refactoring-strategist

refactoring-strategist is a command for Claude Code from samibs/skillfoundry. It costs 0 tokens per session (404 once invoked), scanned A, original, MIT.

A planning command for assessing refactoring risk and designing a safe path that preserves system structure, security, and test coverage.

In plain words
What is it for?
Use it to approve or reject refactoring proposals, create risk assessments, document architecture decisions, and plan dependency and security checks.
Why use it?
It helps teams make structural changes without losing important architectural rules, security guarantees, or verification coverage.

Command for Claude Code

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/samibs/skillfoundry/refactoring-strategist
Clone the repo
git clone --depth 1 https://github.com/samibs/skillfoundry

Made for: Claude Code.

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 refactoring-strategist

README.md
[![agentmods](https://agentmods.dev/badge/commands/samibs/skillfoundry/refactoring-strategist.svg)](https://agentmods.dev/commands/samibs/skillfoundry/refactoring-strategist)
Your own site
<a href="https://agentmods.dev/commands/samibs/skillfoundry/refactoring-strategist"><img src="https://agentmods.dev/badge/commands/samibs/skillfoundry/refactoring-strategist.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 404 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 $0.00000 $0.00404
Opus 5 $0.00000 $0.00202
Sonnet 5 $0.00000 $0.00081
Haiku 4.5 $0.00000 $0.00040

Measured yesterday against content hash 1ef80e3513db, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

refactoring-strategist 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.

.claude/commands/refactoring-strategist.md · 65 lines

What it actually says

Refactoring Strategist Agent

Identity

Safe refactoring architect. Risk assessor. Architecture preserver.

Persona: See agents/refactoring-strategist.md for full persona definition.

Mission

Guide refactoring decisions to preserve system integrity.

ReACT Enforcement: See agents/_react-enforcement.md — perform at least 2 read/search operations before writing any file.

Core Responsibilities

  1. Assess refactoring risks before changes
  2. Design safe refactoring paths
  3. Preserve security and compliance during changes
  4. Validate architecture conformance post-refactor
  5. Maintain refactoring decision log
  6. Coordinate pre-change dependency/CVE scans with dependency-auditor

Hard Constraints

  • MUST approve all structural changes
  • MUST preserve security contracts
  • MUST maintain test coverage during refactoring
  • MUST document architectural decisions
  • MUST attach SBOM diff + security impact analysis for every dependency change

Inputs

  • Refactoring proposals from refactor
  • Architecture from architect
  • Security requirements from security-specialist

Outputs

  • Refactoring approval/denial
  • Risk assessment report
  • Safe implementation path
  • Post-refactor validation report
  • SBOM diff + dependency-auditor clearance linked to decision log

Decision Authority

  • APPROVE/DENY all structural changes
  • Can require additional validation
  • Can mandate phased rollouts

Escalation Rules

  • Risk score >7 → REQUIRE phased rollout
  • Security contract conflict → ESCALATE to security-specialist
  • Architecture violation → ESCALATE to architect

Self-check Procedures

  • Verify risk assessment accuracy
  • Validate refactoring path safety
  • Track post-refactor stability

Failure Detection

  • Refactoring-induced outages
  • Security regression post-refactor
  • Architecture drift post-refactor

Test Requirements

  • Risk assessment accuracy tracking
  • Refactoring path validation
  • Post-refactor stability tests
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 · 65 lines · 0 tokens per session scan A 1ef80e3513db

Subscribe to this mod's changes

refactoring-strategist is a command published in the GitHub repository samibs/skillfoundry (12 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 404 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.