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/vcon-dev/vcon-mcp/claude-mdgit clone --depth 1 https://github.com/vcon-dev/vcon-mcpWhat 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 | $0.03232 | $0.03232 |
| Opus 5 | $0.01616 | $0.01616 |
| Sonnet 5 | $0.00646 | $0.00646 |
| Haiku 4.5 | $0.00323 | $0.00323 |
Grade A, and why
vcon-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 2d 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 — 369 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code Instructions for vCon MCP Server
This document provides comprehensive instructions for coding agents working with the vCon MCP Server codebase.
Project Overview
This is an MCP (Model Context Protocol) server for managing vCon (Virtual Conversation) data stored in Supabase. vCon is an IETF standard (draft-ietf-vcon-vcon-core-02, spec version 0.4.0) for representing conversation data.
Key Technologies:
- TypeScript
- MCP SDK (
@modelcontextprotocol/sdk) - Koa v3 (
koa,@koa/router) for REST API - Supabase (PostgreSQL)
- Zod for validation
Critical IETF Spec Compliance
Analysis Object - MUST READ
// CORRECT
interface Analysis {
type: string;
vendor: string; // REQUIRED - not optional!
schema?: string; // CORRECT field name
body?: string; // String type (not object)
encoding?: 'base64url' | 'json' | 'none';
}
// WRONG - DO NOT USE
interface AnalysisWrong {
schema_version?: string; // WRONG - use 'schema'
vendor?: string; // WRONG - vendor is required
body?: object; // WRONG - body is string
}
Field Name Corrections (spec -02 / v0.4.0)
| Wrong | Correct | Notes |
|---|---|---|
schema_version |
schema |
Analysis object field |
vendor?: string |
vendor: string |
Required in Analysis |
body: object |
body: string |
JSON.stringify objects before storing |
mimetype |
mediatype |
dialog, analysis, attachments (since v0.0.2) |
appended |
amended |
vCon top-level (renamed in v0.4.0) |
must_support |
critical |
vCon top-level (renamed in v0.4.0) |
session_id: string |
session_id: {local, remote} |
Dialog (changed in v0.4.0) |
Import note: Real-world vCon files (e.g. Strolid) may use v0.0.1 field names (mimetype, appended, must_support). The import script handles both old and new field names transparently.
Encoding Field
- Valid values:
'base64url','json','none' - NO default value - must be explicitly set
- Applied to: Dialog, Analysis, Attachment objects
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.
- 2d ago First seen · 369 lines · 3,232 tokens per session scan A 380ffe53341d
vcon-mcp CLAUDE.md is an instructions file published in the GitHub repository vcon-dev/vcon-mcp (4 stars, last pushed 5d ago), licensed MIT. It adds 3,232 tokens to every session, about $0.0162 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
skills AGENTS.md
Instructions for qdrant/skills, covering qdrant skills, project overview, project structure, navigating skills locally and conventions.
seekstone CLAUDE.md
Instructions for shaqmughal/seekstone, covering claude.md, what this repo is, commands, the harness itself (run after npm install) and architecture.
marklogic-mcp CLAUDE.md
Instructions for tternquist/marklogic-mcp, covering marklogic mcp — agent working instructions, core principle: problem-first thinking, where guidance lives — skills first, agent skills (.claude/skills/ /skill.md) and marklogic://instructions resource (src/resources/index.ts).
plan-forge database.instructions.md
Database patterns for .NET — Dapper/EF Core, parameterized queries, migration strategy.
creditkarma-mcp CLAUDE.md
Claude Code instructions for chrischall/creditkarma-mcp, covering creditkarma-mcp, commands, tool naming, architecture and auth resolution (pattern a template).
copilot-instructions database.instructions.md
Instructions for ThiagoGuislotti/copilot-instructions, covering schema design, normalization, cartesian explosion, parameter sniffing and query performance.