add-mcp: Instructions file for Codex

AGENTS.md

add-mcp AGENTS.md is an instructions file for Codex, OpenCode from neon-solutions/add-mcp. It costs 629 tokens per session, scanned A, original, Apache-2.0.

Project instructions for add-mcp, a command-line tool that installs MCP servers for several AI coding tools. MCP servers provide coding agents with access to external tools or data.

In plain words
What is it for?
Developing, testing, documenting, and releasing the command-line installer.
Why use it?
They define the development workflow, testing expectations, release notes, and versioning rules needed to change the tool safely.

Instructions file for CodexOpenCode

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

This is neon-solutions/add-mcp's own configuration. It tells Codex and OpenCode how to work on add-mcp 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 add-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to neon-solutions/add-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/neon-solutions/add-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/neon-solutions/add-mcp

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 add-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/neon-solutions/add-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/neon-solutions/add-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/neon-solutions/add-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/neon-solutions/add-mcp/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 add-mcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/neon-solutions/add-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/neon-solutions/add-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 629 This file is loaded in full into every session.
When invoked 629 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 $0.00629 $0.00629
Opus 5.5 $0.00252 $0.00252
Sonnet 5.5 $0.00126 $0.00126
Haiku 4.5 $0.00063 $0.00063

Measured 2mo ago against content hash 82bd4c6a4906, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

add-mcp 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 2mo 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 · 32 lines

How it starts

The opening of the file, as written. The whole thing — 32 lines — stays where its author put it; the contents beside it link to each section on GitHub.

add-mcp

A CLI to install MCP servers for different coding agents (Claude Code, Cursor, VS Code, OpenCode, Codex, Grok Build) with a single command.

Dev environment

  • Use bun as package manager and to run package.json scripts
  • Fallow is a local dev dependency (bun run fallow). It reports unused code, duplication, and complexity across the repo; fix what matters locally and ignore noise when appropriate. It does not run in GitHub Actions.

Changelog

CHANGELOG.md is for user-facing changes only: new features and bug fixes that affect people using the CLI. Skip internal-only work (tooling, CI, dev dependencies, refactors with no behavior change). When you ship something that belongs in the changelog, add an entry in the same tone as existing ones and bump package.json per semver—often one entry + bump per release batch.

Dev and PR workflow

  1. Branch from up-to-date main — git checkout main && git pull.
  2. Implement the change — keep the diff focused; match existing style and patterns.
  3. Tests — add or extend tests so behavior and edge cases are covered by the spec. Prefer unit tests without mocks and e2e tests without mocks (this repo’s style).
  4. Typecheck — bun run typecheck; fix all reported issues.
  5. Tests — bun run test; fix failures.
  6. Quality pass — run bun run fmt, then bun run build, bun run typecheck, and bun run test again so formatting, build, types, and tests are all green.
  7. Fallow — bun run fallow (or bun run fallow -- --summary). Address findings that are clearly worth it; not every Fallow warning needs a code change.
  8. Release notes — if the change is user-facing (feature or bug fix), add a short CHANGELOG.md entry and bump package.json per semver; otherwise skip the changelog.
  9. README — update only if end users need to know about a new or changed feature.
  10. PR — push your branch and open a pull request against main.

Read the full file on GitHub · 32 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. 2mo ago First seen · 32 lines · 629 tokens per session scan A 82bd4c6a4906

Subscribe to this mod's changes

add-mcp AGENTS.md is an instructions file published in the GitHub repository neon-solutions/add-mcp (321 stars, last pushed 5d ago), licensed Apache-2.0. It adds 629 tokens to every session, about $0.0025 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 2026-08-30.

Related

add-mcp AGENTS.md compared with instructions from other repositories

add-mcp AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
add-mcp AGENTS.mdneon-solutions/add-mcpInstructions file3215d agoApache-2.0A629Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file275k2d agoMITA4,313Codex, OpenCode