blog AGENTS.md

blog AGENTS.md is an instructions file for Codex, OpenCode from sorcererxw/blog. It costs 1,524 tokens per session, scanned A, original, MIT.

Repository instructions for a standalone Next.js blog, including its purpose, required reading order, architecture boundaries, and operating rules.

In plain words
What is it for?
Use them when maintaining the public blog, finding the correct project documentation, or checking work before claiming it is complete.
Why use it?
They give coding agents the project context and tell them which specifications, plans, roadmap, task records, and verification notes to consult before changing code.

Instructions file for CodexOpenCode

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

Install

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.

agentmods
npx agentmods add instructions/sorcererxw/blog/agents-md
Clone the repo
git clone --depth 1 https://github.com/sorcererxw/blog

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 blog AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/sorcererxw/blog/agents-md.svg)](https://agentmods.dev/instructions/sorcererxw/blog/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/sorcererxw/blog/agents-md"><img src="https://agentmods.dev/badge/instructions/sorcererxw/blog/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,524 This file is loaded in full into every session.
When invoked 1,524 The same file — it is already loaded in full.
Security scan A 1 finding. Scan, not verified.
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 $0.01524 $0.01524
Opus 5 $0.00762 $0.00762
Sonnet 5 $0.00305 $0.00305
Haiku 4.5 $0.00152 $0.00152

Measured 6d ago against content hash 65ed1f16fced, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

blog AGENTS.md scanned grade A with 1 finding 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 6d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- `curl` or HTTP-level checks
AGENTS.md · 255 lines

How it starts

The opening of the file, as written. The whole thing — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Purpose

This repository contains the standalone public blog product.

The goal is to maintain the Next.js + OpenNext public Personal Site application that was extracted from tempura/web/apps/blog2 into its own repository at /Users/sorcererxw/repo/sorcererxw/blog.

This repository replaces the current split public-blog architecture across:

  • web/apps/blog
  • web/apps/blog2
  • server/app/blog
  • Vercel
  • Railway

This app covers the public blog domain only.

It does not cover:

  • fusink
  • route management/admin tooling
  • generic backend platform work outside the public blog

Operating Model

This directory is designed for autonomous agent execution with progressive disclosure.

An agent should not load the entire project context by default. Start with the minimum necessary context, then expand only as needed.

Required Read Order

For any task in this repository, read in this order:

  1. AGENTS.md
  2. the most relevant doc under docs/specs/
  3. the most relevant doc under docs/plans/, if one exists
  4. docs/roadmap.md
  5. the relevant section of docs/task-ledger.md
  6. docs/verification.md before claiming completion

Do not load unrelated specs, plans, or legacy code unless the current task needs them.

Mandatory Execution Loop

Every non-trivial task must follow this loop:

  1. Understand the requirement
  2. Check whether an existing spec already covers it
  3. If the requirement changes behavior or architecture, write or update a spec first
  4. Write or update an implementation plan before substantial implementation work
  5. Implement in small vertical slices
  6. Verify the change with the appropriate mix of:
    • unit/integration tests
    • curl or HTTP-level checks
    • browser verification
  7. Update the living docs before ending the task

Do not skip design and planning for substantial work.

Definition of Done

Work is not done unless all applicable items below are complete:

  • code is implemented
  • tests were run or an explicit reason was recorded for why they could not be run
  • HTTP behavior was checked with curl or equivalent when endpoints/pages are involved
  • browser verification was completed when UI behavior is involved
  • relevant roadmap/task ledger entries were updated
  • any new architectural decisions were reflected in docs

Read the full file on GitHub · 255 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. 6d ago First seen · 255 lines · 1,524 tokens per session scan A 65ed1f16fced

Subscribe to this mod's changes

blog AGENTS.md is an instructions file published in the GitHub repository sorcererxw/blog (86 stars, last pushed 3mo ago), licensed MIT. It adds 1,524 tokens to every session, about $0.0076 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.