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 harleensahni/copy-to-clipboard-plugin --skill copygit clone --depth 1 https://github.com/harleensahni/copy-to-clipboard-pluginWrote 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/harleensahni/copy-to-clipboard-plugin/copy)<a href="https://agentmods.dev/skills/harleensahni/copy-to-clipboard-plugin/copy"><img src="https://agentmods.dev/badge/skills/harleensahni/copy-to-clipboard-plugin/copy/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/harleensahni/copy-to-clipboard-plugin/copy"><img src="https://agentmods.dev/badge/skills/harleensahni/copy-to-clipboard-plugin/copy.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 | $0.00119 | $0.01211 |
| Opus 5 | $0.00060 | $0.00606 |
| Sonnet 5 | $0.00024 | $0.00242 |
| Haiku 4.5 | $0.00012 | $0.00121 |
Grade A, and why
copy scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- A long URL or a curl invocation carrying credentials How it starts
The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copy to clipboard
Two modes
Mode A — proactive (skill auto-applied while constructing a response)
Trigger: your response is about to include text the user will need to paste somewhere external. Examples:
- A PromQL / LogQL / SQL query for Grafana Explore
- A shell command they should run themselves (NOT via the Bash tool)
- A config snippet for a file they edit by hand
- A JavaScript snippet they'll paste into the browser devtools console
- A long URL or a curl invocation carrying credentials
Action:
- Show the text inline first — code-fenced as usual — so they can read it before deciding.
- After the response body, use
AskUserQuestionwith one short question:"Copy <one-line description> to clipboard?" Options:
Yes/No thanks. Single-select. No multiSelect, no preview. - On
Yes, run via Bash (quoted heredoc — keeps$variablesand`backticks`from shell-expanding):cat <<'PBCOPY_EOF' | "${CLAUDE_SKILL_DIR}/scripts/copy.sh" <verbatim content> PBCOPY_EOF - Confirm afterwards in one short line:
Copied.If the helper exited non-zero it printed an install hint on stderr — relay that instead of claiming success. - On
No, do nothing further. Don't re-ask this turn.
If a response has multiple distinct copyable blocks, batch into ONE AskUserQuestion: Copy A / Copy B / Copy both / Copy none — not one prompt per block.
Mode B — user-invoked (the user typed /clipboard:copy ...)
Trigger: you see a <command-name>copy</command-name> tag in the current turn, OR the user's message text starts with /clipboard:copy. Args (the text after the command name) name a specific target; absence of args means "best-effort from the previous response."
Action — SKIP the confirmation. Copy immediately:
- No args (
/clipboard:copy): pick the most recent block in your previous response that was a copy candidate (code-fenced PromQL / shell command / config snippet / etc.). If multiple, pick the largest / most prominent block. - Args (e.g.
/clipboard:copy the sql queryor/clipboard:copy the PromQL): find the block in recent context (this turn or the last few responses) that matches the description and copy that one. - Ambiguous match (the description fits multiple blocks): copy the most recent one and mention in the confirmation line which one you picked, so they can re-issue if you guessed wrong.
- No matching block found: tell the user briefly that there's nothing matching to copy. Don't fabricate.
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.
- 11d ago First seen · 96 lines · 119 tokens per session scan A 36da4093701d
copy is a skill published in the GitHub repository harleensahni/copy-to-clipboard-plugin (1 stars, last pushed 1mo ago), licensed MIT. It adds 119 tokens to every session and 1,211 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
i-have-adhd
Shape output for a reader with ADHD: lead with the next action, number multi-step work, restate state across turns, suppress tangents, give specific time estimates, make wins visible. Invoke with /i-have-adhd; stays on until "stop adhd mode".
my-adhd-caveman
Self-contained output mode: ADHD actable structure (action first, numbered steps, one next action, one-line progress) plus caveman diction (drop fluff/articles, fragments, fewer tokens). Use when the user says "adhd-caveman", "my-adhd-caveman", or invokes /my-adhd-caveman. Needs no other skills.
build-guard
Use when implementing features, refactors, or multi-file changes. Orchestrated plan-then-execute with subagent dispatch and regression checkpoints.
gog
Use the gog CLI for the user's Google account ([email protected]): Gmail search/read, Calendar create/edit, Contacts edit/create, Tasks create/edit. Use when the user asks about email, inbox, calendar events, meetings, contacts, or tasks. Scope is intentionally light: queries and edits only — never delete…
i-have-adhd
Shape output for a reader with ADHD: lead with the next action, number multi-step work, restate state across turns, suppress tangents, give specific time estimates, make wins visible. Invoke with /i-have-adhd; stays on until "stop adhd mode".
service-desk
Runs the IT service desk — intake, triage, prioritization, escalation, knowledge, and the metrics that improve service rather than distort it. Use this to set up or fix a service desk, design ticket priority and escalation, reduce repeat contacts, structure a knowledge base, or work out why a desk hitting its targets…