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 CodeAlive-AI/ai-driven-development --skill clipboardgit clone --depth 1 https://github.com/CodeAlive-AI/ai-driven-developmentWrote 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/codealive-ai/ai-driven-development/clipboard)<a href="https://agentmods.dev/skills/codealive-ai/ai-driven-development/clipboard"><img src="https://agentmods.dev/badge/skills/codealive-ai/ai-driven-development/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/codealive-ai/ai-driven-development/clipboard"><img src="https://agentmods.dev/badge/skills/codealive-ai/ai-driven-development/clipboard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 68 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00036 | $0.00859 |
| Opus 5.5 | $0.00014 | $0.00344 |
| Sonnet 5.5 | $0.00007 | $0.00172 |
| Haiku 4.5 | $0.00004 | $0.00086 |
Grade A, and why
clipboard 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clipboard
Copy the most recent relevant text block from the conversation to the macOS system clipboard.
Plain Text Copy (Default)
Use a heredoc to safely handle special characters (quotes, apostrophes, backticks, dollar signs):
cat <<'CLIPBOARD' | pbcopy
<text to copy>
CLIPBOARD
Rich Text Copy (Formatted)
Use when the user wants formatting preserved for pasting into Slack, Word, Google Docs, Notion, etc. Sets both HTML and plain text on the clipboard via Swift, so the receiving app picks the richest format it supports.
Step 1: Write the HTML content to a temp file:
cat <<'CLIPBOARD_HTML' > /tmp/_clipboard_rich.html
<html><body>
<h2>Title</h2>
<p>Paragraph with <b>bold</b> and <i>italic</i>.</p>
<ul><li>Item one</li><li>Item two</li></ul>
</body></html>
CLIPBOARD_HTML
Step 2: Write the plain text fallback to a temp file:
cat <<'CLIPBOARD_TEXT' > /tmp/_clipboard_rich.txt
Title
Paragraph with bold and italic.
- Item one
- Item two
CLIPBOARD_TEXT
Step 3: Set clipboard with both HTML and plain text using Swift:
swift -e '
import AppKit
let html = try Data(contentsOf: URL(fileURLWithPath: "/tmp/_clipboard_rich.html"))
let text = try String(contentsOfFile: "/tmp/_clipboard_rich.txt", encoding: .utf8)
let pb = NSPasteboard.general
pb.clearContents()
pb.setData(html, forType: .html)
pb.setString(text, forType: .string)
'
Step 4: Clean up temp files:
rm -f /tmp/_clipboard_rich.html /tmp/_clipboard_rich.txt
When to Use Rich vs Plain
- Rich (HTML): User says "copy formatted", "copy as rich text", "copy for Slack/LinkedIn/Word/Docs/Notion", or the content has meaningful formatting (bold, headers, lists, code blocks). This is also the correct way to copy for Slack and LinkedIn — they accept HTML rich text from clipboard and render it with proper formatting (bold, lists, code, etc.). Do NOT use Slack mrkdwn or markdown syntax for clipboard copy — use HTML rich text instead, it works universally.
- ⚠️ Slack does NOT render HTML
<table>tags. Tables pasted into Slack appear as a broken mess of text. Instead of<table>, present tabular data as plain-text lines (e.g.Label: valueper line, or use<pre>for aligned columns). This also applies to LinkedIn and most chat apps.
- ⚠️ Slack does NOT render HTML
- Plain: Default for code snippets, terminal output, simple text, or when user says "copy to clipboard" without formatting context
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 · 85 lines · 36 tokens per session scan A 10c2cb8d1639
clipboard is a skill published in the GitHub repository CodeAlive-AI/ai-driven-development (163 stars, last pushed yesterday), licensed MIT. It adds 36 tokens to every session and 859 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 2026-08-30.
Other skills, from other repositories
chief-of-staff
Pursue a long-running goal in a single session by co-ordinating subagents.
asana
Organize Asana projects and tasks, configure custom fields and rules, and automate scoped updates through its API.
cc-status
A structured workflow for checking Codex configuration, task status, synchronization results, and project .codex task records.
token-saver
Minimize token consumption & maximize prompt cache hit rate. Use when user asks to save tokens, reduce cost, improve cache hit rate, or be more concise.
full-output-enforcement
Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.
developer-portal
Professional Developer Portal Expert skill. Improve code delivery speed and developer workflows through automation and modern tooling.