1msg-mcp: Instructions file for Codex

AGENTS.md

1msg-mcp AGENTS.md is an instructions file for Codex, OpenCode from 1msg/1msg-mcp. It costs 577 tokens per session, scanned A, original, MIT.

Repository instructions for the 1msg/1msg-mcp project, covering its Node.js version, package boundaries, installation, hooks, and quality checks. They guide coding agents working in that repository.

In plain words
What is it for?
Use them when modifying the repository so installs, imports, configuration, comments, and validation follow the project's stated conventions.
Why use it?
They give an agent the project's rules before it changes code, helping preserve public entry points, dependency boundaries, and required checks.

Instructions file for CodexOpenCode

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

This is 1msg/1msg-mcp's own configuration. It tells Codex and OpenCode how to work on 1msg-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 1msg-mcp configures →

Reuse

Borrowing it

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

README.md
[![agentmods](https://agentmods.dev/badge/instructions/1msg/1msg-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/1msg/1msg-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/1msg/1msg-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/1msg/1msg-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 1msg-mcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/1msg/1msg-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/1msg/1msg-mcp/agents-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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00577 $0.00577
Opus 5.5 $0.00231 $0.00231
Sonnet 5.5 $0.00115 $0.00115
Haiku 4.5 $0.00058 $0.00058

Measured 4d ago against content hash bf892f985205, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

1msg-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 4d 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 · 18 lines

What it actually says

Quality and ownership

Profile A, Node 24.22.2. SDK/tooling maintainers own this repository. The public package entrypoints are defined in package.json; framework registration and executable consumers must remain intact. Imports must be acyclic at runtime, production cannot import tests, and dependency boundaries are enforced in .dependency-cruiser.cjs. quality.config.mjs is the source inventory and exact generated-path declaration.

Configuration belongs in the existing config/bootstrap adapters; pure conversion/validation helpers must not gain transport or environment reads. SDK and HTTP calls belong in the existing transport/client adapters. Keep complete scenarios readable at their application entrypoints; avoid pass-through facade layers. Comments on new/changed functions describe purpose, inputs/results, invariants and relevant failure/resource ownership. Check comments against behavior rather than repeating the function name.

Install with the frozen lockfile, then pnpm --dir tools/quality --ignore-workspace install --lockfile-dir "$PWD/quality/tooling" --frozen-lockfile --ignore-scripts. Run pnpm run hooks:install for local Husky/lint-staged feedback. Run all commands listed in .github/workflows/quality.yml before review: formatter, static and typed ESLint, strict production/test typecheck, dependency-cruiser, both Knip graphs, jscpd runtime gate and full report, complexity, guard negative fixtures, tests, build and packed-entrypoint smoke. No CI skip variable disables typed lint.

Historical debt is recorded per finding in quality/baselines, with adoption SHA, evidence, owner, issue and expiry. Initial allowances are replayed against the default branch; new findings and increases are forbidden. Remove entries when fixed. Generated paths have producer provenance; authored tooling is always checked.

The quality-required job fails on failed/skipped/cancelled prerequisites. Configure branch protection to require it; YAML alone does not change server protection. Tests use isolated/local inputs; never point them at production services.

Generated MCP files are owned by the pinned API producer. Run pnpm run test:generated to replay the exact producer against the checksummed public contract and locked SDK declarations, including changed/deleted/ignored-output negative fixtures. Update the producer provenance before deliberately running node quality/mcp/generate.mjs --write; never hand-edit the two generated files.

The strict source program excludes only quality/mcp/vendor/apis/**: these incomplete API snapshots are checksummed generator inputs, not executable modules. test:generated verifies their exact provenance; generated runtime outputs remain in the strict program. All authored TS/TSX/MTS/CTS files remain covered.

Jest uses the strict quality TypeScript program with isolated module compilation for NodeNext. Tests must release their listeners/transports and terminate naturally; forced process exit is not a substitute for cleanup.

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. 4d ago First seen · 18 lines · 577 tokens per session scan A bf892f985205

Subscribe to this mod's changes

1msg-mcp AGENTS.md is an instructions file published in the GitHub repository 1msg/1msg-mcp (0 stars, last pushed 2d ago), licensed MIT. It adds 577 tokens to every session, about $0.0023 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 2026-11-03.

Related

1msg-mcp AGENTS.md compared with instructions from other repositories

1msg-mcp AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
1msg-mcp AGENTS.md1msg/1msg-mcpInstructions file02d agoMITA577Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA2,022GitHub Copilot