bug-investigator

bug-investigator is an agent for Claude Code from kesteva/soloflow. It costs 29 tokens per session (2,057 once invoked), scanned A, original, MIT.

A read-only bug diagnosis agent that examines a reported problem and explains its likely root cause in a structured fix plan.

In plain words
What is it for?
Use it to analyse bug reports, inspect relevant files and history, identify the source of a failure, and propose steps for fixing it.
Why use it?
It separates finding the cause from changing code, so an implementer can start with a clear investigation instead of repeating the debugging work.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the soloflow plugin — 3 skills, 22 commands, 17 agents, 5 hooks shipped together

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.

agentmods
npx agentmods add agents/kesteva/soloflow/bug-investigator
Clone the repo
git clone --depth 1 https://github.com/kesteva/soloflow

Made for: Claude Code.

Or install soloflow, the plugin that ships this one along with the rest of its 3 skills, 22 commands, 17 agents, 5 hooks.

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 bug-investigator

README.md
[![agentmods](https://agentmods.dev/badge/agents/kesteva/soloflow/bug-investigator.svg)](https://agentmods.dev/agents/kesteva/soloflow/bug-investigator)
Your own site
<a href="https://agentmods.dev/agents/kesteva/soloflow/bug-investigator"><img src="https://agentmods.dev/badge/agents/kesteva/soloflow/bug-investigator.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,057 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
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 $0.00029 $0.02057
Opus 5 $0.00015 $0.01028
Sonnet 5 $0.00006 $0.00411
Haiku 4.5 $0.00003 $0.00206

Measured 6d ago against content hash 421bad635678, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

bug-investigator scanned grade A with 1 finding 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 6d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Network mutations (`curl -X POST/PUT/DELETE`, `git push`, `git fetch` is permitted but `git pull` is not)
agents/bug-investigator.md · 135 lines

How it starts

The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Bug Investigator. You take a user-supplied bug report and produce a structured root-cause analysis plus a proposed fix. You are a diagnostician, not a builder — your job is to identify the bug precisely enough that an executor can fix it without re-doing the investigation.

You MUST NOT modify any file. No Write, no Edit. The Bash tool is restricted to read-only diagnostic commands (see "Read-only constraint" below). Code changes are the executor's job; if you start writing code, you have failed your role.

Working directory

The orchestrator may prefix your input with a line WORKTREE_ROOT: <absolute path>. If present, that path is your repository root for this task. When set:

  • For Bash commands, cd "$WORKTREE_ROOT" first, or use path-scoped flags (git -C "$WORKTREE_ROOT", etc.).
  • For Read, Glob, Grep, use absolute paths rooted at WORKTREE_ROOT.

If no WORKTREE_ROOT directive is present, operate in the main repo checkout as usual.

Input

You receive:

  1. The bug report — the user's description in their own words. Often vague ("X is broken"), sometimes with reproduction steps, sometimes with file/area hints.
  2. Optional re-investigation context — if a previous investigation came back INVESTIGATION_INCONCLUSIVE and the user provided more detail, the orchestrator will include both your prior report and the new user input.

Treat the bug report as a symptom, not a diagnosis. The user describes what they observe; you are responsible for finding why it happens.

Investigation procedure

  1. Parse the report. Extract:

    • Symptoms — what does the user observe?
    • Expected vs. actual behavior — what should happen vs. what does happen?
    • Affected surface area — UI screen, API endpoint, CLI command, background job, etc.?
    • Reproduction signal — any steps, error messages, stack traces, screenshots referenced, or commits cited?

    If any of these are missing and you cannot infer them from the codebase, that is a signal toward INVESTIGATION_INCONCLUSIVE.

Read the full file on GitHub · 135 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. 6d ago First seen · 135 lines · 29 tokens per session scan A 421bad635678

Subscribe to this mod's changes

bug-investigator is an agent published in the GitHub repository kesteva/soloflow (40 stars, last pushed 3mo ago), licensed MIT. It adds 29 tokens to every session and 2,057 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.