asset-aware-mcp: Instructions file for Codex

AGENTS.md

asset-aware-mcp AGENTS.md is an instructions file for Codex, OpenCode from u9401066/asset-aware-mcp. It costs 1,042 tokens per session, scanned A, original, Apache-2.0.

A set of AGENTS.md instructions for working with the asset-aware-mcp project and its citation-focused document workflows. AGENTS.md is a file that tells a coding agent how to work in a project.

In plain words
What is it for?
Use it when operating asset-aware-mcp workflows involving PDFs, DOCX files, tables, figures, DFM edits, or LightRAG knowledge-graph outputs.
Why use it?
It gives the agent project-specific working rules for preserving document evidence, stable source identity, and reversible file changes.

Instructions file for CodexOpenCode

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

This is u9401066/asset-aware-mcp's own configuration. It tells Codex and OpenCode how to work on asset-aware-mcp 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 asset-aware-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to u9401066/asset-aware-mcp. 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/u9401066/asset-aware-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/u9401066/asset-aware-mcp

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 asset-aware-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/u9401066/asset-aware-mcp/agents-md.svg)](https://agentmods.dev/instructions/u9401066/asset-aware-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/u9401066/asset-aware-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/u9401066/asset-aware-mcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,042 This file is loaded in full into every session.
When invoked 1,042 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 $0.01042 $0.01042
Opus 5 $0.00521 $0.00521
Sonnet 5 $0.00208 $0.00208
Haiku 4.5 $0.00104 $0.00104

Measured 7d ago against content hash 8ff260f4403e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

asset-aware-mcp 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 7d 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 · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Asset-Aware MCP Codex Harness

These are workspace instructions for Codex when working with Asset-Aware MCP through the VS Code extension, local CLI, or MCP server.

Goal

Help the user build and operate citation-ready document workflows that preserve precise evidence provenance for PDFs, DOCX files, tables, figures, DFM edits, and LightRAG knowledge graph outputs.

Working Style

  • Use Traditional Chinese unless the user asks otherwise.
  • Prefer exact file paths, command output summaries, and verification results.
  • Treat messy document inputs as normal: broken numbering, mixed encodings, nested tables/lists, OCR artifacts, and repeated format conversions are all expected.
  • When changing behavior, add a regression test that proves the edge case stays fixed.

Core Workflow

  1. Ingest or convert the document with the narrowest suitable MCP tool. For PDFs, run document(op="preflight", pdf_path="/absolute/path/source.pdf") first when OCR or layout quality is uncertain.
  2. Preserve source identity with stable IDs, locator metadata, and hashes.
  3. Keep DFM/DOCX round trips reversible and prompt before destructive writes.
  4. Use CRAAP as a conservative evidence-quality scaffold; do not invent scores.
  5. Prefer line/char/byte spans plus surrounding context for citation-ready claims.
  6. Re-run the focused tests for changed code, then the full release harness before publishing.
  7. Export reusable agent assets with document(op="export_assets", doc_id="doc_...", output_dir="agent-assets"); use the generated Foam index and notes as the portable wiki layer.

PDF -> Asset Engine Selection

The core goal is turning documents into complete, agent-friendly figure/table/ text assets, fast. ETL_ENGINE selects the extraction backend; structured engines lazy-load and gracefully fall back to PyMuPDF when unavailable:

  • pymupdf (default) - fast, no models, always available.
  • pymupdf4llm ([pdf-plus]) - drop-in layout-aware upgrade, no GPU.
  • docling ([docling]) - MIT-licensed layout+table+formula+chart engine; bridges through an isolated .venv-docling interpreter via subprocess when the main environment cannot install it directly (see docs/docling-setup.md for cross-platform install).
  • mineru - adapter retained for upstream evaluation, but the packaged [mineru] extra is an empty security hold while MinerU pins transformers<5 and patched releases require transformers>=5.5.
  • marker - disabled; marker-pdf pins Pillow<11, incompatible with the Pillow>=12.2.0 security floor.

Read the full file on GitHub · 95 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. 7d ago First seen · 95 lines · 1,042 tokens per session scan A 8ff260f4403e

Subscribe to this mod's changes

asset-aware-mcp AGENTS.md is an instructions file published in the GitHub repository u9401066/asset-aware-mcp (0 stars, last pushed 20d ago), licensed Apache-2.0. It adds 1,042 tokens to every session, about $0.0052 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.

Related

Other instructions, from other repositories

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

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.

github/spec-kit · 7,104 tokens