MyMCPs: Instructions file for Codex

AGENTS.md

MyMCPs AGENTS.md is an instructions file for Codex, OpenCode from 0xtlt/MyMCPs. It costs 1,370 tokens per session, scanned A, original, MIT.

Project-specific instructions for AI coding agents working on the MyMCPs codebase. They cover changelog updates, command usage, and interface-building workflow.

In plain words
What is it for?
Keeping CHANGELOG.md current, running Astryx commands through pnpm, loading required styles, and discovering suitable interface components before writing UI.
Why use it?
They give the agent rules that are easy to miss when working in this project, helping keep changes consistent and user-visible updates documented.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

This is 0xtlt/MyMCPs's own configuration. It tells Codex and OpenCode how to work on MyMCPs itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything MyMCPs configures →

View source ↗ 0xtlt/MyMCPs
Reuse

Borrowing it

Nothing to install: this file belongs to 0xtlt/MyMCPs. 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/0xtlt/MyMCPs/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/0xtlt/MyMCPs

Made for: Codex, OpenCode.

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.

agentmods badge for MyMCPs AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/0xtlt/mymcps/agents-md/github.svg)](https://agentmods.dev/instructions/0xtlt/mymcps/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/0xtlt/mymcps/agents-md"><img src="https://agentmods.dev/badge/instructions/0xtlt/mymcps/agents-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.

agentmods 80×15 button for MyMCPs AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/0xtlt/mymcps/agents-md"><img src="https://agentmods.dev/badge/instructions/0xtlt/mymcps/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,370 This file is loaded in full into every session.
When invoked 1,370 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01370 $0.01370
Opus 5.5 $0.00548 $0.00548
Sonnet 5.5 $0.00274 $0.00274
Haiku 4.5 $0.00137 $0.00137

Measured 16d ago against content hash b77bfb440c35, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

MyMCPs 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 16d 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.

AGENTS.md · 40 lines

How it starts

The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Project-specific guidance for AI coding agents.

Changelog

  • Keep the root CHANGELOG.md up to date in every pull request that changes user-visible behavior, security, or operations, including dependency and developer-workflow changes that affect users or operators.
  • Before final validation, add concise English entries under the current UTC date (## YYYY-MM-DD), grouped as Added, Changed, Fixed, Security, or Removed.
  • Consolidate related commits into outcome-focused entries. Do not list commit hashes or merge commits, and omit tests and internal refactors unless they affect users or operators.

Pages and design

The server renders its own pages: maud templates in crates/web/src/views, one stylesheet (crates/web/assets/css/app.css) and one script (crates/web/assets/js/app.js), both written by hand and embedded in the binary. There is no JavaScript build and no component library.

  • Read docs/design-system.md before you write or change a page: it lists every component with its markup and class names, the page shell, the data- attributes the script understands, and the protocol of the forms sent without a page load. The design it implements is the Figma file "MyMCP".
  • Compose a page from the components that exist. Add CSS only when no component fits, at the end of app.css, with the --mm-* tokens: no raw colour and no value the tokens already name.
  • The Content-Security-Policy is strict: no inline style attribute, no <style>, no inline script, no asset from another origin. Sizes that depend on data use the classes and data- attributes the design system lists (data-pct, .col-<px>), and charts are SVG drawn by the server.
  • The server does the work and the script only presents it: every list, filter and page is a URL the server renders, and a form sent in the background also answers a plain post with a redirect. Dialogs are the exception: a <dialog> is opened by the script, so the forms that live in one (create, edit, install) need JavaScript, while the actions of a row (revoke, delete, test, enable) do not. So are passkeys, which a browser only makes and uses through its script. Keep it that way: a new page must not need the script for anything but its dialogs and its passkeys.
  • Validate input with a mymcps-vine validator, as the rest of the code does, not with hand-written checks.

Read the full file on GitHub · 40 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.

  1. 16d ago Changed · +61 tokens per session b77bfb440c35
  2. 24d ago Changed · +121 tokens per session ffa401126df0
  3. 25d ago Changed · -20 lines · -201 tokens per session 6f81fd88bf01
  4. 1mo ago Changed · +2 lines · +147 tokens per session 88d8929c92b8
  5. 1mo ago Changed · +18 tokens per session b1e83b4c4aa3
  6. 2mo ago First seen · 58 lines · 1,224 tokens per session scan A 7bd53c90657e

Subscribe to this mod's changes

MyMCPs AGENTS.md is an instructions file published in the GitHub repository 0xtlt/MyMCPs (0 stars, last pushed 4d ago), licensed MIT. It adds 1,370 tokens to every session, about $0.0055 per session on Opus 5.5. 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.

Related

MyMCPs AGENTS.md compared with instructions from other repositories

MyMCPs AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
MyMCPs AGENTS.md0xtlt/MyMCPsInstructions file04d agoMITA1,370Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode