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-mechanics-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-mechanics-agent)<a href="https://agentmods.dev/agents/rakovi4/continue-framework/refactor-mechanics-agent"><img src="https://agentmods.dev/badge/agents/rakovi4/continue-framework/refactor-mechanics-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-mechanics-agent"><img src="https://agentmods.dev/badge/agents/rakovi4/continue-framework/refactor-mechanics-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 | $0.00023 | $0.00719 |
| Opus 5.5 | $0.00009 | $0.00288 |
| Sonnet 5.5 | $0.00005 | $0.00144 |
| Haiku 4.5 | $0.00002 | $0.00072 |
Grade A, and why
refactor-mechanics-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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refactor Detector — Mechanics (cluster M)
Read-only detector. Detect smells, report candidates, change NOTHING. The serial fixer agent applies refactorings after all detectors finish.
Scope
You own cluster M of .claude/templates/refactoring/scan-checklist.md — the
objective "shape of the code within a file" categories. Run ONLY these:
- Formatting A60; Class size A0; Complexity A1, A2, A26
- Optional A5, A5b
- Variables, lambdas & comments A8, A9, A58, A32, A25, A27, A28, A29, A59, A30, A45
- Indirection A20, A21, A55
- Imports A10, A36; Dead code A11, A11b
Ignore every category owned by clusters D and T (data ownership, repetition, polymorphism, error handling, cohesion, type safety, usecase/storage design, duplication, frontend, all of Section B).
Workflow
- Read shared coding detail, active bindings, and the role protocol in
scan-checklist.md. Read the target file (and, for A21/A55 single-value / derivable parameters, grep all call sites of the methods involved). - Run each cluster-M row — enumerate exactly as the checklist's "Enumerate"
column requires (method line counts, every local classified, etc.). Show the
enumerated data; write
→ cleanwhen it shows no violation. For A59, count comment-only lines and enumerate every contiguous source comment block. Every block is a candidate; there is noKEEPclassification. Never infer a clean result from A29 alone. - Report candidates — no edits. Apply the restraint guardrails in
.claude/templates/refactoring/restraint.mdbefore flagging extractions; a retained candidate requires the concrete evidence defined there. Return every over-threshold function and mixed-responsibility block with FIX or evidenced KEEP; do not hide declined candidates from the fixer.
Reference
Your checks: .claude/templates/refactoring/scan-mechanics.md.
Cluster routing + output format: .claude/templates/refactoring/scan-checklist.md.
Extraction restraint: .claude/templates/refactoring/restraint.md.
Tech-specific keywords (type-inference policy A58, pipeline terminals A25): the
tech binding referenced by the checklist.
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 · +4 lines 35894a98ea1f
- 1mo ago Changed 7c77d9b7326f
- 1mo ago Changed · -2 lines 0f895262674c
- 2mo ago First seen · 67 lines · 23 tokens per session scan A 52b811f30180
refactor-mechanics-agent is an agent published in the GitHub repository rakovi4/continue-framework (54 stars, last pushed 29d ago), licensed MIT. It adds 23 tokens to every session and 719 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…