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 agentmods add skills/jtsternberg/claude-plugins/diff-viewnpx skills add jtsternberg/claude-plugins --skill diff-viewgit clone --depth 1 https://github.com/jtsternberg/claude-pluginsWhat 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 | $0.00044 | $0.02489 |
| Opus 5 | $0.00022 | $0.01244 |
| Sonnet 5 | $0.00009 | $0.00498 |
| Haiku 4.5 | $0.00004 | $0.00249 |
Grade A, and why
diff-view 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 2d 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 — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
diff-view
Generates a single self-contained HTML file that renders a rich code diff — dark GitHub-ish theme, line-numbered, syntax-highlighted, with word-level intra-line highlighting on lines that changed. No external dependencies, no network: the diff is computed by a small vanilla-JS pass embedded in the file, which runs on load. The file opens in the user's $EDITOR/browser and can be screenshotted full-page for dropping straight into a GitHub PR description or Slack.
This is a collab-tools skill: like its companions temp-draft and promote-draft, it routes work that doesn't belong in chat (a big visual diff) into a real artifact under /tmp/collab-tools/.
Two modes, auto-detected by how many sources you pass:
- 2-way (2 sources) — side-by-side. Line-level LCS alignment; adjacent delete/insert runs pair into "changed" rows.
- 3-way (3 sources) — three columns. A 3D LCS finds the lines common to all three (the shared "spine"); lines unique to a column stack in per-column gaps. Ideal for before / after / extracted-shared refactors.
When to use this
Use it when:
- The user invokes
/collab-tools:diff-view, or asks to "diff these", "compare side by side", "show this as an HTML diff", "screenshot the diff to share", etc. - Comparing two versions of a file, two near-identical functions, or three variants where a unified
git diffwould be noisy or hard to read. - The user wants something shareable (a screenshot for a PR/Slack), not just a terminal read.
Don't use it for:
- Applying patches, staging, or anything that mutates code.
- A quick terminal read of a small change — plain
git diffis fine.
How it works
A bundled Node script (scripts/gen-diff.js, zero dependencies — Node built-ins only, no npm install) templates the HTML: it injects the sources, title, column labels, and syntax keyword set, picks the 2-way vs 3-way layout, writes the .html, and optionally drives a headless browser to capture a PNG.
Key properties (carried over from the proven prototype, hardened for arbitrary input):
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 152 lines · 44 tokens per session scan A 11aa25c0c3c0
diff-view is a skill published in the GitHub repository jtsternberg/claude-plugins (5 stars, last pushed 4d ago), licensed MIT. It adds 44 tokens to every session and 2,489 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…