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.
git clone --depth 1 https://github.com/rp1-run/rp1Wrote 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.
[](https://agentmods.dev/agents/rp1-run/rp1/bloat-scout)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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
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.
- 9d ago First seen · 289 lines · 29 tokens per session scan A d3cc47083d3b
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.
Other agents, from other repositories
silent-failure-hunter
Detects swallowed errors — empty catch blocks, promise suppression, fallback masking, log-and-forget, catch-alls, and unexplained linter suppressions — across TS/JS, Python, Go, Rust, Java/Kotlin, and Bash, with severity-graded findings and concrete fixes.
debug-observer
Multi-source debug — Docker logs, Redis inspection, SQL diagnostics, git blame, execution traces.
health-checker
Project health dashboard — auto-detects the stack, runs 9 checks (compilation, tests, TODO inventory, API spec drift, migration pairs, deps, security, docs, bundle) and reports OK/WARN/FAIL per check plus an overall HEALTHY / NEEDS ATTENTION / UNHEALTHY verdict.
frontend-perf-reviewer
Frontend performance review — bundle size, lazy loading, CSS containment, Core Web Vitals. Activate when reviewing frontend code for performance.
r3f-scene-reviewer
Review React Three Fiber and Three.js code — color management, tone mapping, texture pipeline, GLB handling, useFrame performance, disposal patterns. Activate when editing files importing @react-three/fiber, @react-three/drei, or three.
audit-bots
Audit Telegram bot code for goroutine safety, rate limits, callback integrity, and production readiness.