Borrowing it
Nothing to install: this file belongs to ShunmeiCho/cc-clip. 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/ShunmeiCho/cc-clip/main/CLAUDE.mdgit clone --depth 1 https://github.com/ShunmeiCho/cc-clipWrote 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/shunmeicho/cc-clip/claude-md)<a href="https://agentmods.dev/instructions/shunmeicho/cc-clip/claude-md"><img src="https://agentmods.dev/badge/instructions/shunmeicho/cc-clip/claude-md.svg" alt="Measured on agentmods" 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 | $0.05088 | $0.05088 |
| Opus 5 | $0.02544 | $0.02544 |
| Sonnet 5 | $0.01018 | $0.01018 |
| Haiku 4.5 | $0.00509 | $0.00509 |
Grade C, and why
cc-clip CLAUDE.md scanned grade C with 3 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 8d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
`token.Manager` holds the session in memory. `LoadOrGenerate(ttl)` reuses an unexpired token from disk, or generates a new one. Token file at `~/.cache/cc-clip/session.token` (chmod 600) stores `token\nexpires_at_rfc3339 Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
18. **claude settings hooks** (`internal/shim/settings.go`) — `connect` merges managed Stop and Notification hooks into remote `~/.claude/settings.json` and cleans up legacy wrappers to avoid double delivery. The `~/.loc Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
3. **shim** (`internal/shim/template.go`) — Bash script templates for xclip and wl-paste. Intercepts two specific invocation patterns Claude Code uses, fetches via curl through tunnel, falls back to real binary on any fa How it starts
The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What This Project Does
cc-clip bridges your local Mac/Windows clipboard to a remote Linux server over SSH, so Ctrl+V image paste works in remote Claude Code and Codex CLI sessions. It uses an xclip/wl-paste shim that transparently intercepts only Claude Code's clipboard calls, an X11 selection owner bridge for Codex CLI which reads the clipboard via X11 directly, and an SSH notification bridge that forwards Claude Code hook events (stop, permission prompt, idle) back to the local machine as native notifications.
Claude Code path:
Local Mac clipboard → pngpaste → HTTP daemon (127.0.0.1:18339) → SSH RemoteForward → xclip shim → Claude Code
Codex CLI path (--codex):
Local Mac clipboard → pngpaste → HTTP daemon (127.0.0.1:18339) → SSH RemoteForward → x11-bridge → Xvfb CLIPBOARD → arboard → Codex CLI
Notification path:
Claude Code hook → cc-clip plugin run claude-notify (stdin JSON) → POST /notify via tunnel → classifier → dedup → DeliveryChain → native notification
(fallback when the settings.json merge fails: Claude Code hook → cc-clip-hook → same POST /notify)
Build & Test Commands
make build # Build binary with version from git tags
make test # Run all tests (go test ./... -count=1)
make vet # Run go vet
go test ./internal/tunnel/ -v -run TestFetchImageRoundTrip # Single test
make release-local # Build bare binaries for all platforms (dist/), local testing only
Version is injected via -X main.version=$(VERSION) ldflags. The version variable in cmd/cc-clip/main.go defaults to "dev".
Release Process
Production releases use goreleaser via GitHub Actions (.github/workflows/release.yml). Push a version tag to trigger:
git tag v0.6.0
git push origin v0.6.0
# CI runs: test → contract check → goreleaser → published release with tar.gz + checksums
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.
- 8d ago First seen · 154 lines · 5,088 tokens per session scan C 9c01f8adf4e7
cc-clip CLAUDE.md is an instructions file published in the GitHub repository ShunmeiCho/cc-clip (154 stars, last pushed 9d ago), licensed MIT. It adds 5,088 tokens to every session, about $0.0254 per session on Opus 5. A static security scan graded it C with 3 findings (asks for root, reads agent configuration directories, 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
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).
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.
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.
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.