refactor-strict

refactor-strict is a skill for Claude Code from cembasaranoglu/crafting-system-claude. It costs 26 tokens per session (277 once invoked), scanned A, original, MIT.

A source-based refactoring planner with an option to carry out one limited refactoring change when authorized.

In plain words
What is it for?
Use it to plan code restructuring and, when permitted, apply a bounded refactor.
Why use it?
It keeps refactoring grounded in the existing code and limits execution to a defined, approved slice.

Skill for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

Part of the crafting-system plugin — 81 skills, 32 agents shipped together

Good fit Use it to plan code restructuring and, when permitted, apply a bounded refactor.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/cembasaranoglu/crafting-system-claude/refactor-strict
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.

Any agent
npx skills add cembasaranoglu/crafting-system-claude --skill refactor-strict
Clone the repo
git clone --depth 1 https://github.com/cembasaranoglu/crafting-system-claude

Made for: Claude Code.

Or install crafting-system, the plugin that ships this one along with the rest of its 81 skills, 32 agents.

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-strict

README.md
[![agentmods](https://agentmods.dev/badge/skills/cembasaranoglu/crafting-system-claude/refactor-strict.svg)](https://agentmods.dev/skills/cembasaranoglu/crafting-system-claude/refactor-strict)
Your own site
<a href="https://agentmods.dev/skills/cembasaranoglu/crafting-system-claude/refactor-strict"><img src="https://agentmods.dev/badge/skills/cembasaranoglu/crafting-system-claude/refactor-strict.svg" alt="Measured on agentmods" height="20"></a>
Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 277 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00026 $0.00277
Opus 5 $0.00013 $0.00138
Sonnet 5 $0.00005 $0.00055
Haiku 4.5 $0.00003 $0.00028

Measured 4d ago against content hash 435975d82a90, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

refactor-strict 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 4d 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.

cowork/skills/refactor-strict/SKILL.md · 32 lines

What it actually says

refactor-strict

Use this skill when the user requests: Plan a strict refactor from source evidence, then optionally execute one bounded refactor slice only when authorized.

Source prompt references

Primary prompt-system reference: prompts/10_refactoring_strategy_and_plan.md and prompts/11_refactoring_execution_bounded.md.

Operating contract

  1. Inspect repository/source material before making claims.
  2. Separate facts, assumptions, recommendations, unknowns, blockers, failed validation, and not-run validation.
  3. Do not claim implementation, readiness, tests, builds, deployments, pushes, or packaging unless actually evidenced.
  4. If code or Git write actions are requested, apply the safe mutation gates from the base prompt.
  5. Produce durable artifacts when the user asks for files or reusable output.
  6. Use $ARGUMENTS as the user-supplied scope, branch, feature, component, or question when provided.

Task argument

$ARGUMENTS

Required behavior

Load the relevant prompt-system file from the repository or plugin package if available. If it is not available, follow the summarized contract above and produce the same named artifacts defined by the referenced prompt.

Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 4d ago First seen · 32 lines · 26 tokens per session scan A 435975d82a90

Subscribe to this mod's changes

refactor-strict is a skill published in the GitHub repository cembasaranoglu/crafting-system-claude (5 stars, last pushed 4mo ago), licensed MIT. It adds 26 tokens to every session and 277 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 2026-09-03.