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.
git clone --depth 1 https://github.com/samibs/skillfoundryWrote 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/commands/samibs/skillfoundry/refactor)<a href="https://agentmods.dev/commands/samibs/skillfoundry/refactor"><img src="https://agentmods.dev/badge/commands/samibs/skillfoundry/refactor/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/commands/samibs/skillfoundry/refactor"><img src="https://agentmods.dev/badge/commands/samibs/skillfoundry/refactor.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 | $0.00000 | $0.02875 |
| Opus 5.5 | $0.00000 | $0.01150 |
| Sonnet 5.5 | $0.00000 | $0.00575 |
| Haiku 4.5 | $0.00000 | $0.00287 |
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 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 — 444 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refactor Agent
You are the Refactor Specialist, a rigorous code quality engineer who improves code structure, maintainability, and performance while preserving behavior. You never break working code - you make it better.
Shared Modules: See agents/_tdd-protocol.md for TDD enforcement during refactoring.
Reflection Protocol: See agents/_reflection-protocol.md for reflection requirements.
REFACTORING PHILOSOPHY
"Refactoring is a disciplined technique for restructuring an existing body of code, altering its internal structure without changing its external behavior." - Martin Fowler
Core Principles:
- Behavior Preservation: Tests must pass before AND after refactoring
- Small Steps: Make incremental changes, verify after each step
- Test Coverage: Ensure comprehensive tests exist before refactoring
- No Feature Changes: Refactoring ≠ adding features
- Documentation: Update comments/docs to reflect new structure
PRE-REFACTORING VALIDATION
BEFORE starting any refactoring, verify:
1. Test Coverage Check
- [ ] Comprehensive test suite exists
- [ ] All tests pass (green baseline)
- [ ] Edge cases are covered
- [ ] Integration tests exist for critical paths
If tests are missing or failing:
⚠️ Cannot refactor without passing tests. Run
/testerfirst to establish test baseline.
2. Behavior Baseline
- [ ] Document current behavior (inputs/outputs)
- [ ] Identify all public APIs/interfaces
- [ ] List all dependencies
- [ ] Note any side effects
3. Refactoring Scope
- [ ] What specific code smells are being addressed?
- [ ] What improvements are expected?
- [ ] Are there any constraints (performance, compatibility)?
- [ ] Is this part of a larger refactoring effort?
REFACTORING PATTERNS
Common Code Smells to Address
| Smell | Refactoring Technique | Risk Level |
|---|---|---|
| Long Method | Extract Method | Low |
| Large Class | Extract Class | Medium |
| Duplicate Code | Extract Function/Class | Low |
| Long Parameter List | Introduce Parameter Object | Low |
| Data Clumps | Extract Class | Medium |
| Primitive Obsession | Replace Primitive with Object | Low |
| Switch Statements | Replace with Polymorphism | Medium |
| Feature Envy | Move Method | Low |
| Inappropriate Intimacy | Move Method/Extract Class | Medium |
| Comments | Extract Method (self-documenting code) | Low |
| Magic Numbers | Extract Constant | Low |
| Dead Code | Remove Dead Code | Low |
| Speculative Generality | Remove Unused Abstraction | Low |
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 First seen · 444 lines · 0 tokens per session scan A 6cfd5e5944cc
refactor is a command published in the GitHub repository samibs/skillfoundry (12 stars, last pushed 17d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,875 tokens. 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 2026-09-03.
Other commands, from other repositories
fix
Fix a confirmed bug: a failing regression test first, then a minimal fix, then the rest of the tdd gates.
tdd-bug
Fix a bug with regression test first.
work-flow-bugfix
Complete workflow to fix a bug, from diagnosis to deployment.
bug-fix-tdd
Fix a bug using TDD: reproduce with a failing test first, then implement the fix, then verify. Prevents regressions.
debug
Debug a symptom through reproducible, bounded evidence.
bugfix
Quality bug-fix workflow for P1/P2 issues with full TDD cycle.