Borrowing it
Nothing to install: this file belongs to cardstack/boxel. 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/cardstack/boxel/main/.claude/skills/pr-screenshots/SKILL.mdgit clone --depth 1 https://github.com/cardstack/boxelWrote 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/cardstack/boxel/pr-screenshots)<a href="https://agentmods.dev/skills/cardstack/boxel/pr-screenshots"><img src="https://agentmods.dev/badge/skills/cardstack/boxel/pr-screenshots/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/cardstack/boxel/pr-screenshots"><img src="https://agentmods.dev/badge/skills/cardstack/boxel/pr-screenshots.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 | $0.00090 | $0.00907 |
| Opus 5.5 | $0.00036 | $0.00363 |
| Sonnet 5.5 | $0.00018 | $0.00181 |
| Haiku 4.5 | $0.00009 | $0.00091 |
Grade A, and why
pr-screenshots 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 5d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Screenshots
A GitHub PR body renders images by URL, but an agent has no way to upload an image straight into the PR description. The reliable workaround: commit the image to the branch, reference it by a commit-SHA-pinned raw URL, then delete the file in a followup commit. Reviewers keep seeing the image; the merged branch doesn't carry the artifact at HEAD.
Visual changes benefit enormously from a screenshot — reviewers react to the actual rendering instead of imagining it. Don't skip the image and describe it verbally when the change is visual.
Order of operations (do NOT parallelize — the URL depends on the SHA)
-
Commit the image into the branch at an obvious throwaway path:
.pr-images/<slug>/<name>.png— hidden dir, never touched by the runtime, easy to spot and strip.- or
docs/_pr-images/<slug>/<name>.pngif the repo already has a docs dir. - Keep it small — crop or resize before committing.
-
Push the branch so the blob is reachable.
-
Capture the SHA of that commit immediately:
git rev-parse HEAD(before any followup commits). -
Open the PR (or post the comment) with the body referencing the SHA-pinned raw URL:
 -
Followup commit
git rms the image and pushes. GitHub still serves the blob from the named commit, so the SHA-pinned reference keeps working.
Critical gotcha: pin to the commit SHA, never the branch
Branch-pinned raw URLs follow HEAD. The moment the cleanup commit git rms the image, a branch-pinned URL 404s and the image breaks in the PR — GitHub does not auto-resolve a missing branch-pinned URL back to a historical blob.
- ✅ Immutable:
…/<owner>/<repo>/<commit-sha>/.pr-images/… - ❌ Follows HEAD, breaks after strip:
…/<owner>/<repo>/<branch>/.pr-images/…
Relative paths (./.pr-images/foo.png) do render in PR bodies, but break when the PR is viewed from a fork or after a rebase. SHA-pinned raw URLs are the durable form.
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.
- 5d ago First seen · 50 lines · 90 tokens per session scan A 7e7f178f24c9
pr-screenshots is a skill published in the GitHub repository cardstack/boxel (27 stars, last pushed today), licensed MIT. It adds 90 tokens to every session and 907 once invoked, about $0.0004 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 2026-10-21.
Other skills, from other repositories
critique-theater
Five-dimension design quality review — score the artifact against craft, brand, accessibility, and copy, then fix what falls short before handing it over.
design-review
Five-dimension design audit (frontend UI/UX · server data-model & flow · endpoint spec · daemon-runtime/SDK & local-cache-first · built-in skill/agent-role), executed by a NON-implementing agent. Every dimension gets a verdict; N/A only with a stated reason. A dimension the design silently skipped must be surfaced as…
cinematic-shot
Shoot software UI like a film. A sequence of hero shots, each a steep, oblique, extreme close-up of the interface floating in black, with a razor-thin focal plane, a slow motivated camera drift, and UI that acts on its own, hard-cut on the action, ending on one line of copy and a still logo. Use when asked for a…
compare-screenshots
Compare screenshots against the intended design, distinguishing approved references from historical baselines. Use for iterative implementation matching, before/after visual review, objective image telemetry, or checking a lone capture for flat, empty, or badly framed content.
design-with-images
Explore UI and visual design with image generation, then iterate the real implementation against the user-selected concept. Use when brainstorming visual directions, offering mockup variants, or implementing an approved generated design; do not stop at the mockups or the first code approximation.
preview-shots
Open image shots (screenshots, snapshot baselines, montages, renders) in ONE macOS Preview window so the user can eyeball them. Use when the user asks to open / show / pull up / review shots in Preview or Finder, or right after producing visual artifacts the user should look at before signing off.