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 commands/mktoronto/python-clean-architecture/refactor-legacygit clone --depth 1 https://github.com/MKToronto/python-clean-architectureWhat 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 | $0.00016 | $0.00506 |
| Opus 5 | $0.00008 | $0.00253 |
| Sonnet 5 | $0.00003 | $0.00101 |
| Haiku 4.5 | $0.00002 | $0.00051 |
Grade A, and why
refactor-legacy 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.
What it actually says
Analyze the code at $ARGUMENTS (or the current working directory if no path given) and produce a step-by-step refactoring plan with testability as the first goal.
Process
-
Read the code — Find and read ALL Python files in the target path recursively.
-
Identify testability blockers — Look for:
- Global state and module-level side effects
- Hardcoded dependencies (
self.x = ConcreteClass()) - Mixed I/O and business logic (print/input in logic classes)
- Missing abstractions (no Protocol interfaces)
- Complex
__init__methods with setup logic - Functions with inconsistent return types
-
Identify code smells — Scan for recurring refactoring opportunities:
- Deep nesting (→ guard clauses)
- Magic numbers (→ named constants)
- String comparisons (→ Enums)
- Scattered if/elif chains (→ data-driven rules)
- Raw data structures (→ domain classes)
- Catch-all exception handling (→ specific catches)
-
Produce a phased plan:
Phase 1: Add characterization tests
- Capture current behavior with pinning tests
- Don't fix anything yet — just lock down what exists
Phase 2: Extract pure logic from side effects
- Separate UI/IO from business logic
- Move print/input into dedicated classes
- Extract named helper functions from complex conditions
Phase 3: Introduce Protocol interfaces
- Define Protocol for external dependencies
- Apply dependency injection at the composition root
- Create stubs for testing
Phase 4: Add proper unit tests
- Test extracted pure logic with stubs
- Verify business rules independently of I/O
-
For each phase, show specific before/after code snippets from the actual codebase.
References:
${CLAUDE_PLUGIN_ROOT}/skills/clean-architecture/references/refactoring-case-studies.md${CLAUDE_PLUGIN_ROOT}/skills/clean-architecture/references/testing-legacy-code.md${CLAUDE_PLUGIN_ROOT}/skills/clean-architecture/references/code-smells.md${CLAUDE_PLUGIN_ROOT}/skills/clean-architecture/references/dependency-injection.md
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 · 56 lines · 16 tokens per session scan A 399c97a369a4
refactor-legacy is a command published in the GitHub repository MKToronto/python-clean-architecture (8 stars, last pushed 2mo ago), licensed MIT. It adds 16 tokens to every session and 506 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 commands, from other repositories
go-stack.bundb.setup
Instructions to setup the go-stack BunDB integration for database access, migration management, and the bundled DB CLI command.
go-stack.project-update
Compare the current project against the latest go-stack scaffold template and propose or apply updates (tasks, linters, dependencies, skills, provider patterns, security tooling) while preserving project-specific business logic and module identity.
go-stack.inertia.setup
Instructions to setup the go-stack Inertia.js integration for fullstack Go applications, including boot provider wiring and frontend workflow.
design-to-code
Mockup-to-component pipeline using Google Stitch, 21st.dev, and Storybook MCP. Accepts a screenshot, a description, or a URL and produces production-ready React components, checking existing Storybook components before generating anything new. Use when implementing UI from a mockup or screenshot. To call the MCP tool…
deploy
Build, test, deploy with staged rollout.
test
QA verification with real dependencies — the quality gate before review.