texttile: Instructions file for Codex

AGENTS.md

texttile AGENTS.md is an instructions file for Codex, OpenCode from texttile-blog/texttile. It costs 4,839 tokens per session, scanned A, original, MIT.

Repository instructions describing Texttile, a self-hosted blog system for two writers, and the product rules that guide its development. Self-hosted means the site and its data run on the owner's own server rather than a hosted service.

In plain words
What is it for?
Use it when changing Texttile's blog, storage, performance, privacy, or collaborative-writing behavior.
Why use it?
It keeps changes aligned with the product's focus on local data, small pages, few outside connections, and shared writing.

Instructions file for CodexOpenCode

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

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

Reuse

Borrowing it

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

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 texttile AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/texttile-blog/texttile/agents-md"><img src="https://agentmods.dev/badge/instructions/texttile-blog/texttile/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 4,839 This file is loaded in full into every session.
When invoked 4,839 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 $0.04839 $0.04839
Opus 5.5 $0.01936 $0.01936
Sonnet 5.5 $0.00968 $0.00968
Haiku 4.5 $0.00484 $0.00484

Measured 9d ago against content hash 9d8f859b9589, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

texttile 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 9d 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 · 369 lines

How it starts

The opening of the file, as written. The whole thing — 369 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Texttile

Texttile is a blog CMS for two people who write together. Phoenix, LiveView and SQLite in one Docker image. One volume holds the whole installation: the database and every uploaded file. Nothing else is needed to run it.

You can think of Texttile as a self-hosted alternative to WordPress, Ghost and Substack, in the spirit of "one container, your data".

What makes Texttile special?

These are the promises the product is built on. Keep them intact.

1. Nothing is loaded from outside

A reader's browser talks to this server and to nothing else. No CDN, no third-party script, no tracker, no captcha, no hosted font, no external video player. The statistics are counted here, the spam filter runs here, the mail leaves from here. A change that adds an outside call breaks the product, not just a rule.

2. Light enough for a slow line

Texttile is written for a person reading on a phone far from a data center. Pages stay small, JavaScript stays little, and a picture is only ever as large as the screen asks for. Weigh every kilobyte you add. Continuously repainting animations are out; they cost the reader battery and the writer frames.

3. Written together

Two people work on the same entry at the same time. The title and body are locked, and only softly: the holder writes, the other one watches the text arrive live and can take over in one click. Tiles, tags, settings and publish controls stay free for both, last write wins per field. The admin area shows who is on which screen. This is the hero feature, and it is why the lock is a GenServer and not a database column.

4. The writer's Markdown, byte for byte

The body is plain text, not a document tree. What the writer typed is what is stored, character for character, so a version diff shows real edits and nothing else. Never normalize, reflow or clean Markdown, and never introduce an editor that serializes it from a tree (ProseMirror, TipTap, Milkdown).

5. Minimal, and everybody is an admin

Read the full file on GitHub · 369 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. 9d ago Changed · +5 lines · +60 tokens per session 9d8f859b9589
  2. 12d ago Changed · +3 lines · +49 tokens per session 506407fc2d58
  3. 14d ago Changed · +11 lines · +193 tokens per session 1e856b99cdf6
  4. 20d ago Changed · -1 lines · -25 tokens per session b659cb01dcae
  5. 23d ago First seen · 351 lines · 4,562 tokens per session scan A 668e80d53478

Subscribe to this mod's changes

texttile AGENTS.md is an instructions file published in the GitHub repository texttile-blog/texttile (28 stars, last pushed today), licensed MIT. It adds 4,839 tokens to every session, about $0.0194 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 2026-10-14.

Related

texttile AGENTS.md compared with instructions from other repositories

texttile AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
texttile AGENTS.mdtexttile-blog/texttileInstructions file28todayMITA4,839Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, 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