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 LandonSchropp/agent-toolkit --skill interactive-commandgit clone --depth 1 https://github.com/LandonSchropp/agent-toolkitWrote 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/landonschropp/agent-toolkit/interactive-command)<a href="https://agentmods.dev/skills/landonschropp/agent-toolkit/interactive-command"><img src="https://agentmods.dev/badge/skills/landonschropp/agent-toolkit/interactive-command/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/landonschropp/agent-toolkit/interactive-command"><img src="https://agentmods.dev/badge/skills/landonschropp/agent-toolkit/interactive-command.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 | $0.00043 | $0.00646 |
| Opus 5.5 | $0.00017 | $0.00258 |
| Sonnet 5.5 | $0.00009 | $0.00129 |
| Haiku 4.5 | $0.00004 | $0.00065 |
Grade A, and why
interactive-command scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 32 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Interactive Command
Run scripts/interactive-command.sh --command '<command>' --name <name>. It opens the command in a new herdr tab in the agent's workspace and blocks until that tab closes. The command persists its own result — an editor saves the file it was given, so write a scratch file first and read it back after.
The script also exits with the command's own exit code once the tab closes (or 1 if the tab is closed before the command finishes). Read this exit code if the wrapped command's own success/failure is meaningful to the caller. If it isn't, ignore it explicitly — wait "$command_pid" || true — so set -e doesn't abort the caller on an exit code it doesn't care about.
Always run the script in the background, with no timeout, so it can run until the tab closes. After running the command, print a short message provided by the calling skill to let the user know it has been opened. You're notified when the tab closes.
Closing a Tab
The tab you opened is yours. You put it on the user's screen, so you take it off again, and never end a turn asking them to close a window you opened.
On the normal path there is nothing to do: the user closes the tab, and the script exits carrying the command's result. Close it yourself the moment you stop waiting on that result, whatever the reason — the user redirects the session, or the workflow it belongs to is abandoned. A result you have stopped waiting for is worth nothing, so losing it costs nothing.
The script traps termination signals and closes its own tab on exit, so end the script rather than closing its tab: run it with the Bash tool's run_in_background and stop it with TaskStop on the task id it returns.
- Never background a script with
&.run_in_backgroundgives you a task id to stop it by and tells you when it finishes.&gives you neither. - Never hunt for a script's process.
pkill -f,killall, andps | grep | xargs killmatch every workspace and agent session on the machine, killing other sessions' tabs and the user's editors along with yours. A filter that looks scoped, likegrep "name review", is the worst: that label is identical in every workspace.
What ships with it
1 file 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 · +4 lines 5c55bee5d7ac
- 1mo ago Changed · +1 lines · +3 tokens per session 64a34f29b955
- 1mo ago First seen · 27 lines · 40 tokens per session scan A f37e99398666
interactive-command is a skill published in the GitHub repository LandonSchropp/agent-toolkit (3 stars, last pushed today), licensed MIT. It adds 43 tokens to every session and 646 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
cf-cli
Cloudflare's official cf CLI (beta) for the public Cloudflare API and Workers projects. Use for finding and running Cloudflare commands from the terminal — sign-in and profiles, cf cli search, cf schema, cf deploy/dev/build, resource commands for DNS, zones, D1, KV, and R2 — and for choosing between cf and Wrangler in…
workers-best-practices
Cloudflare Workers best practices for production applications. Use when writing, reviewing, or configuring Workers.
find-journalists
Build a researched, fit-checked journalist list for a specific PR campaign. Prefer Medialyst's asynchronous media-list research workflow when available, with explicit approval before credit spend; otherwise produce a best-effort local list without guessed contacts.
story-origin-check
Recover the first public timestamp and canonical major coverage for a newsjacking signal, then decide whether newer coverage is the same story, a different story, or a materially new development.
relevance-coarse-filter
Cheap, high-recall first-pass filter that removes obvious junk from a detector candidate pool before expensive story-origin research and PR judgment. Decides keep, monitoronly, or reject — never ranks, writes angles, verifies dates, or decides whether to pitch.
ai-visibility-writing
Audit, question, suggest, or fact-preservingly revise a press release, blog post, contributed article, or expert explainer so AI answer systems can more easily retrieve, understand, quote, and cite its useful information. Use when someone asks for AI visibility, AI search, answer-engine, AEO, GEO, AI Overview, or…