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.
npx agentmods add agents/rakovi4/continue-framework/refactor-agentgit clone --depth 1 https://github.com/rakovi4/continue-frameworkWhat 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 | $0.00021 | $0.01043 |
| Opus 5 | $0.00010 | $0.00522 |
| Sonnet 5 | $0.00004 | $0.00209 |
| Haiku 4.5 | $0.00002 | $0.00104 |
Grade A, and why
refactor-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 2d 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refactor Agent — Serial Fixer
One refactoring at a time. Run tests after each change. Re-scan cascades.
Purpose
The three read-only detectors scan in parallel and return candidate tables. They
are fanned out by /continue itself, in one message and awaited, and this agent
is handed the merged list — the scatter half lives on the orchestrator's surface
because a dispatched sub-agent must nest no fan-out of its own. Which detectors
those are, and the flag that awaits them, are named in /continue's Sub-Skill
Dispatch row for /refactor.
This agent applies the refactorings serially — because refactorings cascade (a class split changes sizes, a parameter removal frees locals), fixing MUST stay single-threaded with a re-scan after each change.
Workflow
- Read the merged, deduped candidate list you were handed. If it arrived
undeduped, keep one entry per
file:line. - Order the list highest-impact first: class/file splits (A0) before method extractions (A1) before local/expression cleanups — so cascades resolve downward and you don't refactor code you are about to delete.
- Apply ONE refactoring. Pick the top candidate, load its template from the
Code Smells Routing Table in
.claude/templates/refactoring/code-smells-routing-table.md, and follow the template steps. Apply the restraint guardrails in.claude/templates/refactoring/restraint.mdfirst — skip the candidate if a "NO ACTION" verdict is correct. - Verify size —
wc -lon every changed file (code, stylesheet, config). If any exceeds 200 lines the refactoring is incomplete — split further now. - Run tests for the module.
- Re-scan cascades — re-run only the checks that cascade from this change (param removal A55 → re-check locals A8 + repeated expressions A7; method extraction → re-check A1; class split → re-check A0). Add any new candidate to the list. This targeted re-scan is inline — do NOT re-dispatch the detectors.
- Repeat from step 2 until the list is empty AND the cascade re-scan is clean. Then run the full build to catch missed files.
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.
- 2d ago First seen · 88 lines · 21 tokens per session scan A edc71a67a6e1
refactor-agent is an agent published in the GitHub repository rakovi4/continue-framework (50 stars, last pushed 5d ago), licensed MIT. It adds 21 tokens to every session and 1,043 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.