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.
git clone --depth 1 https://github.com/callmejustdodo/popcornWrote 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/commands/callmejustdodo/popcorn/browser)<a href="https://agentmods.dev/commands/callmejustdodo/popcorn/browser"><img src="https://agentmods.dev/badge/commands/callmejustdodo/popcorn/browser/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/commands/callmejustdodo/popcorn/browser"><img src="https://agentmods.dev/badge/commands/callmejustdodo/popcorn/browser.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 | $0.00019 | $0.00310 |
| Opus 5.5 | $0.00008 | $0.00124 |
| Sonnet 5.5 | $0.00004 | $0.00062 |
| Haiku 4.5 | $0.00002 | $0.00031 |
Grade B, and why
browser scanned grade B 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
echo "current: $(cat "$HOME/.claude/.popcorn-browser")" What it actually says
Set the browser popcorn controls. Argument: $ARGUMENTS
Run this bash command to update (or show) the config, then report the result in one short sentence:
case "$ARGUMENTS" in
chrome|Chrome|"Google Chrome") BROWSER="Google Chrome" ;;
arc|Arc) BROWSER="Arc" ;;
safari|Safari) BROWSER="Safari" ;;
brave|Brave|"Brave Browser") BROWSER="Brave Browser" ;;
edge|Edge|"Microsoft Edge") BROWSER="Microsoft Edge" ;;
"")
if [ -f "$HOME/.claude/.popcorn-browser" ]; then
echo "current: $(cat "$HOME/.claude/.popcorn-browser")"
else
echo "current: Google Chrome (default — no config set)"
fi
exit 0
;;
*) BROWSER="$ARGUMENTS" ;;
esac
mkdir -p "$HOME/.claude"
echo "$BROWSER" > "$HOME/.claude/.popcorn-browser"
echo "popcorn browser set to: $BROWSER"
The config file lives at ~/.claude/.popcorn-browser. The hooks read it on every prompt; no restart needed.
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 · 34 lines · 19 tokens per session scan B d109a491d6a5
browser is a command published in the GitHub repository callmejustdodo/popcorn (9 stars, last pushed 5mo ago), licensed MIT. It adds 19 tokens to every session and 310 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
archive-mail
A command that archives Apple Mail messages involving a chosen contact into Markdown files, which are plain-text documents with simple formatting. It can use a contact filter, an output directory, or saved settings.
archive-mail-repair-synthetic-ids
A one-time repair command for archived email files whose message ID was replaced with a made-up placeholder. A message ID is the identifier email systems use to distinguish one message from another.
archive-mail-migrate
A one-time command that moves old email archive indexes and settings into the newer `.claude/.mail/` folder structure. It leaves the archived Markdown emails where they are.
archive-mail-view
A command that combines the saved emails for one conversation into a single readable thread file. It finds the conversation by matching part of its key in the thread index.
archive-mail-rebuild-threads
A command that rebuilds the index connecting archived email files to their conversation threads. It reads the metadata at the top of each Markdown file and recreates the thread index file.
changelog
Generate changelog from session work with Problem/Solution format.