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/vladolaru/claude-code-pluginsWrote 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/vladolaru/claude-code-plugins/copy-as)<a href="https://agentmods.dev/commands/vladolaru/claude-code-plugins/copy-as"><img src="https://agentmods.dev/badge/commands/vladolaru/claude-code-plugins/copy-as/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/vladolaru/claude-code-plugins/copy-as"><img src="https://agentmods.dev/badge/commands/vladolaru/claude-code-plugins/copy-as.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 | $0.00028 | $0.03568 |
| Opus 5 | $0.00014 | $0.01784 |
| Sonnet 5 | $0.00006 | $0.00714 |
| Haiku 4.5 | $0.00003 | $0.00357 |
Grade A, and why
copy-as 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 7d 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 — 323 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a format-aware clipboard tool. You convert content to the target format and copy it to the system clipboard. Do what is asked; nothing more, nothing less.
Step 1: Identify Target Format, Then Extract Content
Arguments: $ARGUMENTS
Before extracting content, determine the target format — it controls how you process everything downstream.
Target format — scan arguments for a destination keyword:
slackorfor slackormrkdwn→ Slack mrkdwnp2orfor p2orgutenbergorwordpress→ P2/Gutenberg HTMLmarkdown,md, or nothing specified → Standard markdown (default)
Content source — one of:
- Inline text in the arguments
- A conversation reference (e.g., "the summary above", "that code block")
- A file path to read
If the content reference is ambiguous, ask the user to clarify.
Step 2: Prepare Content
Extract the content. If it comes from a file, read it. If it references conversation context, locate and extract the relevant portion.
Default to human-readable form. Unless the user explicitly asks for raw output (JSON, code, logs, tool output), extract the prose or structured representation that a person would read — not the underlying data. If both exist (e.g., a summary and a JSON payload), copy the summary.
PR descriptions, review comments, and similar dual-audience content
Exception to the default above. PR content serves two audiences with different needs: human reviewers who need a quick scannable recap, and future AI sessions that benefit from rich context. Human reviewers won't read walls of text; AI sessions need detail to work effectively. Serve both by structuring content:
1. Lead with a human recap — 3-5 short bullets covering what changed, why, and anything the reviewer should pay attention to. This is the part a human actually reads. Keep it under ~100 words.
2. Follow with detailed context — Below a --- separator (or a <details> block), include the richer description: implementation approach, trade-offs, affected areas, test coverage notes. This section serves future AI sessions and thorough reviewers.
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.
- 7d ago First seen · 323 lines · 28 tokens per session scan A 9906b3114edc
copy-as is a command published in the GitHub repository vladolaru/claude-code-plugins (8 stars, last pushed today), licensed MIT. It adds 28 tokens to every session and 3,568 once invoked, about $0.0001 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 2026-09-03.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.