minimal-diff

minimal-diff is a skill for Claude Code, Codex from Oriolshhh/runware-image-mcp. It costs 14 tokens per session (331 once invoked), scanned A, original, MIT.

A development practice for making only the small, necessary changes required by a specification.

In plain words
What is it for?
It is for implementing focused fixes and features while preserving existing interfaces, behavior, conventions, and formatting outside the requested scope.
Why use it?
It keeps code reviews manageable, lowers regression risk, and avoids unrelated refactors or speculative abstractions.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

Good fit It is for implementing focused fixes and features while preserving existing interfaces, behavior, conventions, and formatting outside the requested scope.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/oriolshhh/runware-image-mcp/minimal-diff
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 Oriolshhh/runware-image-mcp --skill minimal-diff
Clone the repo
git clone --depth 1 https://github.com/Oriolshhh/runware-image-mcp

Made for: Claude Code, Codex.

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 minimal-diff

README.md
[![agentmods](https://agentmods.dev/badge/skills/oriolshhh/runware-image-mcp/minimal-diff/github.svg)](https://agentmods.dev/skills/oriolshhh/runware-image-mcp/minimal-diff)
Your own site
<a href="https://agentmods.dev/skills/oriolshhh/runware-image-mcp/minimal-diff"><img src="https://agentmods.dev/badge/skills/oriolshhh/runware-image-mcp/minimal-diff/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for minimal-diff

Your own site · 80×15
<a href="https://agentmods.dev/skills/oriolshhh/runware-image-mcp/minimal-diff"><img src="https://agentmods.dev/badge/skills/oriolshhh/runware-image-mcp/minimal-diff.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 14 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 331 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 $0.00014 $0.00331
Opus 5 $0.00007 $0.00166
Sonnet 5 $0.00003 $0.00066
Haiku 4.5 $0.00001 $0.00033

Measured 8d ago against content hash 5c3a2762f5dc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

minimal-diff 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 8d 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.

.agents/skills/minimal-diff/SKILL.md · 40 lines

What it actually says

Minimal Diff

Purpose

Deliver the required change with the smallest, most reviewable diff that fully satisfies the spec.

When to use it

  • Always, unless the spec explicitly calls for a large refactor.
  • Especially in shared, high-traffic, or legacy code.

Instructions

  1. Change only what the task requires.
  2. Reuse existing helpers and patterns before adding new ones.
  3. Preserve public APIs and behavior unless the spec requires otherwise.
  4. Keep unrelated refactors, renames, and formatting out of the diff.
  5. If a refactor is genuinely needed, propose it separately.

Output format

A focused diff plus a one-line rationale for any surprising change.

Anti-patterns

  • Drive-by refactors mixed into a feature change.
  • Reformatting files unrelated to the task.
  • Speculative abstractions for hypothetical future needs.

Verification checklist

  • Every changed line is required by the request, a necessary test, or generated output from an explicitly requested operation.
  • Public interfaces and unrelated formatting remain stable.
  • Any unavoidable broader change is isolated and explained before proceeding.

Apply context-discovery before broad scanning: use a supplied context capsule first; otherwise check context frontmatter freshness, read .agent/context/routing.md, load only relevant summaries, and verify critical claims against source.

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. 8d ago First seen · 40 lines · 14 tokens per session scan A 5c3a2762f5dc

Subscribe to this mod's changes

minimal-diff is a skill published in the GitHub repository Oriolshhh/runware-image-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 14 tokens to every session and 331 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.