difit is a command-line tool that starts a local web server showing Git commit differences in a GitHub-style file-change viewer. Developers use it to inspect and review local diffs or pull requests, with review comments that can also be copied into AI prompts. The catalogue entries connect coding-agent workflows to difit for requesting or performing reviews.
Borrowing it
Nothing to install: this file belongs to yoshiko-pg/difit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/yoshiko-pg/difit/main/.claude/skills/difit-dev/SKILL.mdgit clone --depth 1 https://github.com/yoshiko-pg/difitWrote 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/yoshiko-pg/difit/difit-dev)<a href="https://agentmods.dev/skills/yoshiko-pg/difit/difit-dev"><img src="https://agentmods.dev/badge/skills/yoshiko-pg/difit/difit-dev/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/yoshiko-pg/difit/difit-dev"><img src="https://agentmods.dev/badge/skills/yoshiko-pg/difit/difit-dev.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00028 | $0.00670 |
| Opus 5.5 | $0.00011 | $0.00268 |
| Sonnet 5.5 | $0.00006 | $0.00134 |
| Haiku 4.5 | $0.00003 | $0.00067 |
Grade A, and why
difit-dev 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Difit Dev
Overview
This skill requests a code review from the user using pnpm run dev in this repository.
Running pnpm run dev once is sufficient to start the review request workflow.
Do not open a browser yourself, verify that a browser connected, or restart the server just to keep it alive.
If the user leaves review comments, they are printed to stdout when the difit command exits.
When review comments are returned, continue work and address them.
If the server is shut down without comments, treat it as "no review comments were provided." Restarting it is unnecessary.
Treat Client disconnected, shutting down server... without comments as a successful no-comments outcome.
Manual verification of whether the page launched correctly is also unnecessary.
Commands
- Review uncommitted changes before commit:
pnpm run dev . - Review the HEAD commit:
pnpm run dev - Review staging area changes:
pnpm run dev staged - Review unstaged changes only:
pnpm run dev working
Basic Usage:
pnpm run dev <target> # View single commit diff. ex: pnpm run dev 6f4a9b7
pnpm run dev <target> [compare-with] # Compare two commits/branches. ex: pnpm run dev feature main
Optional Startup Comments
If there is something you want to tell the user when difit opens, attach it as startup comments with --comment.
This is useful for review findings, explanations, and any context the user should see directly on the diff.
pnpm run dev <target> [compare-with] \
--comment '{"type":"thread","filePath":"src/foobar.ts","position":{"side":"old","line":102},"body":"line 1\nline 2"}' \
--comment '{"type":"thread","filePath":"src/example.ts","position":{"side":"new","line":{"start":36,"end":39}},"body":"Range comment for L36-L39"}'
- Do not insert
--afterpnpm run devin this repository.pnpm run dev -- ...breaks argument parsing here. - Use
type: "thread"for each comment. - Write comment bodies in the language the user is using.
- Use
position.side: "new"for lines that exist on the target side of the diff. - Use
position.side: "old"for lines that exist only on the deleted side. - Use range comments for issues that span multiple lines.
- Never copy secrets, tokens, passwords, API keys, private keys, or other credential-like material from the diff into
--commentbodies or any command-line arguments.
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 · 65 lines · 28 tokens per session scan A cbba701be8f3
difit-dev is a skill published in the GitHub repository yoshiko-pg/difit (3,296 stars, last pushed 2mo ago), licensed MIT. It adds 28 tokens to every session and 670 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…