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 glide-the/im-dream --skill react-grabgit clone --depth 1 https://github.com/glide-the/im-dreamWrote 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/glide-the/im-dream/react-grab)<a href="https://agentmods.dev/skills/glide-the/im-dream/react-grab"><img src="https://agentmods.dev/badge/skills/glide-the/im-dream/react-grab/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/glide-the/im-dream/react-grab"><img src="https://agentmods.dev/badge/skills/glide-the/im-dream/react-grab.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 | $0.00086 | $0.00730 |
| Opus 5.5 | $0.00034 | $0.00292 |
| Sonnet 5.5 | $0.00017 | $0.00146 |
| Haiku 4.5 | $0.00009 | $0.00073 |
Grade A, and why
react-grab 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 12d 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.
This is a copy
100% identical to react-grab — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
React Grab
The user selects UI elements in their browser and copies them with React Grab.
npx react-grab@latest pull waits for new grabs and prints each as one line of
JSON (usually one, sometimes a few if several were copied), starting the
background watcher automatically the first time. Run it in a loop.
The loop
Repeat until the user says stop:
- Wait for the next grab:
npx react-grab@latest pull --max-age 0
It blocks until the user grabs something, then prints the new grab(s) — one JSON
object per line. --max-age 0 is important: it delivers every grab regardless of
age, so a comment the user added while you were busy on the previous task isn't
silently dropped (the default skips grabs older than ~5 min as stale). Act on
every line. If your shell cancels the command before a grab arrives, just run it
again — nothing is lost; the watcher keeps capturing in the background and pull
resumes where it left off.
- Act on the grab (below).
- Go back to step 1.
A new grab while you're working wins
The watcher never stops capturing — including while you're mid-task. A grab the user makes before you finish is them redirecting you, so it supersedes whatever you're doing. Don't make them wait for the old task to finish.
While acting on a grab:
- Run anything slow (dev servers, builds, installs, test runs) as a background process, never a blocking foreground call, so you stay free to notice new grabs.
- Between steps, peek without blocking:
npx react-grab@latest pull --max-age 0 --wait 0
Empty output means nothing new — keep going. If it prints a grab, the user has moved on: stop the current task, cancel any background processes you started for it, and act on the newest grab instead.
Acting on a grab
Each grab JSON has content (the element's source references) and, in prompt
mode, prompt (the user's typed instruction):
promptpresent → that comment IS the task. Execute it against the grabbed source;contentholds the references (// path:line,in Component (at …)), so jump straight to that file.- No
prompt→ apply the standing instruction the user set when starting the loop, or, if there is none, triage it (summarize component +file:line) and wait for direction.
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.
- 12d ago First seen · 83 lines · 86 tokens per session scan A 977f2d610790
react-grab is a skill published in the GitHub repository glide-the/im-dream (0 stars, last pushed yesterday), licensed MIT. It adds 86 tokens to every session and 730 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to react-grab, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
next-dev-loop
Verify Next.js runtime behavior after editing app code. Use this skill to confirm a change actually works in a running app — not just that it compiles or type-checks. Combines /next/mcp (Next.js's view) with agent-browser (the browser's view). Requires a running next dev.
next-bundle-optimizer
Audit and reduce Next.js browser initial-load work. Use for slow route startup, oversized client bundles, duplicate browser dependencies, or features that can wait for interaction.
next-partial-prefetching-optimizer
Optimize what selected Next.js client navigations include before the click under Partial Prefetching. Use after Cache Components and Partial Prefetching are adopted when the user wants selected URL-specific UI to be instant, wants reusable content to wait for navigation, or needs to choose between default, viewport…