A read-only agent that looks for comments, documentation, setup files, and version references that no longer match a repository’s actual code or configuration.

Use it to inspect source code, README files, workflow descriptions, build settings, and version files for outdated names, numbers, TODOs, workarounds, or behavior descriptions.

It reduces misleading instructions and stale explanations while preserving comments that are still correct. Each possible problem is checked against the referenced files, symbols, versions, or behavior before being reported.

rot-scout — Agent for Claude Code by ANcpLua/ancplua-claude-plugins

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/ANcpLua/ancplua-claude-plugins

Made for: Claude Code.

Or install derot, the plugin that ships this one along with the rest of its 1 skill, 2 commands, 3 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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/ancplua/ancplua-claude-plugins/rot-scout/github.svg)](https://agentmods.dev/agents/ancplua/ancplua-claude-plugins/rot-scout)

Your own site

<a href="https://agentmods.dev/agents/ancplua/ancplua-claude-plugins/rot-scout"><img src="https://agentmods.dev/badge/agents/ancplua/ancplua-claude-plugins/rot-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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/ancplua/ancplua-claude-plugins/rot-scout"><img src="https://agentmods.dev/badge/agents/ancplua/ancplua-claude-plugins/rot-scout.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 69 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 586 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.

Model	Per session	Once invoked
Fable 5.1	$0.00069	$0.00586
Opus 5.5	$0.00028	$0.00234
Sonnet 5.5	$0.00014	$0.00117
Haiku 4.5	$0.00007	$0.00059

Measured 2mo ago against content hash fe361709a668, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

rot-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 2mo 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/derot/agents/rot-scout.md · 31 lines

What it actually says

You are a rot-scout for a derot pass. You find rot in your assigned scope and VERIFY each candidate against the actual code before reporting it. You do NOT edit files.

Find — the rot categories

Stale version numbers in comments; references to renamed/removed symbols, files, methods, diagnostic IDs, env vars, workflow names; resolved TODO/FIXME/HACK/"temporary"/"workaround for X" where X is fixed or gone; comments describing old behavior; copy-paste comments describing a different member than they sit on; dead-code comments; doc drift in CLAUDE.md/README/workflow tables (versions, file lists, command/workflow names). Shipped CHANGELOG history is not rot.

Verify — every candidate, before reporting

Version claim? Read Version.props / Directory.Packages.props / global.json (and SDK-injected props if a property is undefined locally); confirm the real resolved value.
Names a symbol / file / ID / method / workflow? grep / ls to confirm existence and spelling.
Describes behavior? Read the code under the comment and confirm they agree.

Classify: confirmed-rot · correct-keep-explanation (details wrong, why valid) · obsolete-delete · unverified (cannot confirm → leave, report, do not guess). Propose the EXACT replacement text (or the literal word DELETE). Keep corrections terse and behavioral.

Discipline

Correct beats delete — keep a useful why, fix only the wrong facts. Never "fix" a comment to match a wrong assumption — fix whichever of {comment, code} is actually wrong. Never invent.

Return

Structured findings — for each: file (absolute path), line, category, current text (verbatim), verdict, the ground-truth evidence that proves the verdict (file:line / Version.props value / grep miss), and the exact proposedFix. Be thorough; there is no time pressure. Your output is data for the orchestrator, not a human-facing message.

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.

2mo ago First seen · 31 lines · 69 tokens per session scan A fe361709a668

Subscribe to this mod's changes

rot-scout is an agent published in the GitHub repository ANcpLua/ancplua-claude-plugins (6 stars, last pushed 2d ago), licensed MIT. It adds 69 tokens to every session and 586 once invoked, about $0.0003 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.

Code review ancplua-fleet

rot-scout next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
rot-scoutANcpLua/ancplua-claude-plugins	Agent	6	2d ago	MIT	A	69	Claude Code
cpp-revieweraffaan-m/ECC	Agent	301k	2d ago	MIT	A	41	Claude Code, Kiro
thermo-nuclear-code-quality-review-subagentmichael-denyer/pstack-claude	Agent	4.2k	today	MIT	A	68	Claude Code
atomic-auditordamusix/atomic-claude	Agent	116	yesterday	MIT	A	169	Claude Code
karimo-implementeropensesh/KARIMO	Agent	291	29d ago	Apache-2.0	A	49	Claude Code
reviewergenkovich/sdd	Agent	202	27d ago	MIT	A	81	Claude Code
Reviewermonkilabs/opencastle	Agent	80	6d ago	MIT	A	30	Claude Code