What is dev-io-mcp CLAUDE.md?

Project instructions for a Kubernetes-hosted TypeScript MCP server that turns Claude or Codex conversation results into Markdown posts stored on persistent disk. Markdown is plain text formatted with simple symbols for headings and links.

For developing and publishing conversation-based posts, following repository rules, validating generated files, and handling optional DEV.to publishing.

They define a safer publishing process, including removing secrets, checking proposed content, and distinguishing a local file from a confirmed DEV.to publication.

How amirtaherkhani/dev-io-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to amirtaherkhani/dev-io-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/amirtaherkhani/dev-io-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/amirtaherkhani/dev-io-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/amirtaherkhani/dev-io-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/amirtaherkhani/dev-io-mcp/claude-md)

Your own site

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

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/amirtaherkhani/dev-io-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/amirtaherkhani/dev-io-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 577 This file is loaded in full into every session.

When invoked 577 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	$0.00577	$0.00577
Opus 5	$0.00289	$0.00289
Sonnet 5	$0.00115	$0.00115
Haiku 4.5	$0.00058	$0.00058

Measured 8d ago against content hash 1c320c63b049, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

dev-io-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 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.

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 · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Purpose

This repository contains a Kubernetes-hosted TypeScript MCP server for converting Claude or Codex conversation results into Markdown posts under PVC-backed posts/ storage.

Working rules

Read AGENTS.md and the applicable file in skills/ before editing.
Inspect the worktree before changing files. Preserve changes that are not part of the current task.
Use apply_patch for manual edits.
Keep TypeScript strict and keep generated dist/ output out of source edits.
Keep MCP responses deterministic and return useful file names, timestamps, and metrics.

Publishing workflow

Extract the useful outcome from the conversation.
Redact secrets and private data.
Prepare a concise title, summary, topic, source, and tags.
Show or validate the proposed content before calling publish_post when the host supports confirmation.
Confirm the resulting Markdown file under posts/.

The publish_post tool writes to Kubernetes-backed storage and can optionally publish to DEV.to when DEV_TO_PUBLISH=true is configured. Do not imply that a website post was created without a verified remote API response.

DEV.to publishing is a separate explicit opt-in through DEV_TO_PUBLISH=true. It targets the official DEV.to/Forem article API, not an assumed dev.io API.

Runtime

Kubernetes only: Streamable HTTP behind Traefik at https://dev-io-mcp.dev.local/mcp.
The Dockerfile is an image-build input for Kubernetes, not a local runtime.

The HTTP deployment must retain /healthz, /readyz, and /mcp.

MCP and logging

The public tool names and resource URIs are documented in AGENTS.md. Do not write diagnostics with console.log; stdout carries MCP protocol messages. Use stderr instead.

Checks

npm run lint
npm run build

For tool or resource changes, run an MCP initialization and tools/list smoke test. Clean up temporary posts and metrics after testing.

Relevant skills

skills/conversation-to-post/SKILL.md
skills/mcp-server-maintenance/SKILL.md
skills/metrics-adapter/SKILL.md
skills/verify-mcp-server/SKILL.md
skills/runtime-modes/SKILL.md
skills/dev-io/SKILL.md

Read the full file on GitHub · 60 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.

8d ago First seen · 60 lines · 577 tokens per session scan A 1c320c63b049

Subscribe to this mod's changes

dev-io-mcp CLAUDE.md is an instructions file published in the GitHub repository amirtaherkhani/dev-io-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 577 tokens to every session, about $0.0029 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.

Claude Code ai-agents codex content-publishing devto forem

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.

vercel/next.js · 7,296 tokens

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

dev-io-mcp: Instructions file for Claude Code