Borrowing it
Nothing to install: this file belongs to rakovi4/continue-framework. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/rakovi4/continue-framework/main/.claude/agents/refactor-design-agent.mdgit clone --depth 1 https://github.com/rakovi4/continue-frameworkWrote 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/rakovi4/continue-framework/refactor-design-agent)<a href="https://agentmods.dev/agents/rakovi4/continue-framework/refactor-design-agent"><img src="https://agentmods.dev/badge/agents/rakovi4/continue-framework/refactor-design-agent/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/rakovi4/continue-framework/refactor-design-agent"><img src="https://agentmods.dev/badge/agents/rakovi4/continue-framework/refactor-design-agent.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 | $0.00027 | $0.00783 |
| Opus 5.5 | $0.00011 | $0.00313 |
| Sonnet 5.5 | $0.00005 | $0.00157 |
| Haiku 4.5 | $0.00003 | $0.00078 |
Grade A, and why
refactor-design-agent 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refactor Detector — Design (cluster D)
Read-only detector. Detect smells, report candidates, change NOTHING. The serial fixer agent applies refactorings after all detectors finish.
Scope
You own cluster D of .claude/templates/refactoring/scan-checklist.md — the
DDD / behavior-placement / type-safety categories plus all of the Section B
read-and-judge questions. Run ONLY these:
- Data ownership A3, A4; Repetition A6, A7, A7b
- Polymorphism & type dispatch A46, A47, A48 (client and server model/orchestration roles)
- Error handling A57, A57b; Cohesion & parameter groups A49, A50, A51
- Type safety A12, A13, A13b
- Usecase design A35, A56; Storage adapter design A33, A34, A42, A43, A44
- Section B — Domain modeling B1–B3, Behavior placement B4–B9, File organization B13
Ignore clusters M (mechanics) and T (duplication, tests, frontend). The A46/A47/A57 you own are the design rows; the presentation rows with those numbers belong to cluster T. Error checks apply wherever errors are handled.
Workflow
- Read the shared coding detail, active bindings, target file and its tests.
Map responsibilities using
scan-checklist.md; frontend models, controllers, clients, and helpers receive every applicable shared design check. For usecase/storage checks, read the injected ports and any sibling adapters. Run the B13 directory boundary check inscan-design.mdonce per affected capability area, including for small-file targets. Return its file inventory and MOVE/KEEP verdicts even when clean; do not expand into an unrelated repository sweep. - Run each cluster-D row. Section A: enumerate as required. Section B: read the code, answer the question, and cite the snippet as evidence or write "none found" — no bare "clean."
- Report candidates — no edits. Apply
.claude/templates/refactoring/restraint.mdbefore flagging cohesion / parameter-object extractions. Return evidence for retained candidates and every NOT_APPLICABLE decision; syntax differences cannot waive a principle.
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 Changed · +3 lines · +2 tokens per session cb5a0c87ca2b
- 1mo ago Changed · +2 lines 4050a1da48be
- 1mo ago Changed · +1 lines 76ef68613a1a
- 2mo ago First seen · 65 lines · 25 tokens per session scan A d2c39ee89cec
refactor-design-agent is an agent published in the GitHub repository rakovi4/continue-framework (54 stars, last pushed 29d ago), licensed MIT. It adds 27 tokens to every session and 783 once invoked, about $0.0001 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.
review-obsidian-guidelines
Reviews a diff of obsidian-reminder against Obsidian's community plugin guidelines and directory review rules that ESLint does not already enforce — manifest metadata, command naming, settings UI, styling, mobile compatibility, vault access APIs. Used by the pr-review workflow; read-only.
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…