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.
npx skills add Sagargupta16/claude-skills --skill diff-explaingit clone --depth 1 https://github.com/Sagargupta16/claude-skillsWrote 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.
[](https://agentmods.dev/skills/sagargupta16/claude-skills/diff-explain)<a href="https://agentmods.dev/skills/sagargupta16/claude-skills/diff-explain"><img src="https://agentmods.dev/badge/skills/sagargupta16/claude-skills/diff-explain/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.
<a href="https://agentmods.dev/skills/sagargupta16/claude-skills/diff-explain"><img src="https://agentmods.dev/badge/skills/sagargupta16/claude-skills/diff-explain.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00055 | $0.00602 |
| Opus 5.5 | $0.00022 | $0.00241 |
| Sonnet 5.5 | $0.00011 | $0.00120 |
| Haiku 4.5 | $0.00006 | $0.00060 |
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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
diff-explain
Live context (when diffing a local branch)
- Current branch diff stat: !
git diff $(git merge-base HEAD origin/main 2>/dev/null || git merge-base HEAD main 2>/dev/null || echo HEAD)...HEAD --stat 2>/dev/null || echo "no local diff vs main"
When to activate
- User pastes a diff and asks "what does this do?" / "summarize" / "explain".
- User shares a PR link or branch name and wants a quick read before reviewing.
- Reviewing unfamiliar changes before merge.
Do NOT activate when the user is asking for a detailed line-by-line review -- that's a different task.
Steps
- Get the diff.
- PR link:
gh pr diff <url-or-number> - Local branch:
git diff <base>...HEAD(default base:mainormaster) - Pasted: use what the user pasted.
- PR link:
- Read it fully. Don't skim the first 50 lines and guess.
- Group by concern. Even if the diff touches many files, most diffs have 1-3 concerns (a bug fix, a rename, a new feature). Name each concern in plain language.
- Write ONE paragraph. 3-5 sentences covering:
- What changed (the concern, not the files).
- Why it likely changed (if the commit message / PR title / linked issue says).
- What risk it introduces (behavior change, API change, DB migration, dependency bump).
- Optional risk line. If one specific thing deserves attention before merge, append one line starting with
Watch out for:.
Rules
- No file-by-file walk. Group by concern, not by path.
- No bullet lists. Prose only.
- If the diff is large (>500 lines), say so in the first sentence and narrow to the top 2-3 concerns instead of trying to cover everything.
- Don't speculate about business motivation beyond what commits, PR title, or linked issue state.
- Flag real problems. Suspected bugs, security issues, missing tests, or breaking API changes go in the summary or in the "Watch out for" line. Don't paper over them.
Output
One paragraph. Optional single-line Watch out for: ... trailer.
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.
- 2mo ago First seen · 48 lines · 55 tokens per session scan A 0abe755e6127
diff-explain is a skill published in the GitHub repository Sagargupta16/claude-skills (5 stars, last pushed yesterday), licensed MIT. It adds 55 tokens to every session and 602 once invoked, about $0.0002 per session on Opus 5.5. 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.
diff-explain compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| diff-explainSagargupta16/claude-skills | Skill | 5 | yesterday | MIT | A | 55 | Claude Code |
| phpunit-test-team-reviewingshopwareLabs/ai-coding-tools | Skill | 45 | 2d ago | MIT | A | 52 | Claude Code |
| phpunit-test-reconcilingshopwareLabs/ai-coding-tools | Skill | 45 | 2d ago | MIT | A | 32 | Claude Code |
| issue-analyzingshopwareLabs/ai-coding-tools | Skill | 45 | 2d ago | MIT | A | 51 | Claude Code |
| pr-analyzingshopwareLabs/ai-coding-tools | Skill | 45 | 2d ago | MIT | A | 56 | Claude Code |
| code-reviewmelodic-software/claude-code-plugins | Skill | 30 | today | MIT | A | 63 | Claude Code |
| audit-comment-residuemelodic-software/claude-code-plugins | Skill | 30 | today | MIT | A | 95 | Claude Code |