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/okeefeco/pyeye-mcp/claude-mdgit clone --depth 1 https://github.com/okeefeco/pyeye-mcpWrote 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/okeefeco/pyeye-mcp/claude-md)<a href="https://agentmods.dev/instructions/okeefeco/pyeye-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/okeefeco/pyeye-mcp/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 | $0.00520 | $0.00520 |
| Opus 5 | $0.00260 | $0.00260 |
| Sonnet 5 | $0.00104 | $0.00104 |
| Haiku 4.5 | $0.00052 | $0.00052 |
Grade A, and why
pyeye-mcp 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PyEye Server - Claude Instructions
This file loads modular Claude behavior instructions. The actual instructions are in .claude/instructions/.
🎯 CRITICAL: First, Understand the Documentation System
@.claude/instructions/00-documentation-system.md
Core Behavior and Rules
@.claude/instructions/01-core-rules.md @.claude/instructions/02-session-startup.md
Development Workflows
@.claude/instructions/05-workflow-issues.md @.claude/instructions/06-workflow-commits.md @.claude/instructions/07-validation.md @.claude/instructions/11-pr-requirements.md
Required Development Practices
@.claude/instructions/03-mcp-dogfooding.md @.claude/instructions/04-agent-triggers.md
Tools and Utilities
@.claude/instructions/09-task-management.md @.claude/instructions/10-cross-platform.md
Project-Specific Configuration
@.claude/instructions/08-project-specific.md
GitHub Labels Reference
@docs/LABELS.md
This file defines the GitHub label system you MUST use when creating issues, PRs, or suggesting labels.
Optional Human Documentation References
These files contain detailed human documentation that you can reference if needed:
CONTRIBUTING.md- Detailed setup guides, explanations, and human-oriented documentation
Note: The mandatory Claude-specific rules from CONTRIBUTING.md have been extracted to appropriate instruction files
Optional User-Specific Configuration
For personal development settings (worktrees, local paths, etc.):
@~/.claude/projects/okeefeco/pyeye-mcp.md
This file is optional and ignored if it doesn't exist. It won't be committed to the repository.
Dogfooding Metrics Tracking
To measure our MCP adoption:
# View real-time analytics
mcp-report # 7-day report
mcp-report-month # 30-day report
mcp-logs # Watch live activity
mcp-session # View active session
mcp-errors # Check for hook errors
Metrics tracking is automatic via Claude Code hooks. See scripts/claude_hooks/README.md for details.
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 · 77 lines · 520 tokens per session scan A 67e952f7ca5e
pyeye-mcp CLAUDE.md is an instructions file published in the GitHub repository okeefeco/pyeye-mcp (0 stars, last pushed 4d ago), licensed MIT. It adds 520 tokens to every session, about $0.0026 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
mcp-server copilot-instructions.md
Instructions for ALCops/mcp-server, covering copilot instructions, build, build (requires bc devtools dlls, see below), run tests and pack as .net global tool.
sonde AGENTS.md
AGENTS.md instructions for anishmoncivarghese/sonde, covering project history, recording decisions, handing off active work, sonde and picking up this project (any agent, any vendor).
flyto-indexer AGENTS.md
AGENTS.md instructions for flytohub/flyto-indexer, covering agent rules, gate remediation loop, flyto2 project memory contract and flyto2 frontend quality gate.
flyto-indexer CLAUDE.md
Claude Code instructions for flytohub/flyto-indexer, covering claude notes, cross-agent handoff, shared code intelligence, code intelligence (flyto-indexer) and first-time setup.
sonde CLAUDE.md
Claude Code instructions for anishmoncivarghese/sonde, a project described as: Local code-context engine for AI coding agents: structural answers within a token budget.
cctx-mcp AGENTS.md
AGENTS.md instructions for nikondrat/cctx-mcp, covering code context — ai agent guide, mandatory: use these tools first, tool naming, priority rules and tool selection hierarchy (cctx > subagent > native).