refactor-sprint

refactor-sprint is a command for coding agents from sifxprime/kodelyth-ecc. It costs 32 tokens per session (668 once invoked), scanned A, original, MIT.

A command that runs several code-cleanup and testing reviews at the same time. It looks for dead code, hard-to-read code, weak types, and missing tests.

In plain words
What is it for?
Use it for a whole repository or one module, or limit the work to type safety or test coverage.
Why use it?
It brings several maintenance checks together instead of requiring separate review passes.

Command

Install

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.

agentmods
npx agentmods add commands/sifxprime/kodelyth-ecc/refactor-sprint
Clone the repo
git clone --depth 1 https://github.com/sifxprime/kodelyth-ecc

Wrote 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.

agentmods badge for refactor-sprint

README.md
[![agentmods](https://agentmods.dev/badge/commands/sifxprime/kodelyth-ecc/refactor-sprint.svg)](https://agentmods.dev/commands/sifxprime/kodelyth-ecc/refactor-sprint)
Your own site
<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>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 668 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured yesterday against content hash 38661c34a39b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

commands/refactor-sprint.md · 78 lines

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%

Read the full file on GitHub · 78 lines

Changes

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.

  1. yesterday First seen · 78 lines · 32 tokens per session scan A 38661c34a39b

Subscribe to this mod's changes

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.