Borrowing it
Nothing to install: this file belongs to hqhq1025/clipaste. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/hqhq1025/clipaste/main/AGENTS.mdgit clone --depth 1 https://github.com/hqhq1025/clipasteWrote 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/instructions/hqhq1025/clipaste/agents-md)<a href="https://agentmods.dev/instructions/hqhq1025/clipaste/agents-md"><img src="https://agentmods.dev/badge/instructions/hqhq1025/clipaste/agents-md/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/instructions/hqhq1025/clipaste/agents-md"><img src="https://agentmods.dev/badge/instructions/hqhq1025/clipaste/agents-md.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 | $0.02110 | $0.02110 |
| Opus 5 | $0.01055 | $0.01055 |
| Sonnet 5 | $0.00422 | $0.00422 |
| Haiku 4.5 | $0.00211 | $0.00211 |
Grade A, and why
clipaste AGENTS.md 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 9d 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.
it is 9 MB of RAM and a handful of syscalls. HTTP is `curl`; JSON output is How it starts
The opening of the file, as written. The whole thing — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Instructions for coding agents working with clipaste — both installing it for a user and contributing to this repository.
clipaste is a clipboard daemon that makes screenshot paste work in terminal AI tools (Claude Code, Codex CLI, Cursor CLI), locally and across SSH/WSL2 boundaries.
Part 1 — Installing clipaste for a user
The one command that tells you what to do
clipaste doctor --json
This is the entry point. It classifies the machine, runs the checks that are
meaningful for that machine, and returns a fix command for anything broken.
Do not guess at the state of a clipaste install — ask doctor.
{
"version": "2.4.1",
"os": "macos",
"role": "clipboard-host",
"status": "warn",
"checks": [
{
"name": "daemon",
"status": "ok",
"detail": "daemon responding on 127.0.0.1:18340",
"fix": null
},
{
"name": "clipboard",
"status": "warn",
"detail": "no image staged yet — take a screenshot, then re-run doctor",
"fix": null
}
]
}
| Field | Contract |
|---|---|
role |
clipboard-host / ssh-remote / wsl2 — decides which checks apply |
status |
worst of all checks: ok, warn, fail |
checks[].status |
ok / warn / fail |
checks[].fix |
a literal command to run, or null |
| exit code | 0 usable (ok or warn), 1 broken, 2 bad arguments |
A warn is not a failure. "No screenshot on the clipboard yet" is the normal
state of a freshly installed machine — do not report it to the user as a
problem, and do not try to fix it.
Decide where you are before installing anything
clipaste has two sides and they install differently. Getting this wrong is the single most common mistake.
the machine holding the clipboard the machine running the agent
(where you press Cmd+Shift+4) (where Claude Code runs)
───────────────────────────── ─────────────────────────────
macOS / Windows ──HTTP──► same machine
SSH remote
runs the daemon WSL2 distro
install: brew / install.ps1 install: run setup FROM the
clipboard host, not here
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.
- 9d ago First seen · 226 lines · 2,110 tokens per session scan A 5885ea19e957
clipaste AGENTS.md is an instructions file published in the GitHub repository hqhq1025/clipaste (54 stars, last pushed yesterday), licensed MIT. It adds 2,110 tokens to every session, about $0.0106 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 2026-08-30.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.