agentmods.dev

contxt-box: Instructions file for Codex

AGENTS.md

contxt-box AGENTS.md is an instructions file for Codex, OpenCode from Oshadha345/contxt-box. It costs 762 tokens per session, scanned A, original, MIT.

Project instructions for ConTXT BOX, a local file-context system that connects folders to coding assistants through a command-line tool and MCP server. They define how files are indexed, extracted, and stored.

In plain words
What is it for?
Guiding agents on project scope, file indexes, configuration, lazy extraction, supported document engines, and storage under .contextbox/.
Why use it?
They keep indexing predictable, avoid unnecessary processing, and prevent generated context from overwriting user files.

Instructions file for CodexOpenCode

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

This is Oshadha345/contxt-box's own configuration. It tells Codex and OpenCode how to work on contxt-box 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 contxt-box configures →

not rated 0repo 3mo ago A scan 762 tokens original MIT
View source ↗ Oshadha345/contxt-box
Reuse

Borrowing it

Nothing to install: this file belongs to Oshadha345/contxt-box. 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/Oshadha345/contxt-box/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/Oshadha345/contxt-box

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 contxt-box AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/oshadha345/contxt-box/agents-md/github.svg)](https://agentmods.dev/instructions/oshadha345/contxt-box/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/oshadha345/contxt-box/agents-md"><img src="https://agentmods.dev/badge/instructions/oshadha345/contxt-box/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 contxt-box AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/oshadha345/contxt-box/agents-md"><img src="https://agentmods.dev/badge/instructions/oshadha345/contxt-box/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 762 This file is loaded in full into every session.
When invoked 762 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 $0.00762 $0.00762
Opus 5.5 $0.00305 $0.00305
Sonnet 5.5 $0.00152 $0.00152
Haiku 4.5 $0.00076 $0.00076

Measured 1mo ago against content hash ce51c5c9a7d7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

contxt-box 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 1mo 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 · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

ConTXT BOX agents follow a strict Ponytail plus gstack style: minimal, structured, scoped, and reliable. The product goal is an external context box that connects any local folder to coding assistants through CLI and MCP.

Non-Negotiable Scope

  • Core heavy extraction has exactly two supported engines: MarkItDown and Docling.
  • Do not add fallback chains across OCR, audio, video, Whisper, FFmpeg, Chunkr, or vision APIs unless the product scope is explicitly changed.
  • Indexing must stay lazy. Do not open or parse heavy documents/images during index or watchdog updates.
  • Heavy extraction happens only through extract-media or MCP get_file(path, depth="full").
  • Never overwrite user files. Store generated context only under .contextbox/.

Index Contract

Every indexed file must include:

  • rel_path
  • filename
  • folder_path
  • mtime
  • size
  • file_type
  • neighbors
  • parent_folder_summary
  • last_indexed
  • context_summary

Cheap context_summary must be based on filename, folder, and neighbors only. It should be 1-2 concise sentences and avoid wild speculation.

Configuration Contract

  • init must create .contextbox/config.toml if it is missing.
  • Runtime behavior must load .contextbox/config.toml through AppConfig.for_root.
  • Configurable settings include extraction engine, ignore directories, priority folders, max neighbors, inline byte limit, large file limit, watchdog debounce, and auto-watch.
  • Do not add hidden behavior that bypasses the workspace config.

Folder And Neighbor Rules

  • Every folder gets a lightweight summary based on its name and top-level files.
  • Every file records up to 10 sibling files.
  • File summaries should use 5-7 nearby files as context cues.
  • Prioritize special folders in indexing order: codebases/, research/, specs/, decisions/, assets/images/.

Extraction Contract

  • Cache sidecars at .contextbox/history/media/<sanitized_path>.context.md.
  • After extraction, update index.json with extracted_at, context_ref, extraction_method, extraction_status, extraction_warnings, and extraction_duration_seconds.
  • Capture engine warnings and noisy stdout/stderr as structured audit metadata.
  • Large files over 50 MB get metadata-only sidecars unless explicit chunked extraction is implemented later.
  • The configured engine is strict. If Docling is selected and fails, report the failure. Do not silently switch to MarkItDown.

Read the full file on GitHub · 82 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. 1mo ago First seen · 82 lines · 762 tokens per session scan A ce51c5c9a7d7

Subscribe to this mod's changes

contxt-box AGENTS.md is an instructions file published in the GitHub repository Oshadha345/contxt-box (0 stars, last pushed 3mo ago), licensed MIT. It adds 762 tokens to every session, about $0.0030 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 2026-09-01.

mcp-local-first-knowledge-base-context-management
Related

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).

microsoft/vscode · 9,715 tokens

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 · 7,581 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, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 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 · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,731 tokens

deno copilot-instructions.md

Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.

denoland/deno · 3,077 tokens