agentmods.dev

ohmyself: Instructions file for Codex

AGENTS.md

ohmyself AGENTS.md is an instructions file for Codex, OpenCode from juanchoabdon/ohmyself. It costs 504 tokens per session, scanned A, original, MIT.

Repository instructions for ohmyself, including how its server is deployed and which files must be included or excluded.

In plain words
What is it for?
Checking deployment commands, understanding the public proxy and Railway backend, and preparing server or MCP changes.
Why use it?
They prevent deployment mistakes that can cause missing source files or incompatible native dependencies in the production container.

Instructions file for CodexOpenCode

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

This is juanchoabdon/ohmyself's own configuration. It tells Codex and OpenCode how to work on ohmyself 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 ohmyself configures →

not rated 0repo changed 2mo ago A scan 504 tokens original MIT
View source ↗ juanchoabdon/ohmyself
Reuse

Borrowing it

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

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 ohmyself AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/juanchoabdon/ohmyself/agents-md"><img src="https://agentmods.dev/badge/instructions/juanchoabdon/ohmyself/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 504 This file is loaded in full into every session.
When invoked 504 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 $0.00504 $0.00504
Opus 5.5 $0.00202 $0.00202
Sonnet 5.5 $0.00101 $0.00101
Haiku 4.5 $0.00050 $0.00050

Measured 2mo ago against content hash 2b3bcbaa1c9a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ohmyself 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

What it actually says

Agent notes for the ohmyself repo

Deploying (read this before shipping server/MCP changes)

www.ohmyself.ai is the single public origin for all clients (Cursor, ChatGPT, Claude, OAuth). It is a proxy — the real backend is Railway.

  • Deploy server changes to Railway: cd server && railway up --service ohmyself-api --no-gitignore (Railway does not auto-deploy from GitHub today).
  • --no-gitignore is required. Root .gitignore has /versions/ and server/versions/ for runtime version data; Railway's default upload respects .gitignore and can exclude server/src/core/versions/ (the TypeScript source). Without the flag, tsc fails with Cannot find module './versions/types.js'.
  • Don't delete server/.railwayignore. The flag above is all-or-nothing, so it would also upload node_modules, which since sharp carries platform-specific native binaries. Shipping macOS ARM builds to Railway's linux/amd64 container breaks get_media at first use, long after a green deploy. That file excludes node_modules while keeping src/core/versions/.
  • One backend only: Railway. The old Vercel server copy (ohmyself-api.vercel.app) was decommissioned 2026-07-11 — don't recreate it and never vercel deploy --prod from server/. Everything goes www → Railway.
  • When changing the MCP tool contract, bump CONTRACT_VERSION in server/src/mcp/tools.ts, then verify live via get_structure against https://www.ohmyself.ai/mcp.
  • After deploy, clients cache the tool list — reconnect (ChatGPT/Claude) or reload (Cursor) to pick up new tools.
  • Hosted billing: set STRIPE_* on Railway and OMS_ENFORCE_PRO=true only when you want paywalls live. The webhook path is POST /webhooks/stripe (proxied from www). Leave enforcement unset for self-host.

Full topology, runbook, and history: docs/DEPLOYMENT.md.

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 Changed · +3 lines · +58 tokens per session 2b3bcbaa1c9a
  2. 2mo ago First seen · 29 lines · 446 tokens per session scan A 14119fb34c85

Subscribe to this mod's changes

ohmyself AGENTS.md is an instructions file published in the GitHub repository juanchoabdon/ohmyself (0 stars, last pushed 14d ago), licensed MIT. It adds 504 tokens to every session, about $0.0020 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

ohmyself AGENTS.md compared with instructions from other repositories

ohmyself AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
ohmyself AGENTS.mdjuanchoabdon/ohmyselfInstructions file014d agoMITA504Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, 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