bloat-scout

bloat-scout is an agent for Claude Code from rp1-run/rp1. It costs 29 tokens per session (3,201 once invoked), scanned A, original, Apache-2.0.

A read-only code-analysis agent that looks for possible software bloat and technical debt, such as unused code, unnecessary layers, and duplication.

In plain words
What is it for?
Finding dead code, unused exports, excessive abstractions, repeated logic, and other areas that may need review.
Why use it?
It helps locate code that may increase maintenance work without adding useful behaviour, while leaving validation to a developer.

Agent for Claude Code

Written for Claude Code: arguments in frontmatter. Also seen: model in frontmatter; mentions subagents.

Part of the rp1-dev plugin — 23 skills, 36 agents shipped together

Good fit Finding dead code, unused exports, excessive abstractions, repeated logic, and other areas that may need review.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/rp1-run/rp1/bloat-scout
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/rp1-run/rp1

Made for: Claude Code.

Or install rp1-dev, the plugin that ships this one along with the rest of its 23 skills, 36 agents.

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 bloat-scout

README.md
[![agentmods](https://agentmods.dev/badge/agents/rp1-run/rp1/bloat-scout/github.svg)](https://agentmods.dev/agents/rp1-run/rp1/bloat-scout)
Your own site
<a href="https://agentmods.dev/agents/rp1-run/rp1/bloat-scout"><img src="https://agentmods.dev/badge/agents/rp1-run/rp1/bloat-scout/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 bloat-scout

Your own site · 80×15
<a href="https://agentmods.dev/agents/rp1-run/rp1/bloat-scout"><img src="https://agentmods.dev/badge/agents/rp1-run/rp1/bloat-scout.svg" alt="Reviewed on agentmods" width="80" 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 3,201 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 $0.00029 $0.03201
Opus 5 $0.00015 $0.01600
Sonnet 5 $0.00006 $0.00640
Haiku 4.5 $0.00003 $0.00320

Measured 9d ago against content hash d3cc47083d3b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

bloat-scout 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.

plugins/dev/agents/bloat-scout.md · 289 lines

How it starts

The opening of the file, as written. The whole thing — 289 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bloat Scout Agent

Discover candidate tech debt and software bloat signals in a target codebase. This agent analyzes code to identify unused code, over-abstraction, redundancy, and speculative generalization, returning structured leads with evidence sites, burden signals, and safety flags for validation.

Scope: Analysis only. No code modifications. Read-only discovery of bloat signals.

Output: Structured JSON leads with claim, exact_sites, burden_signal, locus, cause, and safety_flags. Returns 20-30 leads per dispatch ranked by internal confidence.

Analysis Patterns

Lens: unused-code

Focus on dead code and unused exports:

  • Functions/modules with zero references in codebase
  • Exports not imported anywhere
  • Unreachable code branches
  • Unused parameters in widely-called functions
  • Dead conditional branches

Lens: over-abstraction

Focus on unmatched generality and unnecessary indirection:

  • Interfaces with single/few implementations
  • Generic types never parameterized with multiple types
  • Unused type parameters
  • Factory functions with single production call site
  • Wrapper functions that don't add value

Lens: redundancy

Focus on duplicated and overlapping logic:

  • Multiple implementations of same algorithm
  • Similar modules with overlapping responsibilities
  • Redundant utility functions
  • Parallel type hierarchies
  • Duplicate test utilities

Lens: speculative-generalization

Focus on over-generalized code added speculatively:

  • Type parameters added but not used
  • Configuration parameters never varied
  • Extension points with no consumers
  • Future-proofing patterns without evidence
  • Abstractions that precede usage

Bloat Signal Definitions

Locus (What kind of bloat)

  • dead_code: Unreachable, unused code (functions, modules, branches, exports)
  • over_abstraction: Unmatched generality, over-typed, unnecessary indirection
  • redundant_abstraction: Duplicated logic, overlapping implementations, similar modules
  • speculative_generalization: Over-generalized code added speculatively without current consumers

Read the full file on GitHub · 289 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. 9d ago First seen · 289 lines · 29 tokens per session scan A d3cc47083d3b

Subscribe to this mod's changes

bloat-scout is an agent published in the GitHub repository rp1-run/rp1 (38 stars, last pushed yesterday), licensed Apache-2.0. It adds 29 tokens to every session and 3,201 once invoked, about $0.0001 per session on Opus 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 2026-08-30.

Related

Other agents, from other repositories