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 mostafa-drz/claude-skills --skill clean-copygit clone --depth 1 https://github.com/mostafa-drz/claude-skillsWrote 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/mostafa-drz/claude-skills/clean-copy)<a href="https://agentmods.dev/skills/mostafa-drz/claude-skills/clean-copy"><img src="https://agentmods.dev/badge/skills/mostafa-drz/claude-skills/clean-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/mostafa-drz/claude-skills/clean-copy"><img src="https://agentmods.dev/badge/skills/mostafa-drz/claude-skills/clean-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 | $0.00122 | $0.03233 |
| Opus 5 | $0.00061 | $0.01617 |
| Sonnet 5 | $0.00024 | $0.00647 |
| Haiku 4.5 | $0.00012 | $0.00323 |
Grade A, and why
clean-copy 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 today.
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 — 256 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clean Copy
Clean a draft from the conversation (or a pasted/file source) and copy it to the clipboard, formatted for a specific platform. The goal: a paste that looks right in Gmail / Slack / LinkedIn on the first try, with zero manual cleanup.
Preferences
Before starting, use the Read tool to read
~/.claude/skills/clean-copy/preferences.md. If the file does not exist, treat
as "no preferences set" and use defaults below.
Defaults:
- default-platform:
gmail - default-source:
last(most recent assistant draft in the conversation) - reflow-paragraphs:
true(rewrap soft-wrapped paragraphs into single lines) - bullet-style:
-(preserve as-is) - preview-after-copy:
true(show first 12 lines + char count)
Command routing
Check $ARGUMENTS:
help→ display help, stopconfig→ interactive setup, stopreset→ delete~/.claude/skills/clean-copy/preferences.md, confirm, stop- anything else (including empty) → run the skill
Help
Clean Copy — Clean terminal-formatted text and copy to clipboard for a target platform
Usage:
/clean-copy <platform> Clean latest draft, format, pbcopy
/clean-copy Use default platform from preferences
/clean-copy config Set defaults (default platform, reflow, etc.)
/clean-copy reset Clear preferences
/clean-copy help This help
Platforms:
gmail Plain prose, bullets as "- ", no markdown rendering
slack Slack mrkdwn: *bold*, _italic_, `code`, > quotes
linkedin Plain prose, no markdown (LinkedIn strips it), short paragraphs
plain Strip all markdown, just clean prose
markdown Preserve markdown, only clean terminal whitespace
Options:
--source last Latest assistant draft in conversation (default)
--source paste Prompt the user to paste the source text
--source file:<path> Read source from a file
--no-reflow Keep hard line breaks as-is (don't unwrap paragraphs)
--preview Show full cleaned text before copying
Examples:
/clean-copy gmail Clean my last draft for Gmail compose
/clean-copy slack Format for Slack mrkdwn
/clean-copy linkedin --no-reflow Keep my line breaks (poetry / structured posts)
/clean-copy plain --source paste I'll paste the messy text after invocation
/clean-copy markdown --source file:/tmp/draft.md
Current preferences:
(loaded from preferences.md, or defaults shown above)
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.
- today Changed · +3 lines 4ef27e3b0f48
- 12d ago First seen · 253 lines · 122 tokens per session scan A 332f4e5ec370
clean-copy is a skill published in the GitHub repository mostafa-drz/claude-skills (4 stars, last pushed today), licensed MIT. It adds 122 tokens to every session and 3,233 once invoked, about $0.0006 per session on Opus 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
hydra
Fan multiple independent tasks out to SEPARATE Terminal.app windows, each running its own live claude session with exactly the context it needs — real parallel sessions with isolated context windows, not subagents. Confirms grouping/model/risk with the user before launching, delivers context invisibly, auto-tiles…
shipkit-work-memory
Log session progress and save resume state. Infers from conversation and git. Triggers: 'log progress', 'session summary', 'checkpoint', 'save progress', 'end session'.
session-update
Use when the user says "update session", "log progress", "checkpoint session", or invokes /session-update — especially before /clear or handoff.
interview-kit-builder
Generate a complete structured interview kit for a role — 3-5 role-specific competencies, one behavioral (STAR-format) question per competency, 1-5 scoring rubric with explicit behavioral anchors at each level, per-panel scorecards, interviewer debrief template.
codex-symphony
Install and operate a portable OpenAI Symphony + Linear orchestration setup in any Git repository. Use when the user wants a one-command local Symphony runner, a reusable WORKFLOW template, background launch scripts, or a Codex wrapper that restarts Symphony automatically when reopening the CLI.
claudeshrink
Automatically compress large natural text or log files before processing. Trigger when the user pastes massive text blobs, or asks to analyze a large file (logs, docs, transcripts), or provides a prompt that is too large for the context window. DO NOT trigger on source code files or structural data (JSON, XML).