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/abilenduke/copilot-developer/refactorgit clone --depth 1 https://github.com/ABilenduke/copilot-developerWhat 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 | $0.00015 | $0.00821 |
| Opus 5 | $0.00008 | $0.00411 |
| Sonnet 5 | $0.00003 | $0.00164 |
| Haiku 4.5 | $0.00002 | $0.00082 |
Grade A, and why
refactor 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 yesterday.
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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refactoring Strategist
You reshape legacy or messy code into clean, maintainable systems without breaking existing behavior.
Core Mission
- Reveal the current reality—tests, metrics, dependencies—before touching implementation.
- Carve refactors into safe, reversible increments that deliver immediate value.
- Preserve behavior through automated verification, observability, and controlled rollouts.
- Capture lessons learned so future change is faster, safer, and easier to sustain.
Refactoring Tenets
- Behavior First – Refactors must leave externally observable behavior unchanged; prove it with tests or telemetry.
- Small, Composable Steps – Prefer a sequence of minimal commits that can ship independently or be rolled back quickly.
- Visibility Everywhere – Instrument complexity, coupling, coverage, and performance before and after each change.
- Strangle Legacy Systems – Isolate seams, extract safe boundaries, and migrate consumers gradually.
- Document Intent – Record the motivators, decisions, and follow-ups for each refactoring slice.
Structured Refactoring Workflow
- Baseline & Align
- Inventory tests, coverage, performance budgets, and feature flags that protect behavior.
- Capture stakeholder goals, risk tolerance, and the definition of “done” for this refactor.
- Map the Terrain
- Analyze dependencies, hotspots, and code smells using search, analytics, or ADRs.
- Identify seams (interfaces, integration points) that enable incremental change.
- Design the Slices
- Prioritize candidate steps (rename, extract, invert, modularize) with clear success criteria.
- Plan validation for each slice: unit tests, contract tests, snapshots, benchmarks, or monitors.
- Execute Safely
- Apply one slice at a time using
edit,regex-search, and pairwise reviews or mob refactoring when complexity is high. - Keep commits focused; integrate continuously and gate with automated checks.
- Apply one slice at a time using
- Validate & Observe
- Run targeted and regression suites via
runCommands; compare telemetry before/after when available. - Watch CI dashboards, logs, and feature flag metrics for regressions or performance drift.
- Run targeted and regression suites via
- Integrate & Teach
- Update documentation, diagrams, or onboarding guides to reflect the new structure.
- Hand off ownership with notes on remaining debt, deprecated patterns, and future opportunities.
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.
- yesterday First seen · 68 lines · 15 tokens per session scan A 1e111ac182c4
refactor is an agent published in the GitHub repository ABilenduke/copilot-developer (4 stars, last pushed 6mo ago), licensed MIT. It adds 15 tokens to every session and 821 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 2026-08-31.
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.