explain-diff

A command that turns a code change, called a diff, into a self-contained HTML teaching page. It explains what changed and the surrounding code so the reader can understand it.

In plain words
What is it for?
Use it to explain staged changes, commits, branches, file changes, or pull requests in a guided walkthrough rather than as a code review.
Why use it?
A raw diff shows changed lines but often leaves out the system background and the reason for the change.

Command

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/theclaymethod/artifacture/explain-diff
Clone the repo
git clone --depth 1 https://github.com/theclaymethod/artifacture
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 554 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 $0.00015 $0.00554
Opus 5 $0.00008 $0.00277
Sonnet 5 $0.00003 $0.00111
Haiku 4.5 $0.00002 $0.00055

Measured yesterday against content hash 22b287c822c6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

explain-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.

plugins/visual-explainer/commands/explain-diff.md · 40 lines

What it actually says

Load the visual-explainer skill, then generate an explain-diff page as a self-contained HTML artifact.

Credit: this mode adapts Geoffrey Litt's "explain-diff" gist: https://gist.github.com/geoffreylitt/a29df1b5f9865506e8952488eac3d524

Which diff command to use. Use /explain-diff when the reader needs a teaching walkthrough; use /diff-review when the reader needs reviewer-risk findings.

Arguments. $1 may be a diff range, PR number, branch, commit, or file path. If omitted, use staged changes when present; otherwise default to HEAD~1..HEAD.

Scope detection.

  • PR number (#42): gh pr diff 42
  • Range (abc..def): git diff abc..def
  • Branch: git diff <branch>...HEAD
  • Commit: git show <commit>
  • No argument: git diff --staged; if empty, git diff HEAD~1..HEAD

Data gathering.

  1. Read the diff and git diff --stat/--name-status for scope.
  2. Read surrounding code before and after each meaningful hunk. Do not explain a line without knowing the function/module contract around it.
  3. Identify the audience-facing background: what system this code belongs to, what invariant existed before, and what behavior the diff changes.
  4. Build a fact sheet with cited file paths, function names, and claims before authoring.

Authoring contract. Read cards/explain-diff.md. Write MDX, no top-level tabs. Use a long-page format with a table of contents and four sections: Background, Intuition, Code, Quiz. Use DiffBlock, CodeBlock, and Quiz; use DiagramCanvas/MermaidBlock for 1-2 reusable diagram families and reuse them across sections with example data.

Prose bar: clarity and flow of Martin Kleppmann, classic style, smooth transitions. Then run the standard unslop step from SKILL.md before export.

Output path:

mkdir -p ~/.agent/diagrams
npm run ve:export -- <source.mdx> --out ~/.agent/diagrams/$(date +%F)-explain-<slug>.html

Then run §6 Verify from SKILL.md on the exported HTML and report the artifact path, report JSON, screenshots directory, and any remaining uncertainty.

$@

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 · 40 lines · 15 tokens per session scan A 22b287c822c6

Subscribe to this mod's changes

explain-diff is a command published in the GitHub repository theclaymethod/artifacture (2 stars, last pushed 9d ago), licensed MIT. It adds 15 tokens to every session and 554 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 2026-08-31.