ase-deliver: Instructions file for Codex

AGENTS.md

ase-deliver AGENTS.md is an instructions file for Codex, OpenCode from ylty1516/ase-deliver. It costs 980 tokens per session, scanned A, original, MIT.

Repository instructions for ase-deliver, a tool that packages game artwork into Aseprite files, sprite sheets, GIF previews, and engine metadata. Aseprite is a pixel-art editor, and the instructions require the editable .aseprite file as the source deliverable.

In plain words
What is it for?
Following the artwork workflow: initialize a project, prepare source images, build the deliverables, validate them, and optionally open them in Aseprite.
Why use it?
They prevent an agent from treating a standalone image as finished when the project requires layered, animated, and validated game-art files.

Instructions file for CodexOpenCode

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

This is ylty1516/ase-deliver's own configuration. It tells Codex and OpenCode how to work on ase-deliver 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 ase-deliver configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ylty1516/ase-deliver. 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/ylty1516/ase-deliver/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/ylty1516/ase-deliver

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 ase-deliver AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ylty1516/ase-deliver/agents-md/github.svg)](https://agentmods.dev/instructions/ylty1516/ase-deliver/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/ylty1516/ase-deliver/agents-md"><img src="https://agentmods.dev/badge/instructions/ylty1516/ase-deliver/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 ase-deliver AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/ylty1516/ase-deliver/agents-md"><img src="https://agentmods.dev/badge/instructions/ylty1516/ase-deliver/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 980 This file is loaded in full into every session.
When invoked 980 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 $0.00980 $0.00980
Opus 5.5 $0.00392 $0.00392
Sonnet 5.5 $0.00196 $0.00196
Haiku 4.5 $0.00098 $0.00098

Measured 2mo ago against content hash 3c5a4b961062, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ase-deliver 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 · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AseDeliver — contract for any AI

You are producing shippable Aseprite game art, not a pretty PNG.

Source of truth is always out/<name>.aseprite. A PNG/GIF without that file is not done.

What this tool is

ase-deliver turns a JSON spec + frame images (or ASCII pixels) into:

  • .aseprite with layers, frames, tags, palette, pivot/slices
  • sprite sheet PNG
  • GIF preview
  • engine JSON (frames + meta.frameTags)

It does not replace your image model. You generate pixels however you can. This compiler makes them deliverable in Aseprite.

Do this, in order

  1. doctor — confirm Pillow; Aseprite is optional for compile, required to open the file.
  2. init a project from a template. Fill description with the subject.
  3. brief — follow the returned prompt and exact filenames.
  4. Put one image per required name in raw/. Magenta #FF00FF background. Isolated subject. Integer scale of the canvas is OK.
  5. build (ingest + compile + export + validate).
  6. Only report done if validate.deliverable is true.
  7. open in Aseprite if the user wants to see it.

CLI (Windows):

C:\Users\yyx\ase-deliver\ase-deliver.bat doctor
C:\Users\yyx\ase-deliver\ase-deliver.bat templates
C:\Users\yyx\ase-deliver\ase-deliver.bat init hero --template character-platformer --out D:\game\art\hero --desc "orange fox knight, facing right"
C:\Users\yyx\ase-deliver\ase-deliver.bat brief D:\game\art\hero
C:\Users\yyx\ase-deliver\ase-deliver.bat build D:\game\art\hero
C:\Users\yyx\ase-deliver\ase-deliver.bat open D:\game\art\hero

Python module:

python -m ase_deliver <command>

Set PYTHONPATH=C:\Users\yyx\ase-deliver if you are not cwd'd there.

Templates

id canvas tags
character-platformer 32x32 idle, walk, jump
character-topdown 16x16 idle-down, walk-down/left/right/up
character-turnaround 64x64 front, three-quarter, side, back
portrait 80x80 bust
prop 32x32 idle
tileset-16 16x16 grass, dirt, stone, water
ui-button 48x16 normal, hover, pressed
fx 32x32 burst

Read the full file on GitHub · 97 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. 2mo ago First seen · 97 lines · 980 tokens per session scan A 3c5a4b961062

Subscribe to this mod's changes

ase-deliver AGENTS.md is an instructions file published in the GitHub repository ylty1516/ase-deliver (0 stars, last pushed 2mo ago), licensed MIT. It adds 980 tokens to every session, about $0.0039 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

ase-deliver AGENTS.md compared with instructions from other repositories

ase-deliver AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
ase-deliver AGENTS.mdylty1516/ase-deliverInstructions file02mo agoMITA980Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA2,022GitHub Copilot