investigator

investigator is an agent for Claude Code from makigjuro/cloudstack-ai-plugins. It costs 18 tokens per session (757 once invoked), scanned A, original, MIT.

An evidence-gathering agent for diagnosing software problems. It collects facts from errors, logs, code, configuration, recent changes, and tests without deciding the cause.

In plain words
What is it for?
Use it to search for related errors, inspect affected code and history, check configuration, and find relevant tests.
Why use it?
It gives the main investigator organized evidence to compare possible explanations instead of relying on guesses.

Agent for Claude Code

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

Part of the dev-workflow plugin — 18 skills, 4 agents, 2 hooks, 1 MCP server shipped together

Good fit Use it to search for related errors, inspect affected code and history, check configuration, and find relevant tests.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/makigjuro/cloudstack-ai-plugins/investigator
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.

Clone the repo
git clone --depth 1 https://github.com/makigjuro/cloudstack-ai-plugins

Made for: Claude Code.

Or install dev-workflow, the plugin that ships this one along with the rest of its 18 skills, 4 agents, 2 hooks, 1 MCP server.

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 investigator

README.md
[![agentmods](https://agentmods.dev/badge/agents/makigjuro/cloudstack-ai-plugins/investigator/github.svg)](https://agentmods.dev/agents/makigjuro/cloudstack-ai-plugins/investigator)
Your own site
<a href="https://agentmods.dev/agents/makigjuro/cloudstack-ai-plugins/investigator"><img src="https://agentmods.dev/badge/agents/makigjuro/cloudstack-ai-plugins/investigator/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 investigator

Your own site · 80×15
<a href="https://agentmods.dev/agents/makigjuro/cloudstack-ai-plugins/investigator"><img src="https://agentmods.dev/badge/agents/makigjuro/cloudstack-ai-plugins/investigator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 757 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 $0.00018 $0.00757
Opus 5.5 $0.00007 $0.00303
Sonnet 5.5 $0.00004 $0.00151
Haiku 4.5 $0.00002 $0.00076

Measured 4d ago against content hash e0979d95022e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

investigator 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 4d 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.

plugins/dev-workflow/agents/investigator.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Investigator Agent

Evidence gatherer for diagnosing problems. Collects facts systematically — does not draw conclusions.

When to Use

Run as an agent from /diagnose. Gathers evidence from multiple sources so the main agent can form and test hypotheses.

Evidence Sources

1. Error Messages & Logs

Search for error patterns in the codebase and any available logs.

# Recent git history
git log --oneline -20

# Search for related errors
grep -rn "ERROR_CODE" src/

# Search log patterns (if --logs flag)
grep -rn "{error pattern}" logs/

2. Code Analysis

Find the code related to the problem and check recent changes.

# Find related code
grep -rn "{symptom keyword}" src/

# Recent changes to affected area
git log -p --since="1 week ago" -- {affected paths}

# Find usages and dependencies
grep -rn "{function/class name}" src/

3. Configuration

Check for misconfigurations that could cause the issue.

# Check configuration files
grep -ri "{related config}" src/**/appsettings*.json src/**/*.config

# Check environment variables in code
grep -rn "GetEnvironmentVariable\|GetValue<\|process\.env\." src/

4. Tests

Find related tests and check their status.

# Find related tests
grep -rn "{feature}" tests/

# Run related tests
dotnet test --filter "{test pattern}" --no-build
# or: npm test -- --grep "{test pattern}"

5. Git History

Check for recent changes that might have introduced the problem.

# Recent commits
git log --oneline -20

# Changes to specific files
git log --oneline -- {file path}

# Blame specific lines
git blame {file} -L {start},{end}

6. Library Documentation (context7)

When the error involves a specific library, look up its docs:

  1. mcp__plugin_dev-workflow_context7__resolve-library-id with the library name
  2. mcp__plugin_dev-workflow_context7__query-docs with the library ID and the error message or pattern

Use this for any library in your project's dependency tree — EF Core, Express, Django, Spring Boot, React, etc.

Read the full file on GitHub · 123 lines

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. 4d ago Changed · -2 lines e0979d95022e
  2. 1mo ago First seen · 125 lines · 18 tokens per session scan A e5ef1c25c8a5

Subscribe to this mod's changes

investigator is an agent published in the GitHub repository makigjuro/cloudstack-ai-plugins (1 stars, last pushed 4d ago), licensed MIT. It adds 18 tokens to every session and 757 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-31.

Related

Other agents, from other repositories

ia-performance-oracle

Analyzes code for performance bottlenecks, algorithmic complexity, database queries, memory usage, and scalability. Use after implementing features or when performance concerns arise.

iliaal/whetstone · 37 tokens

ia-bug-reproduction-validator

Validates, reproduces, and root-cause analyzes bug reports (does not fix). Use when a bug report needs verification and root-cause identification before committing to a fix; invoked without a GitHub issue. For issue-linked reproduction use /ia-reproduce-bug.

iliaal/whetstone · 62 tokens

code-explorer

Read-only codebase explorer — searches, maps, and explains code structure. Use when a skill needs to delegate codebase exploration without risk of modification.

harnessprotocol/harness-kit · 34 tokens

code-locator

Delegated, token-isolated code search for C#/.NET or Unreal C++ projects open in JetBrains Rider. Hand it "where is X defined", "what calls Y", "all usages of Z", "find the file named W", "type info at this position" — it uses Rider's MCP symbol/reference index (not raw grep) and returns ONLY a compact file:line…

JSungMin/rider-mcp-enforcer · 114 tokens

divi5-performance

Use this agent when auditing Divi 5 site performance, diagnosing slow pages, improving Core Web Vitals (LCP, INP, CLS), reducing render-blocking CSS, debugging font/image loading, configuring Divi's Critical CSS / Dynamic CSS / Inline Stylesheets, or resolving conflicts between Divi and performance plugins (WP Rocket…

cjsimon2/Divi5-ToolKit · 129 tokens

divi5-error-learner

Use this agent when the user pastes Divi error messages, console errors from Divi pages, or describes CSS issues they encountered in Divi 5. Analyzes the error, provides solutions, and updates the plugin's knowledge base to prevent future occurrences.

cjsimon2/Divi5-ToolKit · 61 tokens