What is Aegisdesk AGENTS.md?

Repository-specific instructions for AegisDesk, an application whose core workflow uses LangGraph to track and run AI tasks.

Choosing the right context files, preserving the human approval step before tools run, and testing changes with the AegisDesk command-line program.

They show an agent where the main architecture lives, which files to inspect, and which project commands to use before changing code.

How sitanshukr08/Aegisdesk configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to sitanshukr08/Aegisdesk. 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/sitanshukr08/Aegisdesk/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/sitanshukr08/Aegisdesk

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/sitanshukr08/aegisdesk/agents-md/github.svg)](https://agentmods.dev/instructions/sitanshukr08/aegisdesk/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/sitanshukr08/aegisdesk/agents-md"><img src="https://agentmods.dev/badge/instructions/sitanshukr08/aegisdesk/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/sitanshukr08/aegisdesk/agents-md"><img src="https://agentmods.dev/badge/instructions/sitanshukr08/aegisdesk/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 630 This file is loaded in full into every session.

When invoked 630 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.

Model	Per session	Once invoked
Fable 5.1	$0.00630	$0.00630
Opus 5.5	$0.00252	$0.00252
Sonnet 5.5	$0.00126	$0.00126
Haiku 4.5	$0.00063	$0.00063

Measured 2mo ago against content hash 7859bcb05d3e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Aegisdesk 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 · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Guide

Verified for AegisDesk v0.1.6 (Phase 16)

This repository is optimized for focused, low-context collaboration between humans and AI agents. Read this file before changing code or docs.

Start Here

Use docs/context-map.md to choose the minimum files needed for the task. Do not load the entire repository unless the change is cross-cutting.

Architecture Boundary

AegisDesk uses LangGraph for its core intelligence and state tracking.

The Nodes are defined in app/rag/pipeline.py and app/rag/graph.py (LangGraph Swarm) (LangGraph Swarm).
The Tools are defined in src/aegisdesk/core/tools.py and integration_tools.py.
The Execution Engine is src/aegisdesk/core/pipeline.py.

Working Rules

Use the aegisdesk CLI. The CLI is installed via pip install -e .. Use aegisdesk ask or aegisdesk doctor to test changes. Do not run random python scripts directly.
Respect the ToolNode Interrupts. AegisDesk uses interrupt_before=["tools"] for Human-in-the-Loop security. If you alter the pipeline execution in src/aegisdesk/core/pipeline.py, ensure the interrupt flow logic remains intact so OS commands are never executed blindly.
Use Native Tool APIs ONLY. Never add conversational preambles to tool-calling agent prompts. Use native tool_calls API directives only. Models like Llama-3 will break and output stringified JSON if instructed to explain their actions before calling a tool.
Use the LLMFactory. Never instantiate ChatGroq or ChatOpenAI directly in the core logic. Always use get_llm() from src/aegisdesk/core/llm_factory.py.
Use the Logger. Do not use print(). Use get_logger() from src/aegisdesk/observability/logger.py.

Task Routing

Documentation/Positioning: read README.md, docs/roadmap.md, and docs/ARCHITECTURE.md.
Tool creation: read src/aegisdesk/core/tools.py and app/rag/graph.py (LangGraph Swarm) (LangGraph Swarm).
CLI work: read src/aegisdesk/cli/main.py.
Persistence work: read docs/adr/0002-sqlite-plus-chroma.md.
API work: read app/api/endpoints.py and src/aegisdesk/core/pipeline.py.

Read the full file on GitHub · 46 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.

2mo ago First seen · 46 lines · 630 tokens per session scan A 7859bcb05d3e

Subscribe to this mod's changes

Aegisdesk AGENTS.md is an instructions file published in the GitHub repository sitanshukr08/Aegisdesk (1 stars, last pushed 5mo ago), licensed MIT. It adds 630 tokens to every session, about $0.0025 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.

Building agents LLM ai-agents chromadb fastapi helpdesk langgraph

Aegisdesk AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
Aegisdesk AGENTS.mdsitanshukr08/Aegisdesk	Instructions file	1	5mo ago	MIT	A	630	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

Aegisdesk: Instructions file for Codex