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/alpayc/mcp-migration-check/agents-mdgit clone --depth 1 https://github.com/AlpayC/mcp-migration-checkWrote 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/alpayc/mcp-migration-check/agents-md)<a href="https://agentmods.dev/instructions/alpayc/mcp-migration-check/agents-md"><img src="https://agentmods.dev/badge/instructions/alpayc/mcp-migration-check/agents-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 | $0.00741 | $0.00741 |
| Opus 5 | $0.00370 | $0.00370 |
| Sonnet 5 | $0.00148 | $0.00148 |
| Haiku 4.5 | $0.00074 | $0.00074 |
Grade A, and why
mcp-migration-check AGENTS.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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working in this repository
Read this before changing anything. It is short, and the parts that look pedantic are the ones that have already gone wrong once.
Shape
One rule engine, two consumers. packages/core is pure and deterministic; it
never reaches the network or the disk from inside a rule. Probing an endpoint
and scanning a repository both produce a normalized RuleContext, and rules
only read that.
packages/core the engine — rules · probe · scan · SSRF guard
packages/core/test node:test suite, no network, no disk
skill/mcp-migration SKILL.md + a generated copy of the engine
web Next.js demo on Cloudflare Workers over the same core
Rules that are not negotiable
skill/mcp-migration/scripts/mcpcheck.mjs is generated. Never edit it by
hand. It is an esbuild bundle of packages/core, produced by
npm run build:skill and committed so the skill works without an install. If
you change the engine, rebuild it in the same commit — CI fails otherwise, and
a stale bundle means the skill and the web demo disagree about the rules while
both look healthy in isolation.
Every specRef must be a URL you have opened. All seven originally pointed
at …/2026-07-28#lifecycle and similar anchors that do not exist; the spec is
split across subpages, so each link silently landed on the overview page. A
test now rejects any specRef containing #.
Verify claims about the ecosystem against the ecosystem, not against
memory. MCP007 once advised upgrading @modelcontextprotocol/sdk to ^2 and
running a codemod. That package has never published a 2.x — v2 shipped as a
rename to @modelcontextprotocol/server and /client. Check npm and the spec
before writing a fix string. See the README section "A rule that was wrong".
Before you say it works
npm run typecheck # core + tests + (separately) web
npm test # 119 assertions
npm run build:skill # then check git status is clean
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 · 71 lines · 741 tokens per session scan A e896ae497dbc
mcp-migration-check AGENTS.md is an instructions file published in the GitHub repository AlpayC/mcp-migration-check (5 stars, last pushed 5d ago), licensed MIT. It adds 741 tokens to every session, about $0.0037 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 AGENTS.md
AGENTS.md instructions for cloudflare/mcp, covering agents.md, project overview, mcp specification compliance, repository structure and setup.
mcp CLAUDE.md
Claude Code instructions for cloudflare/mcp, a project described as: MCP server for the Cloudflare API.
halans-mcp-server CLAUDE.md
Claude Code instructions for halans/halans-mcp-server, covering claude.md - mcp server project guide, project overview, project structure, key dependencies and available tools.
evlife-mcp-server CLAUDE.md
Claude Code instructions for halans/evlife-mcp-server, covering claude.md - mcp server project guide, project overview, project structure, key dependencies and available tools.
cloudflare-workers-nextjs-saas-template AGENTS.md
AGENTS.md instructions for LubomirGeorgiev/cloudflare-workers-nextjs-saas-template, covering project context, vinext, general coding rules, control flow and comments.
claude-skills CLAUDE.md
Claude Code instructions for jezweb/claude-skills, covering claude skills, philosophy, directory structure, plugin anatomy (anthropic spec) and adding a new plugin.