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.
npx agentmods add instructions/vukasintheprogramer/aseprite-mcp/claude-mdgit clone --depth 1 https://github.com/VukasinTheProgramer/Aseprite-MCPWrote 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/vukasintheprogramer/aseprite-mcp/claude-md)<a href="https://agentmods.dev/instructions/vukasintheprogramer/aseprite-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/vukasintheprogramer/aseprite-mcp/claude-md.svg" alt="Measured on agentmods" 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 | $0.03109 | $0.03109 |
| Opus 5 | $0.01554 | $0.01554 |
| Sonnet 5 | $0.00622 | $0.00622 |
| Haiku 4.5 | $0.00311 | $0.00311 |
Grade A, and why
Aseprite-MCP CLAUDE.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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — Aseprite MCP
Coding rules for this repo. aseprite-mcp-build-flow.md is the build plan (what/when).
This file is the law (how). When the two disagree, this file wins.
Stack
- Python 3.11+, MCP Python SDK 2.x, Pillow, numpy, pydantic ≥2.12.
- No new dependency without a reason that a few lines of stdlib can't cover.
- Entrypoint:
aseprite_mcp.server:main, stdio transport.
aseprite-mcp-build-flow.mdwas written against SDK 1.x and its server code is stale. Its architecture, pixel-art craft rules, and pitfall table still hold. Its imports, error handling, and auto-preview return shape do not. See "SDK 2.x" below.
SDK 2.x — the API actually is this
from mcp.server import MCPServer # NOT mcp.server.fastmcp.FastMCP
from mcp.server.mcpserver import Resolve, Context
from mcp.server.mcpserver import Image as MCPImage # PIL owns the bare name `Image`
FastMCPis gone. No alias, no deprecation shim. Anything importingmcp.server.fastmcpis v1 code.- HTTP client is
httpx2, nothttpx. Don't addhttpx. - All Pydantic field names are snake_case in Python (
input_schema,is_error); the wire stays camelCase. - Transport args (
host,port, …) go torun(), not the constructor. - MCP types silently drop unknown fields. Custom data goes in
_metaor it vanishes.
Layout
Follow aseprite-mcp-build-flow.md §2. Don't invent new top-level packages.
New tool → a module in src/aseprite_mcp/tools/ exposing register(mcp), pulling the
Bridge / Session aliases from deps.py (rule 28).
Build order
M0 → M1 → M2 → M3 → M4, then reassess. Do not start a milestone before the previous one's "done when" is actually true. The Phase 0 spike gates everything: no MCP tool code lands before the bridge round-trips 200 commands.
Hard rules — do not violate
These are the failure modes this project is known to hit. Each one cost someone a day.
Bridge
- Atomic queue writes. Write
<id>.tmp, thenrename()to<id>.cmd. Never write.cmddirectly. - Serialize every command behind one lock. Aseprite is single-threaded; concurrent commands corrupt sprite state.
- Poll for process death inside the wait loop. A crash must raise in ms, not hang for the full timeout.
- Both backends implement
AsepriteBridge(base.py). Server code never branches on which backend is live. - Batch backend has no state. Every batch command is open → mutate → save.
app.spriteis nil there.
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.
- 5d ago First seen · 148 lines · 3,109 tokens per session scan A 72b0fdd48fae
Aseprite-MCP CLAUDE.md is an instructions file published in the GitHub repository VukasinTheProgramer/Aseprite-MCP (0 stars, last pushed 23d ago), licensed MIT. It adds 3,109 tokens to every session, about $0.0155 per session on Opus 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.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.