diff-explain

A command that explains Git changes in ordinary language, including uncommitted work, branch differences, commit ranges, or merge and pull requests.

In plain words
What is it for?
Use it to catch up on a branch, prepare for a merge-request review, understand recent commits, or inspect work that has not been committed.
Why use it?
It makes code changes easier to understand by explaining their likely purpose and effect instead of only listing changed files.

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/benkapner/claude-code-basecamp/diff-explain
Clone the repo
git clone --depth 1 https://github.com/Benkapner/claude-code-basecamp

Made for: Claude Code.

Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 846 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 $0.00033 $0.00846
Opus 5 $0.00016 $0.00423
Sonnet 5 $0.00007 $0.00169
Haiku 4.5 $0.00003 $0.00085

Measured yesterday against content hash a5a844c3a72a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

diff-explain 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/diff-explain.md · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Diff Explain Command

Explain code changes in plain language — what was done and why.

Instructions

Step 1: Get the Diff

Determine what to explain based on arguments:

  • No arguments: explain uncommitted changes (git diff + git diff --staged)
  • Branch name: explain difference from that branch (git diff main...HEAD)
  • Commit range: explain those commits (git log --oneline <range>)
  • MR/PR number: fetch and explain that MR
# Default: uncommitted changes
git diff --stat
git diff

# Or: branch comparison
git log --oneline main..HEAD
git diff main...HEAD --stat

Step 2: Analyze and Explain

For each logical group of changes, explain:

  1. What changed — in plain language, not file names
  2. Why — the intent behind the change (infer from commit messages, code context, and patterns)
  3. Impact — what this means for the project (new capability, bug fix, refactor, etc.)

Step 3: Format the Explanation

CHANGES EXPLAINED
=================

SUMMARY:
  [1-2 sentences capturing the overall intent of all changes]

CHANGE 1: [descriptive title]
  What: [plain language description]
  Why:  [inferred intent]
  Files: [list of affected files]

CHANGE 2: [descriptive title]
  What: [plain language description]
  Why:  [inferred intent]
  Files: [list of affected files]

...

OVERALL IMPACT:
  - [What's new or different for users of this code]
  - [Any breaking changes or things to be aware of]
  - [What to test]

Examples

Input: /diff-explain Output:

CHANGES EXPLAINED
=================

SUMMARY:
  The monolithic epic analysis script was split into 3 independent
  pipeline steps, and closed issues are now kept for context
  instead of being discarded.

CHANGE 1: Split summarize_epics.py into 3 scripts
  What: The script that grouped issues, analyzed epics, and filtered
        tasks was split into group_issues.py (grouping only),
        summarize_epics.py (epic analysis only), and
        filter_standalone_tasks.py (task filtering only).
  Why:  Each step can now be run and debugged independently.
        Skipping one step doesn't require skipping the others.
  Files: scripts/group_issues.py (new), scripts/summarize_epics.py,
         scripts/filter_standalone_tasks.py (new), main.py

CHANGE 2: Keep closed issues as lightweight entries
  What: Previously, 66% of fetched records were discarded because
        they were closed. Now they're kept with just title, assignee,
        and dates — no description or comments.
  Why:  The AI can now see the full picture of what was accomplished
        vs what's still in progress, giving richer executive reports.
  Files: scripts/fetch_data.py, prompts/epic_prompts.py,
         prompts/category_prompts.py

Read the full file on GitHub · 113 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 · 113 lines · 33 tokens per session scan A a5a844c3a72a

Subscribe to this mod's changes

diff-explain is a command published in the GitHub repository Benkapner/claude-code-basecamp (16 stars, last pushed 12d ago), licensed MIT. It adds 33 tokens to every session and 846 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 2026-08-30.