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/.codex/skills/release/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/release)<a href="https://agentmods.dev/skills/yoshiko-pg/difit/release"><img src="https://agentmods.dev/badge/skills/yoshiko-pg/difit/release/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/release"><img src="https://agentmods.dev/badge/skills/yoshiko-pg/difit/release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high System Prompt Leakage · line 16 Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.Fix: Remove any instructions that reveal, print, or output system prompts or internal rules. System instructions should never be exposed to end users.
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 | $0.00061 | $0.00647 |
| Opus 5.5 | $0.00024 | $0.00259 |
| Sonnet 5.5 | $0.00012 | $0.00129 |
| Haiku 4.5 | $0.00006 | $0.00065 |
Grade A, and why
release 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release Workflow
Follow this workflow for the current repository.
Prepare changelog draft
- Run
./scripts/get-changes-since-tag.sh. - Categorize changes into these sections as needed:
Added,Changed,Deprecated,Removed,Fixed,Security,Thanks. - Use script output rules:
- Use GitHub username from script output.
- Exclude
yoshiko-pgandrenovate[bot]fromThanks. - Include PR numbers when available.
- Order bullets with PR numbers by ascending PR number within each section, and list multiple PR numbers within a bullet in ascending order.
- Use commit subject and body for categorization.
- Consolidate routine dependency-only updates, including grouped dependency updates, package manager bumps, and ordinary individual dependency bumps, into a single
Changedbullet formatted as- Update dependencies (#123 #124 #125); keep a separate bullet only when the dependency change is clearly user-facing beyond routine maintenance.
- Write the categorized content into
CHANGELOG.mdunder## [Unreleased]. - Ask for user confirmation in Japanese.
Release after explicit OK
- The only allowed
CHANGELOG.mdedits after OK are:- insert the new version heading with today's date directly below
## [Unreleased] - place the captured
Unreleasedbody under that new heading unchanged - leave
## [Unreleased]empty - update the bottom compare links for
Unreleasedand the new version
- insert the new version heading with today's date directly below
- Run
npm version --no-git-tag-version patch. - Move current
Unreleasedcontent into a new version section with today's date. - Update bottom links:
- Update
Unreleasedcompare link to new version tag. - Add compare link for the new version.
- Update
- Commit
CHANGELOG.mdandpackage.jsonwith an English message:chore: release vX.Y.Z. - Create tag
vX.Y.Z. - Push
mainand tags:git push origin main --tags. - If push is rejected by non-fast-forward:
- Run
git pull --rebase origin main. - Retry
git push origin main --tags.
- Run
- Build release notes from the new version section text in
CHANGELOG.md. - Create GitHub release on origin:
gh release create vX.Y.Z --title "vX.Y.Z" --notes-file <notes-file>
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.
- 2mo ago First seen · 54 lines · 61 tokens per session scan A 18b91d4c01a7
release is a skill published in the GitHub repository yoshiko-pg/difit (3,296 stars, last pushed 2mo ago), licensed MIT. It adds 61 tokens to every session and 647 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 2026-08-30.
Other skills, from other repositories
release-announcement
Write a release announcement — changelog, blog post, in-app note, or social post — that leads with user impact, names the audience, and includes upgrade/migration steps without filler.
release
Fully automate a release with version-bump and childhood.
release-notes
Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.
multi-agent-release-manager
Cleans up the workspace, formats code, runs presubmit checks, and uploads CLs to Gerrit.
pack-submit
Package one of this agent's own skills as a standalone community pack and submit it to the aeon registry as a PR.
release-helper
Ensures configuration and code changes are released correctly. Use PROACTIVELY whenever you edit config.json, change any setting, or fix a configuration bug in this project, so the change reaches production.