refactoring-specialist

refactoring-specialist is an agent for coding agents from vinilana/dotcontext. It costs 11 tokens per session (1,431 once invoked), scanned A, original, MIT.

A code-review role focused on finding code smells, duplicated logic, tight dependencies, inconsistent architecture, and weak type safety in the dotcontext codebase.

In plain words
What is it for?
Use it to review command registration, shared services, generators, dependency injection, and other named areas of the codebase. It identifies refactoring opportunities rather than implementing them.
Why use it?
It helps reveal where the code is harder to maintain than necessary or where several parts solve the same problem differently.

Agent

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/vinilana/dotcontext/refactoring-specialist
Clone the repo
git clone --depth 1 https://github.com/vinilana/dotcontext

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 refactoring-specialist

README.md
[![agentmods](https://agentmods.dev/badge/agents/vinilana/dotcontext/refactoring-specialist.svg)](https://agentmods.dev/agents/vinilana/dotcontext/refactoring-specialist)
Your own site
<a href="https://agentmods.dev/agents/vinilana/dotcontext/refactoring-specialist"><img src="https://agentmods.dev/badge/agents/vinilana/dotcontext/refactoring-specialist.svg" alt="Measured on agentmods" height="20"></a>
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,431 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00011 $0.01431
Opus 5 $0.00005 $0.00715
Sonnet 5 $0.00002 $0.00286
Haiku 4.5 $0.00001 $0.00143

Measured 4d ago against content hash d46bb7e8c86c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

refactoring-specialist 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 4d 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.

.context/agents/refactoring-specialist.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Refactoring Specialist

Role

Identify code smells, architectural inconsistencies, and improvement opportunities in the dotcontext codebase. Refactoring targets include: reducing coupling between services, standardizing patterns across generators, consolidating duplicated logic into shared utilities, improving type safety, and simplifying the service dependency injection model.

Key Files to Understand

  • src/index.ts -- CLI entry point. Currently houses all command registration and service instantiation inline. A primary refactoring candidate for command registration extraction.
  • src/services/mcp/gateway/context.ts -- Consolidates multiple scaffold and semantic-context actions behind one gateway. It is a high-impact refactoring surface because multiple MCP flows converge here.
  • src/generators/agents/agentGenerator.ts -- Second most imported (13 dependents). Contains the AGENT_PHASES mapping, agent generation logic, and semantic context integration. Consider extracting the phase mapping to the workflow module.
  • src/services/shared/ -- Shared utilities directory with path helpers, glob patterns, content type registry, context root resolution, UI helpers, and tool registry. Some services duplicate logic that could be centralized here.
  • src/generators/shared/ -- Shared generator code including scaffoldStructures.ts, generatorUtils.ts, contextGenerator.ts, and the structures/ registry. The structures system is well-designed but some generators bypass it.
  • src/workflow/ -- PREVC workflow module with phases, roles, gates, orchestration, scaling, status management, and skills. Internal cohesion is good but the API surface to external consumers could be cleaner.
  • src/services/ai/providerFactory.ts -- AI provider abstraction. Four providers (openrouter, openai, anthropic, google) with similar setup patterns that could benefit from a strategy pattern.
  • src/utils/frontMatter.ts -- Handles both v1 and v2 frontmatter formats. The dual-format support adds complexity; consider a unified parser with format auto-detection.
  • src/types.ts -- Global types file. Some interfaces here are only used by specific services and could be co-located.
  • src/services/init/initService.ts, src/services/sync/syncService.ts, src/services/workflow/workflowService.ts -- Strong reference implementations for the current service pattern.

Read the full file on GitHub · 74 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. 4d ago First seen · 74 lines · 11 tokens per session scan A d46bb7e8c86c

Subscribe to this mod's changes

refactoring-specialist is an agent published in the GitHub repository vinilana/dotcontext (564 stars, last pushed 1mo ago), licensed MIT. It adds 11 tokens to every session and 1,431 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.