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/shahriarshm/planchetteWrote 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/shahriarshm/planchette/planchette)<a href="https://agentmods.dev/commands/shahriarshm/planchette/planchette"><img src="https://agentmods.dev/badge/commands/shahriarshm/planchette/planchette/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/shahriarshm/planchette/planchette"><img src="https://agentmods.dev/badge/commands/shahriarshm/planchette/planchette.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 | $0.00017 | $0.00097 |
| Opus 5.5 | $0.00007 | $0.00039 |
| Sonnet 5.5 | $0.00003 | $0.00019 |
| Haiku 4.5 | $0.00002 | $0.00010 |
Grade A, and why
planchette 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.
What it actually says
Use the control-window skill to drive a macOS window toward this goal:
$ARGUMENTS
Run planchette pick first so the user can select the target window, then loop
(capture → Read the screenshot → one action) until the goal is done. If no goal
is given above, ask what to do after the window is picked.
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 · 12 lines · 17 tokens per session scan A 693f265c9033
planchette is a command published in the GitHub repository shahriarshm/planchette (0 stars, last pushed 3mo ago), licensed MIT. It adds 17 tokens to every session and 97 once invoked, about $0.0001 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 commands, from other repositories
run
A command that starts a planned, isolated Windows computer-use task. It follows prepared steps, checks the computer setup, uses screenshots when needed, and reports what was actually verified.
axstream-teach
Compile a UI task into a fast replayable macro (do it once, instant forever).
CHANGELOG
Command "CHANGELOG" from bytedance/UI-TARS-desktop, covering 0.4.0 2024-12-10 - add logging, 1.2.29, 1.2.28, 1.2.26 and 1.2.25.
screenshot
Screenshot a URL or document and read it visually.
barebrowse
Browser automation using the user's real browser with real cookies. Handles consent walls, login sessions, and bot detection automatically.
live-canvas
Conduct design interviews, generate UI variations, and collect live click-to-annotate feedback that streams into the session so edits land without leaving the browser. Use when the user wants rapid iterative UI refinement, not just batched feedback.