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 fmind/dot --skill clipboardgit clone --depth 1 https://github.com/fmind/dotWrote 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/fmind/dot/clipboard)<a href="https://agentmods.dev/skills/fmind/dot/clipboard"><img src="https://agentmods.dev/badge/skills/fmind/dot/clipboard/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/fmind/dot/clipboard"><img src="https://agentmods.dev/badge/skills/fmind/dot/clipboard.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 | $0.00012 | $0.00625 |
| Opus 5.5 | $0.00005 | $0.00250 |
| Sonnet 5.5 | $0.00002 | $0.00125 |
| Haiku 4.5 | $0.00001 | $0.00063 |
Grade B, and why
clipboard 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 4d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- **Install the matching Linux backend**: for a missing backend, install the one matching the display server (`xclip` or `wl-clipboard`; macOS has `pbcopy` built in); do not use sudo or install tools silently. How it starts
The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clipboard
Treat /clipboard without arguments as “copy the interesting output I requested in the preceding exchange.” Arguments can select a particular result or format.
Workflow
-
Select the latest requested deliverable: a draft, prompt, command, code snippet, table, or test result. Omit assistant preambles, progress updates, tool logs, and offers to continue unless they are the requested output. Preserve the deliverable verbatim; do not regenerate it or rerun a test. For code or commands, omit the surrounding Markdown fence unless the user requested Markdown. If several outputs are equally plausible, ask which one; never guess unavailable conversation content.
-
Pipe the text to the helper: pass the selected UTF-8 text to scripts/copy.py on stdin using
python -I. Use the tool's structured stdin when available, or a single-quoted heredoc with a delimiter absent from the text; never interpolate the content into shell commands or command-line arguments. The helper bounds its stdin read and rejects deliverables above 1 MiB; use a file for larger content. It strips exactly one final newline, the one a heredoc always adds; pass--keep-final-newlinewhen the deliverable must end with one, such as a whole file.python -I ~/.agents/skills/clipboard/scripts/copy.py <<'CLIPBOARD_PAYLOAD' The selected deliverable goes here, unchanged. CLIPBOARD_PAYLOAD -
Confirm briefly what was copied: do not repeat the payload. The helper checks the clipboard byte for byte and reports success only after verification. If it fails, report the cause, including the native tool's diagnostic it prints, and the relevant recovery from platform behavior; do not claim that the clipboard was updated successfully.
Boundaries
- Install the matching Linux backend: for a missing backend, install the one matching the display server (
xcliporwl-clipboard; macOS haspbcopybuilt in); do not use sudo or install tools silently. - Avoid OSC 52 in tool output: do not emit OSC 52 escape sequences through tool output; captured output may never reach the user's terminal.
- Copying does not authorize pasting: invocation authorizes replacing the current clipboard; it does not authorize pasting into an application or sending the content elsewhere.
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.
- 4d ago Changed 7be90b5fbb96
- 11d ago Changed ab6f16a57b6e
- 12d ago First seen · 39 lines · 12 tokens per session scan B ef97eae35399
clipboard is a skill published in the GitHub repository fmind/dot (11 stars, last pushed yesterday), licensed MIT. It adds 12 tokens to every session and 625 once invoked, about $0.0000 per session on Opus 5.5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-05.
Other skills, from other repositories
google-workspace-cli
Use gws across Workspace APIs with schema-first calls, profile isolation, bounded reads, and verified Drive, Docs, Sheets, Gmail, Calendar, or Chat writes.
handover
Write a self-contained follow-up prompt carrying this session's decisions, constraints, and verified findings into a fresh agent session. Use when handing unfinished work to a new context window.
dotfiles-bootstrap
Bootstrap a workstation with the dotfiles framework. Takes a GitHub user / owner+repo / explicit clone URL and runs dot init (which shells out to chezmoi) with the right safety prompts. Honors the active agent profile (ask / plan / apply / audit) so it defaults to dry-run in safer modes and full apply in apply.
vibe
Delegate a coding task to a cheap AI model (Mistral Vibe by default, but any provider Vibe knows about — DeepSeek, Gemini Flash, etc.) and supervise the result via git diff. Claude orchestrates, the cheap model codes. Claude consumes 500-1500 tokens per delegation regardless of how many file reads the delegate does…
telegram
Send notifications, interactive questions, or multiple-choice polls to the user via Telegram. Use when the user asks to be notified ("ping me", "notify me on Telegram", "ask me when..."), when a long-running task finishes and the user is likely away, when an irreversible action needs out-of-band confirmation, or when…
dotfiles
Chezmoi dotfiles conventions and patterns. Use when modifying dotfiles, adding new managed files, working with chezmoi templates, or syncing agent skills and subagents through agentspec. Do NOT use for installing tools, running doctor, or updating a machine through the dotfiles CLI; use manage-machine.