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 skills add PackmindHub/packmind --skill michel-create-pr-with-screenshotsgit clone --depth 1 https://github.com/PackmindHub/packmindWrote 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/packmindhub/packmind/michel-create-pr-with-screenshots)<a href="https://agentmods.dev/skills/packmindhub/packmind/michel-create-pr-with-screenshots"><img src="https://agentmods.dev/badge/skills/packmindhub/packmind/michel-create-pr-with-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/packmindhub/packmind/michel-create-pr-with-screenshots"><img src="https://agentmods.dev/badge/skills/packmindhub/packmind/michel-create-pr-with-screenshots.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 | $0.00105 | $0.01590 |
| Opus 5.5 | $0.00042 | $0.00636 |
| Sonnet 5.5 | $0.00021 | $0.00318 |
| Haiku 4.5 | $0.00011 | $0.00159 |
Grade A, and why
michel-create-pr-with-screenshots scanned grade A with 1 finding 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 1mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
On a **private repo**, raw URLs render only for viewers who are logged-in members — fine for internal PR review (the curl-with-token test below will 404 because the `/raw/` route wants a browser session, not a PAT — that How it starts
The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create PR with Screenshots
GitHub PR descriptions behave differently from README files: relative paths don't resolve and SVG files don't render (sanitized for XSS). This skill codifies the two-step fix every time: convert to PNG, reference with an absolute raw URL pinned to the commit SHA.
Running as the Michel agent? You do NOT build these URLs by hand. Write the PR body with the literal
<!-- ARTIFACTS_PLACEHOLDER -->token (see the implementation prompt's## Artifactssection) and drop every file under.agent/artifacts/issue-<N>/. The publish step lists each file and injects correctly-formed, SHA-pinned image/video markup at the token. Hand-writing paths orthere renders as dead text and the artifacts are lost. The rest of this skill is for the manual case — opening a PR yourself.The publish step (
fly/lib/phases/publish.sh) owns the entire## Artifactssection: it injects the generated block at the heading and discards every line under it — any relative-path images, stray tokens, or hand-written subsections — up to the next##heading. So hand-written junk there is now wiped rather than shipped (it used to survive next to the injected block — see PR #41, where a hand-written### Screenshotsblock withpaths rendered as broken images). This is a backstop, not a license: still emit only the bare token.
The core rule
| Artifact | Renders in PR? | Fix |
|---|---|---|
| PNG via raw URL pinned to SHA | ✅ | nothing |
| PNG via raw URL pinned to branch | ⚠️ dies when branch deleted | pin to the commit SHA |
| PNG via relative path | ❌ | use absolute URL |
| SVG via raw URL | ❌ (blocked by GitHub CSP) | convert to PNG first |
| WebM / MP4 video | ❌ inline | link, don't embed |
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.
- 1mo ago First seen · 134 lines · 105 tokens per session scan A 37651a17b145
michel-create-pr-with-screenshots is a skill published in the GitHub repository PackmindHub/packmind (319 stars, last pushed today), licensed Apache-2.0. It adds 105 tokens to every session and 1,590 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
ce-commit-push-pr
Commit, push, and open a PR. Use when asked to ship/open a PR, or for PR-description-only flows like writing, rewriting, or describing a PR body.
requesting-code-review
Use when completing tasks, implementing major features, or before merging to verify work meets requirements.
finishing-a-development-branch
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup.
gsd-reapply-patches
Reapply local modifications after a GSD update.
skill-design-lineage
Persist design documents with branch tracking, revision chains, and cross-session discovery.
gsd-undo
Safe git revert. Roll back phase or plan commits using the phase manifest with dependency checks.