Hunk is a terminal application for reviewing code changes created by coding agents, with views for multi-file diffs, inline annotations, and Git-backed reviews. Developers use it to inspect, navigate, and approve changesets from the command line.
Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/modem-dev/hunknpx agentmods add skills/modem-dev/hunk/hunk-launch-videoWrote 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/modem-dev/hunk/hunk-launch-video)<a href="https://agentmods.dev/skills/modem-dev/hunk/hunk-launch-video"><img src="https://agentmods.dev/badge/skills/modem-dev/hunk/hunk-launch-video/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/modem-dev/hunk/hunk-launch-video"><img src="https://agentmods.dev/badge/skills/modem-dev/hunk/hunk-launch-video.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 Tool Misuse · line 124 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00060 | $0.05507 |
| Opus 5.5 | $0.00024 | $0.02203 |
| Sonnet 5.5 | $0.00012 | $0.01101 |
| Haiku 4.5 | $0.00006 | $0.00551 |
Grade A, and why
hunk-launch-video 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 4d 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 — 420 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hunk video pipeline
Source-checkout only: the pipeline lives in scripts/launch-video/, which never ships to npm.
It can be used for pull-request demos as well as maintainer release videos. Unix-only — the
capture scripts exec /bin/bash.
Generates product videos where every terminal frame is the real Hunk TUI — no screen recording, no mockups. Three stages:
capture.ts (bun) drive Hunk over a PTY, snap styled keyframes to PNG
compose.mjs (node + Playwright) render each PNG on a 1920x1080 HTML stage in Chromium
ffmpeg encode the composited PNGs at 30fps to mp4/webm
Playwright controls headless Chromium: for each planned frame it loads the terminal PNG onto the HTML stage, applies the window chrome, cards, captions, and transition state, then screenshots the completed stage back to PNG. ffmpeg sequences those composited screenshots into the final videos.
The generic machinery (PTY driving, keyframe rendering, storyboard planning,
Chromium compositing, the stage template) is the @hunk/term-video workspace
package in packages/term-video/; scripts/launch-video/ holds only Hunk's
scenes, captions, and cards on top of it.
Choosing a recipe
The pipeline is not release-specific. Choose the editorial scope, then use the same capture → composite → encode stages:
- Single feature: a short demonstration of one capability or workflow. Use the single-feature recipe below and capture only the required scene.
- Full release: a multi-feature roundup based on a release's changelog or highlights. Use the full-release recipe and update the canonical storyboard.
- Custom video: author any set of scenes and
SHOTSfor tutorials, comparisons, announcements, or workflow explainers; follow the scene and storyboard rules below.
Creating a video
Expect ~3–6 min for capture and ~2–4 min for compose — run both with a long
timeout (or in the background); each logs per-snap / per-shot progress.
compose.mjs needs node ≥ 18 on PATH (bun alone is not enough).
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.
- 4d ago Changed · +2 lines fe2a9ac25cdf
- 1mo ago Changed · +59 lines 06179a8190ed
- 1mo ago Changed · +33 lines 53e09163a2c5
- 1mo ago First seen · 326 lines · 60 tokens per session scan A c8e7afc30ee3
hunk-launch-video is a skill published in the GitHub repository modem-dev/hunk (9,617 stars, last pushed today), licensed MIT. It adds 60 tokens to every session and 5,507 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
gh-find-prs
Survey open Codewhale PRs and triage each for mergeability and disposition against the real landing branch.
github
Skill "github" from Hmbown/Codewhale, covering github, when to use, setup, workflow and non-goals.
revdiff
Review diffs, files, and documents with inline annotations in a TUI overlay, or answer questions about revdiff usage, configuration, themes, and keybindings. Opens revdiff in agterm/tmux/zellij/herdr/kitty/wezterm/cmux/ghostty/iterm2/emacs-vterm, captures annotations, and addresses them. Works in git, hg, and jj repos…
fix-pr
One-verb pipeline for the operator's highest-frequency manual loop: fetch a PR's unresolved reviewer feedback (inline review comments, review-summary bodies, and issue-level conversation comments) and failing CI checks, triage each issue via parallel read-only probes, fix the validated items in an isolated managed…
pull-request-automation
Audits and improves the pull request workflow for a GitHub repository. Covers PR description templates, auto-labelling, CODEOWNERS, PR size checks, and branch protection rules. Invoked when the user asks to improve the PR process, set up PR automation, or add a PR template.
hatch3r-cli-fd
User-friendly find replacement, gitignore-aware. Use when locating filenames or directories by glob with parallel walking; invoke fd. Outputs newline-separated hit records; bound results with -c or --max-count.