What is verity-mcp CLAUDE.md?

A repository-specific instruction file for a Cloudflare Worker that exposes Verity skill routes as MCP tools. The Worker forwards authenticated requests between an MCP client and the Verity service without storing application data.

Use it when developing or reviewing the Verity MCP proxy, its tool routes, authentication forwarding, production-readiness work, or marketplace manifest.

It documents the project's architecture, tracked work, security requirements, and brand rules so changes fit the existing service design.

How cchurctrip/verity-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to cchurctrip/verity-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/cchurctrip/verity-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/cchurctrip/verity-mcp

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/cchurctrip/verity-mcp/claude-md.svg)](https://agentmods.dev/instructions/cchurctrip/verity-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/cchurctrip/verity-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/cchurctrip/verity-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 1,279 This file is loaded in full into every session.

When invoked 1,279 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.01279	$0.01279
Opus 5	$0.00639	$0.00639
Sonnet 5	$0.00256	$0.00256
Haiku 4.5	$0.00128	$0.00128

Measured 7d ago against content hash ccddee4049d1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

verity-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 7d 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.

CLAUDE.md · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

verity-mcp project context

What this repo is

Sibling repo to cchurctrip/verity. Hosts a Cloudflare Worker that exposes Verity's skill routes as MCP (Model Context Protocol) tools at mcp.verityskills.com.

Worker is a thin bearer-token proxy. Zero state. Zero DB credentials. No upfront auth validation. Translates Authorization: Bearer vtk_* (MCP client side) into x-verity-key: vtk_* (parent repo skill route side). Forwards request bodies byte-identical. Forwards responses verbatim except for injecting an absolute upgrade_url on 402 TRIAL_CAP_REACHED bodies.

Story tracking

VRT-146a (in-progress): this repo's scaffold + Worker + 6 tools + manifest.json. Spec at verity/mydocs/specs/2026-05-13_VRT-146a_mcp_worker.md.
VRT-146b (pending): full 8-gate production-readiness bootstrap on this repo (SAST, Renovate, OSV-Scanner, threat model, perf budget).
VRT-146c (done): main-repo synthetic-smoke cron + runbook (lives in cchurctrip/verity).
VRT-148 (pending): marketplace submissions consuming the locked manifest.json schema.

Production-readiness gate posture

Per the parent spec's gate-applicability matrix (VRT-146a Phase 1 vs VRT-146b Phase 1):

Gate 1 (SAST: Semgrep + CodeQL): deferred to VRT-146b.
Gate 2 (Dep/CVE scan): deferred to VRT-146b. Renovate + Dependabot + OSV not yet wired.
Gate 3 (Migrations): N/A. Zero DB access in this Worker.
Gate 4 (Property-based tests): in scope. Three targets: bearer regex, upgrade_url rewrite predicate, JSON-RPC envelope validator.
Gate 5 (Synthetic smoke): wired in main repo VRT-146c at app/api/cron/mcp-synthetic-smoke/route.ts. Pings mcp.verityskills.com/health every 5 minutes behind MCP_HEALTH_EXPECTED env flag in the parent repo. Owner flips the flag after DNS propagation.
Gate 6 (Performance budget): replaced. Lighthouse doesn't apply to a JSON-RPC Worker. Replaced with cold-start <150ms p50 + p99 <500ms in docs/performance-budget.md (deferred to VRT-146b).
Gate 7 (Threat model): deferred to VRT-146b. THREAT_MODEL.md with STRIDE for the bearer-auth-proxy surface.
Gate 8 (Feature flags / kill switch): in scope. MCP_KILL_SWITCH (global) + MCP_TOOLS_DISABLED (per-tool, comma-separated) as Wrangler secrets.

Read the full file on GitHub · 57 lines

Changes

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.

7d ago First seen · 57 lines · 1,279 tokens per session scan A ccddee4049d1

Subscribe to this mod's changes

verity-mcp CLAUDE.md is an instructions file published in the GitHub repository cchurctrip/verity-mcp (0 stars, last pushed 2d ago), licensed MIT. It adds 1,279 tokens to every session, about $0.0064 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.

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

verity-mcp: Instructions file for Claude Code