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 agentmods add instructions/voxos-ai-inc/clink-mcp-server-python/claude-mdgit clone --depth 1 https://github.com/Voxos-ai-Inc/clink-mcp-server-pythonWrote 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/voxos-ai-inc/clink-mcp-server-python/claude-md)<a href="https://agentmods.dev/instructions/voxos-ai-inc/clink-mcp-server-python/claude-md"><img src="https://agentmods.dev/badge/instructions/voxos-ai-inc/clink-mcp-server-python/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 | $0.01051 | $0.01051 |
| Opus 5 | $0.00526 | $0.00526 |
| Sonnet 5 | $0.00210 | $0.00210 |
| Haiku 4.5 | $0.00105 | $0.00105 |
Grade A, and why
clink-mcp-server-python CLAUDE.md 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 5d 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clink MCP Server (Python) - Development Guide
This is the Python MCP server for Clink, published to PyPI as clink-mcp-server.
Source Location
This code lives in the voxos monorepo at projects/clink/mcp-python/ and is published to:
- GitHub: https://github.com/Voxos-ai-Inc/clink-mcp-server-python
- PyPI: https://pypi.org/project/clink-mcp-server/
Publishing to GitHub
This directory is synced to GitHub using git subtree. The GitHub repo is a mirror of this subdirectory.
First-time setup
# Add the GitHub remote
git remote add github-mcp-python [email protected]:Voxos-ai-Inc/clink-mcp-server-python.git
Publishing changes
After making changes to projects/clink/mcp-python/:
# 1. Commit your changes to the monorepo
git add projects/clink/mcp-python/
git commit -m "feat(mcp-python): your change description"
# 2. Push the subdirectory to GitHub
git subtree push --prefix=projects/clink/mcp-python github-mcp-python main
Or use the make target:
make mcp-python-publish
Important notes
- Always commit to the monorepo first, then push to GitHub
- The GitHub repo's
mainbranch mirrors this directory - Don't edit the GitHub repo directly - changes flow monorepo -> GitHub only
Publishing to PyPI
After pushing to GitHub:
cd projects/clink/mcp-python
# Bump version in pyproject.toml, then:
uv build
uv publish
Or with hatch:
hatch version patch # or minor/major
hatch build
hatch publish
Then commit the version bump to the monorepo and push to GitHub again.
Development
Setup
cd projects/clink/mcp-python
uv venv
source .venv/bin/activate # or .venv\Scripts\activate on Windows
uv pip install -e ".[dev]"
Testing locally with Claude Code
- Update your
~/.claude.jsonto use the local source:
{
"mcpServers": {
"clink": {
"command": "python",
"args": ["-m", "clink_mcp_server"],
"env": {
"CLINK_API_KEY": "sk_live_...",
"CLINK_API_URL": "https://api.stg.clink.voxos.ai",
"PYTHONPATH": "/path/to/voxos/projects/clink/mcp-python/src"
}
}
}
}
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.
- 5d ago First seen · 161 lines · 1,051 tokens per session scan A 26a3071c5d9d
clink-mcp-server-python CLAUDE.md is an instructions file published in the GitHub repository Voxos-ai-Inc/clink-mcp-server-python (1 stars, last pushed 7mo ago), licensed MIT. It adds 1,051 tokens to every session, about $0.0053 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 instructions, from other repositories
wanaku CLAUDE.md
Claude Code instructions for wanaku-ai/wanaku, covering wanaku, core guidelines, quick start, build info and architecture.
moo-tasks AGENTS.md
Instructions for dizlexic/moo-tasks, covering agents.md, 1. what is the moo tasks board?, 2. connecting your agent, 3. available mcp tools and 4. recommended workflow for agents.
wanaku AGENTS.md
AGENTS.md instructions for wanaku-ai/wanaku, a project described as: Wanaku MCP Router.
AgentStack convex.instructions.md
Instructions for ssdeanx/AgentStack, covering convex guidelines, function guidelines, new function syntax, http endpoint syntax and validators.
Next.js Best Practices
This rule provides comprehensive guidance for Next.js development, covering code organization, performance, security, testing, and common pitfalls. It helps developers build robust, scalable, and maintainable Next.js applications by adhering to community-accepted best practices and coding standards.
AgentStack update-docs-on-code-change.instructions.md
Automatically update README.md and documentation files when application code changes require documentation updates.