Borrowing it
Nothing to install: this file belongs to sorcererxw/blog. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/sorcererxw/blog/main/AGENTS.mdgit clone --depth 1 https://github.com/sorcererxw/blogWrote 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.
[](https://agentmods.dev/instructions/sorcererxw/blog/agents-md)<a href="https://agentmods.dev/instructions/sorcererxw/blog/agents-md"><img src="https://agentmods.dev/badge/instructions/sorcererxw/blog/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.
<a href="https://agentmods.dev/instructions/sorcererxw/blog/agents-md"><img src="https://agentmods.dev/badge/instructions/sorcererxw/blog/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.01524 | $0.01524 |
| Opus 5.5 | $0.00610 | $0.00610 |
| Sonnet 5.5 | $0.00305 | $0.00305 |
| Haiku 4.5 | $0.00152 | $0.00152 |
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 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.
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 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/blogweb/apps/blog2server/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:
AGENTS.md- the most relevant doc under
docs/specs/ - the most relevant doc under
docs/plans/, if one exists docs/roadmap.md- the relevant section of
docs/task-ledger.md docs/verification.mdbefore 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:
- Understand the requirement
- Check whether an existing spec already covers it
- If the requirement changes behavior or architecture, write or update a spec first
- Write or update an implementation plan before substantial implementation work
- Implement in small vertical slices
- Verify the change with the appropriate mix of:
- unit/integration tests
curlor HTTP-level checks- browser verification
- 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
curlor 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
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.
- 2mo ago First seen · 255 lines · 1,524 tokens per session scan A 65ed1f16fced
blog AGENTS.md is an instructions file published in the GitHub repository sorcererxw/blog (86 stars, last pushed 5mo ago), licensed MIT. It adds 1,524 tokens to every session, about $0.0061 per session on Opus 5.5. 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.
blog AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| blog AGENTS.mdsorcererxw/blog | Instructions file | 86 | 5mo ago | MIT | A | 1,524 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 275k | 3d ago | MIT | A | 4,313 | Codex, OpenCode |