validating-diff

A review step for checking completed code changes against the project's recorded rules. It is intended for logical checkpoints, such as finishing a feature or a test-driven development (TDD) cycle, where a failing test guides a change until it passes.

In plain words
What is it for?
Use it after completing a feature slice, finishing a TDD cycle, or preparing a batch of changes for commit. It helps surface rule violations and presents ways to resolve them.
Why use it?
Rules can be missed when several related files are changed together, while checking after every edit creates unnecessary noise. This provides a checkpoint before declaring work complete or committing it.

Skill for Claude CodeCodex

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/hitmandark07/neatcodeai/validating-diff
Any agent
npx skills add HITMANdark07/neatcodeai --skill validating-diff
Clone the repo
git clone --depth 1 https://github.com/HITMANdark07/neatcodeai

Made for: Claude Code, Codex.

Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,834 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 $0.00055 $0.01834
Opus 5 $0.00028 $0.00917
Sonnet 5 $0.00011 $0.00367
Haiku 4.5 $0.00006 $0.00183

Measured yesterday against content hash ab791b264e47, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

validating-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 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.

packages/cli/templates/skills/validating-diff/SKILL.md · 157 lines

How it starts

The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Validating Diffs

Overview

The captured ruleset is enforced at meaningful checkpoints, not after every keystroke. This skill is the gate at those checkpoints.

This skill calls the validate_diff MCP tool.

When to call — the right cadence

The right call frequency is 3–8 times per phase, not 1 (too coarse) and not 12+ (too noisy). The pattern is "once per testable behavior" — every time a logical unit reaches a state worth gating on.

Call when:

  • A logical unit is complete: a service + its controller + its spec, written and assembled into something that could be tested.
  • A TDD cycle finished — failing test → passing implementation → cleanup. After cleanup is the natural validation point.
  • About to commit a batch of changes.
  • About to tell the user "the change is in" / "ready" / "done".
  • About to hand off to the verifying skill (which runs validate_diff again as the final gate).

Do NOT call when:

  • Writing a test fixture, snapshot, or pure data file. Nothing the engine can flag.
  • Mid-TDD red phase, where the implementation file is empty or stub. Nothing decorated yet.
  • Mid-refactor with files in inconsistent intermediate states. The transient state will produce false positives that disappear once the refactor lands.
  • Writing a single line of formatting / imports / comments. Trivial edits don't shift any rule outcome.

Why not "every file write":

Three concrete costs. (1) During partial multi-file changes, a controller method calling a not-yet-written service method would spuriously trigger edge-forbidden flags that resolve once the second file lands — training the agent to ignore violations in general. (2) TDD-red phases have nothing to validate; calling anyway is theater. (3) Stop-start fragmenting natural reasoning seams reduces flow without catching anything you wouldn't catch at the next checkpoint.

The earlier you call within the right cadence, the cheaper the iteration. But "earlier" means "at the next logical-unit boundary", not "between every two characters typed."

Read the full file on GitHub · 157 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 · 157 lines · 55 tokens per session scan A ab791b264e47

Subscribe to this mod's changes

validating-diff is a skill published in the GitHub repository HITMANdark07/neatcodeai (0 stars, last pushed 3mo ago), licensed MIT. It adds 55 tokens to every session and 1,834 once invoked, about $0.0003 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens