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/sifxprime/kodelyth-ecc/refactor-sprintgit clone --depth 1 https://github.com/sifxprime/kodelyth-eccWrote 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/sifxprime/kodelyth-ecc/refactor-sprint)<a href="https://agentmods.dev/commands/sifxprime/kodelyth-ecc/refactor-sprint"><img src="https://agentmods.dev/badge/commands/sifxprime/kodelyth-ecc/refactor-sprint.svg" alt="Measured on agentmods" 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 | $0.00032 | $0.00668 |
| Opus 5 | $0.00016 | $0.00334 |
| Sonnet 5 | $0.00006 | $0.00134 |
| Haiku 4.5 | $0.00003 | $0.00067 |
Grade A, and why
refactor-sprint 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/refactor-sprint — Parallel Refactor Sprint
Four agents clean, simplify, type-harden, and test-cover your code simultaneously. What would take a full day of careful manual work is scoped and planned in 15 minutes.
What Gets Launched in Parallel
| Agent | Focus |
|---|---|
refactor-cleaner |
Dead code, unused imports, duplicate logic, copy-paste debt, tech debt |
code-simplifier |
Complex functions, deep nesting, clever one-liners, readability improvements |
type-design-analyzer |
any types, weak discriminated unions, missing type guards, type safety gaps |
tdd-guide |
Test coverage gaps, missing unit tests, untested edge cases, coverage below 80% |
Usage
/refactor-sprint # full repo
/refactor-sprint src/auth/ # focus on a module
/refactor-sprint --types-only # skip cleanup, focus on type safety
/refactor-sprint --tests-only # skip cleanup, focus on test coverage
Report Format
## REFACTOR SPRINT REPORT
### Dead Code & Debt (refactor-cleaner)
REMOVE: [files, functions, imports to delete]
EXTRACT: [duplicated logic to consolidate]
DEBT: [tech debt items ranked by impact]
### Simplification (code-simplifier)
COMPLEX: [functions that need splitting]
NESTING: [deep nesting to flatten with early returns]
READABILITY: [naming and clarity improvements]
### Type Safety (type-design-analyzer)
ANY_USAGE: [locations using any/unknown unsafely]
WEAK_TYPES:[discriminated unions to strengthen]
GUARDS: [missing type guards]
### Test Coverage (tdd-guide)
UNCOVERED: [critical paths with no tests]
GAPS: [edge cases missing]
PLAN: [test writing priority order]
---
TOTAL DEBT: X items | QUICK WINS: Y items
RECOMMENDED ORDER: [prioritized action list]
When to Use
- Before a major feature addition (clean house first)
- After a fast-moving sprint that accumulated debt
- Monthly code health pass
- Before onboarding a new team member
- When coverage has dropped below 80%
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 · 78 lines · 32 tokens per session scan A 38661c34a39b
refactor-sprint is a command published in the GitHub repository sifxprime/kodelyth-ecc (11 stars, last pushed 2d ago), licensed MIT. It adds 32 tokens to every session and 668 once invoked, about $0.0002 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 2026-09-03.
Other commands, from other repositories
rust-test
Rust TDD workflow with unit and property tests.
test
Design or run focused test validation for a task, bug, or diff.
autonomous-tdd
SAM Autonomous TDD Pipeline - Transforms PRD into working, tested code using RED-GREEN-REFACTOR methodology.
test-zh
中文生成测试.
testing
Testing hub - run tests, coverage analysis, TDD, benchmarks.
tdd
Enforce test-driven development workflow. Scaffold interfaces, generate tests FIRST, then implement minimal code to pass. Ensure 80%+ coverage.