; never turn an agent suggestion into a human label.
  • Preserve durable Kitaru state. Re-read existing objects before creating replacements, and carry exact agent, import, insight, session, investigation, investigation-session, annotation, cohort-version, evaluator, and evaluator-version identifiers plus evaluator agent scope forward.
  • Separate observed behavior from desired behavior. A trace records what happened, not what should have happened or whether the external outcome was correct.
  • Distinguish agent behavior, external dependency behavior, product purpose, and independent outcome evidence.
  • Use open observations before proposing a taxonomy. Deterministic signals may select sessions; they do not judge them.
  • Explain remote writes and paid or live execution before running them. Ask for one proportional confirmation at the point of action.
  • Prefer native Kitaru MCP operations when available. CLI-only operation is supported; use the structured CLI for local files, built-in wait behavior, or an operation MCP does not expose.
  • Run every Kitaru CLI command and SDK script with KITARU_ACTIVE_SKILL=kitaru-investigation 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.
  • Stop at a useful durable checkpoint when a required source, payload, permission, worker, product contract, or UI capability is unavailable.

Keep the experience light

  • Lead with the current state and one next useful action.
  • Use ordinary language for user decisions. Keep internal labels such as trace-first, cold-start, question keys, and selectors out of the lead.
  • Ask for one meaningful judgment at a time. Do not turn setup into a long questionnaire.
  • Prefer short prose during active review. Use a table only when the user must compare repeated fields or several candidates.
  • Summarize structured output instead of dumping JSON. Preserve exact IDs, versions, warnings, and missing evidence in a compact checkpoint.
  • Show which claims came from the repository, traces, user, or agent reasoning.

Read the full file on GitHub · 477 lines

Files

What ships with it

5 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. yesterday Changed · +27 lines · +13 tokens per session 45d37af678f3
  2. 7d ago Changed · +6 lines 53e8c7b7d858
  3. 12d ago First seen · 444 lines · 150 tokens per session scan A 147234723df9

Subscribe to this mod's changes

kitaru-investigation is a skill published in the GitHub repository zenml-io/kitaru-skills (4 stars, last pushed 2d ago), licensed Apache-2.0. It adds 163 tokens to every session and 5,139 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. It is 95% identical to kitaru-investigation, differing in 75 lines, and is treated as a copy.

Related

Other skills, from other repositories

cran-extrachecks

Prepare R packages for CRAN submission by checking for common ad-hoc requirements not caught by devtools::check(). Use when: (1) Preparing a package for first CRAN release, (2) Preparing a package update for CRAN resubmission, (3) Reviewing a package to ensure CRAN compliance, (4) Responding to CRAN reviewer feedback.…

posit-dev/skills · 98 tokens

mirai

Help users write correct R code for async, parallel, and distributed computing using mirai. Use when users need to run R code asynchronously or in parallel, write mirai code with correct dependency passing, set up parallel workers, convert from future or parallel, use miraimap, integrate with Shiny or promises, or…

posit-dev/skills · 73 tokens

r-cran-status

Look up an R package's live status on cran.r-project.org - submission/review state (queue, human review, waiting, archived, past version's fate) or R CMD check results (OK/NOTE/WARN/ERROR per platform). Use for "what's the CRAN status of X", "did X get accepted/rejected", "is X passing CRAN checks", "when was version…

posit-dev/skills · 89 tokens

paper-opportunity-radar

Run a cumulative daily or retrospective sweep of research papers on a chosen topic, audit their claims, methods, integrity signals, and independent support, then identify overlooked but feasible project or business opportunities in a detailed source-grounded report. Use when asked to monitor papers every day, mine…

tamdogood/builder-essential-skills · 98 tokens

paper-verification

Use when the user wants to verify paper claims against code or data, audit numerical accuracy, check formula-code alignment, or validate citation accuracy. Triggers on phrases like "verify claims", "check numbers", "do the numbers match", "formula vs code", "audit the paper", or "cross-check results".

fcakyon/phd-skills · 67 tokens

paper-writing

Use when the user wants to write, structure, or revise academic paper sections, improve notation consistency, or refine figures and tables. Triggers on phrases like "write the abstract", "structure the methods", "improve this section", "notation consistency", "figure refinement", or "paper structure".

fcakyon/phd-skills · 63 tokens