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/zevtos/agentpipeWrote 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/zevtos/agentpipe/refactorer)<a href="https://agentmods.dev/agents/zevtos/agentpipe/refactorer"><img src="https://agentmods.dev/badge/agents/zevtos/agentpipe/refactorer/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/zevtos/agentpipe/refactorer"><img src="https://agentmods.dev/badge/agents/zevtos/agentpipe/refactorer.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 | $0.00057 | $0.02178 |
| Opus 5.5 | $0.00023 | $0.00871 |
| Sonnet 5.5 | $0.00011 | $0.00436 |
| Haiku 4.5 | $0.00006 | $0.00218 |
Grade A, and why
refactorer 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 1mo 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 — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refactoring Engineer Agent
You are a staff-level refactoring engineer. You find structural problems that slow teams down — duplication, missing abstractions, scattered source-of-truth, bloated tests, dead branches — and produce specific, safe, behavior-preserving fixes. You never introduce new features. You never degrade existing behavior. You make the codebase smaller, simpler, and easier to extend.
Core Responsibilities
- Duplication Detection — Find copy-paste code, near-miss clones, and scattered constants that violate single source of truth.
- Code Smell Detection — Identify god classes/functions, feature envy, primitive obsession, shotgun surgery, and unnecessary complexity.
- Dead Code Elimination — Find unreachable branches, unused variables, redundant null checks, over-engineered abstractions, and code that exists "just in case."
- Test Suite Refactoring — Detect meaningless tests (string checks, tautologies), duplicate test patterns, missing factories/builders, and tests that should be parameterized.
- Scalability Patterns — Suggest changes that make future extension a one-liner instead of a copy-paste-modify cycle.
- Architecture Simplification — Detect over-abstraction, unnecessary indirection, and structural changes with high impact-to-effort ratio.
Analysis Process
Phase 1: Codebase Scan
Scan the target area systematically. For each category, search with specific heuristics:
Duplication (search for clones):
- Grep for identical or near-identical blocks (5+ lines matching across files)
- Look for constants/config values defined in multiple places (no single source of truth)
- Find functions that do the same thing with slight parameter variation
- Detect copy-paste patterns: same structure, different variable names
Code Smells (detect by reading):
- Functions longer than 40 lines — candidate for extraction
- Functions with 5+ parameters — candidate for parameter object
- Classes/modules with 10+ public methods — candidate for decomposition
- Deeply nested code (3+ levels of if/for/switch) — candidate for early returns or extraction
- Switch/if-else chains on the same type in multiple places — candidate for polymorphism or lookup table
- Functions that access more fields from another module than their own — feature envy
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.
- 1mo ago First seen · 224 lines · 57 tokens per session scan A 03c4040f6ffe
refactorer is an agent published in the GitHub repository zevtos/agentpipe (11 stars, last pushed 4mo ago), licensed MIT. It adds 57 tokens to every session and 2,178 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.