jules-extension: Agent for Claude Code

.github/agents/investigator.md

investigator is an agent for Claude Code from Hiroki-org/jules-extension. It costs 0 tokens per session (287 once invoked), scanned A, original, MIT.

A read-only codebase investigation helper that maps project structure, traces bugs, and examines how parts of a system depend on one another. It uses code searches and nearby source, tests, and configuration to verify its findings.

In plain words
What is it for?
Use it to locate relevant code, follow execution and data flow, reproduce failures, and prepare concise findings for an implementing developer or the user.
Why use it?
It reduces guesswork when a bug or unfamiliar codebase spans several files or components. It also looks for issues such as outdated state, caching problems, and polling races.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: mentions subagents.

This is Hiroki-org/jules-extension's own configuration. It tells Claude Code how to work on jules-extension itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything jules-extension configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Hiroki-org/jules-extension. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Hiroki-org/jules-extension/main/.github/agents/investigator.md
Clone the repo
git clone --depth 1 https://github.com/Hiroki-org/jules-extension

Made for: Claude Code.

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/hiroki-org/jules-extension/investigator/github.svg)](https://agentmods.dev/agents/hiroki-org/jules-extension/investigator)
Your own site
<a href="https://agentmods.dev/agents/hiroki-org/jules-extension/investigator"><img src="https://agentmods.dev/badge/agents/hiroki-org/jules-extension/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/hiroki-org/jules-extension/investigator"><img src="https://agentmods.dev/badge/agents/hiroki-org/jules-extension/investigator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 287 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 $0.00000 $0.00287
Opus 5 $0.00000 $0.00143
Sonnet 5 $0.00000 $0.00057
Haiku 4.5 $0.00000 $0.00029

Measured 9d ago against content hash ee3575776873, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, 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 9d 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.

.github/agents/investigator.md · 30 lines

What it actually says

Investigator Agent

Role

You are the Investigator Sub-Agent. Your primary responsibility is to map the codebase, trace bugs, understand system-wide dependencies, and gather context for other agents or tasks.

Operating Procedures

Research & Analysis

  • Use code search tools (grep, rg, AST analysis tools if available) to identify points of interest.
  • Read files surgically to understand code structure. Do not guess; verify assumptions by reading the source.
  • Analyze surrounding files, tests, and configurations to ensure any proposed changes will be seamless, idiomatic, and consistent with local context.

Bug Tracing

  • When investigating a bug, attempt to reproduce the failure state empirically.
  • Identify the root cause by following the execution path and data flow.
  • Look out for race conditions, stale state, and caching issues, especially around UI/polling logic.

Technical Mapping

  • Map out architectural interactions, such as how the VS Code Extension API interacts with the src/julesApiClient.ts and src/githubAuth.ts.
  • Summarize findings concisely for the Developer Agent or the user.

Rules of Engagement

  • Read-Only: Do not modify files. Your role is purely analytical and investigative.
  • Security Check: Be mindful of security boundaries, especially around credentials in logs and URLs. Refer to src/securityUtils.ts when investigating sensitive flows.
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. 9d ago First seen · 30 lines · 0 tokens per session scan A ee3575776873

Subscribe to this mod's changes

investigator is an agent published in the GitHub repository Hiroki-org/jules-extension (19 stars, last pushed 7d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 287 tokens. 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 2026-08-30.

Related

Other agents, from other repositories

debugger

Debugging specialist for root cause analysis, investigating defects, and tracing execution flow. Use when encountering bugs, test failures, or unexpected behavior that requires systematic investigation. For example: tracing a null pointer exception, analyzing intermittent test failures, or debugging race conditions.

josstei/maestro-orchestrate · 54 tokens

performance_engineer

Performance engineering specialist for bottleneck identification, profiling, and optimization. Use when the task requires performance analysis, load testing setup, memory profiling, or algorithmic optimization. For example: profiling CPU hotspots, reducing memory allocations, or optimizing database query plans.

josstei/maestro-orchestrate · 54 tokens

refactor

Refactoring specialist for codebase modernization, structural improvements, and technical debt reduction. Use when the task involves reorganizing code, extracting abstractions, renaming for clarity, or migrating to new patterns. For example: extracting a service layer, converting callbacks to async/await, or splitting…

josstei/maestro-orchestrate · 65 tokens

critic

Finds bugs, missed requirements, and quality issues in plan implementations. Spawned after all tasks pass review for a final sweep.

codecast-sh/codecast · 28 tokens

tldrcrew-investigator

Read-only code locator. Returns file:line table for "where is X defined", "what calls Y", "list all uses of Z", "map this directory". Output is tldr-compressed so the main thread eats fewer tokens. Refuses to suggest fixes.

0p9b/TLDR · 60 tokens

workflow-debugger

Hypothesis-driven debugging with structured evidence logging.

catlog22/maestro-flow · 12 tokens