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/alexmond/alexmskillsnpx agentmods add skills/alexmond/alexmskills/screenshot-tourWrote 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/alexmond/alexmskills/screenshot-tour)<a href="https://agentmods.dev/skills/alexmond/alexmskills/screenshot-tour"><img src="https://agentmods.dev/badge/skills/alexmond/alexmskills/screenshot-tour/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/alexmond/alexmskills/screenshot-tour"><img src="https://agentmods.dev/badge/skills/alexmond/alexmskills/screenshot-tour.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 | $0.00116 | $0.05044 |
| Opus 5.5 | $0.00046 | $0.02018 |
| Sonnet 5.5 | $0.00023 | $0.01009 |
| Haiku 4.5 | $0.00012 | $0.00504 |
Grade C, and why
screenshot-tour scanned grade C 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
**Lead with:** 01-hero · 03-<core-flow> · NN-outcome <!-- the 3-shot subset for a skim, a forum post, or a social embed — pick the images that carry the story alone --> How it starts
The opening of the file, as written. The whole thing — 358 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex: Read the client path before applying this workflow.
Screenshot Tour
Try it:
/screenshot-tour:screenshot-tour— or say "build a presentation deck of this product".
Not
screenshot-sweep, which audits a capture you already have for defects. This one produces a deck. If a tour capture shows something broken, that is a sweep finding — file it, don't put it in the deck.
A presentation deck is not a screenshot — it's the set of aspects a stranger needs to see to understand what the product does, ordered as a narrative they can follow without you talking over it. A single capture answers "what does it look like"; a deck answers "what does it do, end to end, in the moments that matter." The skill's job is to make sure the deck is complete enough to substitute for a 5-minute live demo, and consistent enough that every image reads as one product.
The deliverable is the deck itself — a numbered set of images plus a one-page manifest under presentation/. Slide-deck export, README integration, and docs-site embedding are optional follow-ups (see the bottom of this file), not part of the core loop.
Boundaries
Invoke proactively when the user is preparing a demo, stakeholder meeting,
release announcement, or pitch and there are no captures in presentation/.
Not for: single ad-hoc screenshots (plain Bash or a screenshot skill), visual
regression testing (Chromatic / Playwright tests), or documentation-site
illustrations — that's a downstream consumer of the deck, not its goal.
Files this skill owns
presentation/plan.md— the editable tour plan (numbered aspects + capture method per aspect); user-gated before any capture runs.presentation/tour.md— the final manifest with each image + caption, ordered for narrative.presentation/recipes/*.tape(CLI products) or*.spec.ts(web products) — the per-aspect capture scripts. Re-runnable.presentation/NN-<slug>.{png,gif}— the captures themselves, numbered for ordering.presentation/contact-sheet.png— optional 1-image overview of the whole deck (5×N grid)..claude/screenshot-tour/log.md— the per-run log (one entry per tour run); the skill graduates patterns out of this into a## Screenshot tourblock in the repo'sCLAUDE.md.
What ships with it
2 files 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.
- 1mo ago Changed · +3 lines 050b35373a4a
- 1mo ago Changed · +1 lines · -57 tokens per session fc6cb39e7733
- 2mo ago First seen · 354 lines · 173 tokens per session scan C fcc457ca4a3e
screenshot-tour is a skill published in the GitHub repository alexmond/alexmskills (10 stars, last pushed 11d ago), licensed MIT. It adds 116 tokens to every session and 5,044 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-05.
screenshot-tour compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| screenshot-touralexmond/alexmskills | Skill | 10 | 11d ago | MIT | C | 116 | Claude Code |
| anatomyNousResearch/hermes-agent | Skill | 262k | today | MIT | A | 15 | Claude Code, Codex |
| canvaasgeirtj/system_prompts_leaks | Skill | 71k | 2d ago | CC0-1.0 | A | 62 | Claude Code, Codex |
| optionsasgeirtj/system_prompts_leaks | Skill | 71k | 2d ago | CC0-1.0 | A | 13 | Claude Code |
| qa-test-plannerdavila7/claude-code-templates | Skill | 33k | today | MIT | A | 34 | Claude Code, Codex |
| archifyNousResearch/hermes-agent | Skill | 262k | today | MIT | A | 12 | Claude Code, Codex |
| ux-designDonchitos/Claude-Code-Game-Studios | Skill | 37k | today | MIT | A | 31 | Claude Code |