change-framework

change-framework is a skill for Claude Code from BenchBox-dev/BenchBox. It costs 34 tokens per session (1,669 once invoked), scanned A, original, MIT.

A workflow for selecting the right source-code change, splitting larger work into small verified slices, and managing branches, commits, and authorised pull requests.

In plain words
What is it for?
Use it for features, refactors, and multi-file fixes that need research, incremental implementation, testing, separate commits, and post-edit checks.
Why use it?
It limits unnecessary edits and keeps each part of a change buildable, tested, and traceable.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions subagents; mentions Codex.

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 skills/benchbox-dev/benchbox/shared-change-framework
Any agent
npx skills add BenchBox-dev/BenchBox --skill shared-change-framework
Clone the repo
git clone --depth 1 https://github.com/BenchBox-dev/BenchBox

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 change-framework

README.md
[![agentmods](https://agentmods.dev/badge/skills/benchbox-dev/benchbox/shared-change-framework.svg)](https://agentmods.dev/skills/benchbox-dev/benchbox/shared-change-framework)
Your own site
<a href="https://agentmods.dev/skills/benchbox-dev/benchbox/shared-change-framework"><img src="https://agentmods.dev/badge/skills/benchbox-dev/benchbox/shared-change-framework.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,669 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 5.1 $0.00034 $0.01669
Opus 5 $0.00017 $0.00834
Sonnet 5 $0.00007 $0.00334
Haiku 4.5 $0.00003 $0.00167

Measured yesterday against content hash 952459319240, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

change-framework 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/skills/shared-change-framework/SKILL.md · 161 lines

How it starts

The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Change Framework

1. Source-code selection

After required research and before editing source code, choose the first option that fully satisfies the authorized requirement, repository policy, and safety constraints:

  1. No change, if the required outcome already exists.
  2. An existing helper or established pattern.
  3. A standard-library or native platform feature.
  4. A declared, direct dependency supported by the project.
  5. The smallest clear new implementation.

Do not trade correctness, compatibility, validation, security, accessibility, or explicit requirements for an earlier option. When a simplification has a material or non-obvious limit, document the limit and its replacement trigger.

2. Slicing discipline

Use for multi-file work, features, refactors, or changes likely to exceed about 100 lines before testing.

  • Touch only task-required code. Report adjacent issues as "noticed but not touching."
  • Prefer vertical slices. Use contract-first slices for parallel components and risk-first slices for uncertainty.
  • Each slice must implement, test, and verify one logical behavior. Commit each verified slice separately.
  • Keep the project buildable and each increment independently revertible.
  • New incomplete code stays disabled by default.

3. Post-edit verification ladder

Run before returning, staging, or committing changes.

Checks

  1. Read edited regions with five surrounding lines. Check indentation, nesting, stale imports, and orphaned lines.
  2. Run project lint if available.
  3. Run project typecheck if available.
  4. Run targeted tests, then fast/default suite for meaningful code changes.

Rules

  • Report why any verification step is unavailable.
  • Fix failures before committing or report the blocker.
  • Report command, result, and residual risk.
  • Run the narrowest proving check first. Use fast, full, or preflight checks as final gates. Save long output to a log and report the summary.

Delegated gate runs

A low-effort subagent may run deterministic gates, including full tests, preflight, CI status, push, PR opening or follow-up, and other long run-and-report commands.

Read the full file on GitHub · 161 lines

Files

What ships with it

1 file 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. yesterday First seen · 161 lines · 34 tokens per session scan A 952459319240

Subscribe to this mod's changes

change-framework is a skill published in the GitHub repository BenchBox-dev/BenchBox (12 stars, last pushed today), licensed MIT. It adds 34 tokens to every session and 1,669 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 2026-09-04.