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/emeaappgbb/agentic-shell-python/agents-mdgit clone --depth 1 https://github.com/EmeaAppGbb/agentic-shell-pythonWhat 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 | $0.00983 | $0.00983 |
| Opus 5 | $0.00491 | $0.00491 |
| Sonnet 5 | $0.00197 | $0.00197 |
| Haiku 4.5 | $0.00098 | $0.00098 |
Grade A, and why
agentic-shell-python 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 yesterday.
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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
AI coding agent instructions for agentic-shell-python.
Overview
| Aspect | Details |
|---|---|
| Stack | Python 3.11+ FastAPI backend, Next.js 16/React 19 frontend |
| Infra | Azure Container Apps, OpenAI (gpt-5-mini), Cosmos DB, AI Search (unused) |
| Status | Starter template - use skills to add AI agent capabilities |
| Cost | ~$309/month ($74 wasted on unused Cosmos DB + AI Search) |
Quick Start
# Recommended: Aspire orchestration
dotnet run --project apphost.cs
# Backend: localhost:8080 | Frontend: localhost:3000 | Dashboard: localhost:15888
# Or individually:
cd src/agentic-api && uv run fastapi dev main.py
cd src/agentic-ui && npm run dev
# Deploy to Azure
azd up
Environment Variables
Backend (src/agentic-api/.env):
AZURE_OPENAI_ENDPOINT=https://<name>.openai.azure.com/
AZURE_OPENAI_DEPLOYMENT_NAME=gpt5MiniDeployment
Frontend (src/agentic-ui/.env.local):
AGENT_API_URL=http://localhost:8080
Agent Skills
This repository includes skills for adding AI agent capabilities:
| Skill | Purpose |
|---|---|
.github/skills/ms-agent-framework |
Add Microsoft Agent Framework to Python backend |
.github/skills/ag-ui-integration |
Connect frontend to backend with AG-UI protocol |
To add AI agent capabilities, follow the instructions in these skills.
Key Files
| Path | Purpose |
|---|---|
src/agentic-api/main.py |
FastAPI application (starter template) |
src/agentic-ui/app/page.tsx |
React page component |
src/agentic-ui/app/layout.tsx |
Root layout |
infra/main.bicep |
Subscription-scoped IaC entry point |
infra/resources.bicep |
Container Apps, Cosmos DB, AI Search |
apphost.cs |
.NET Aspire orchestration |
Architecture
Browser → Next.js → FastAPI → (Add agent with skills)
- Starter Template: No AI agent by default - use skills to add
- Auth: Azure Managed Identity (no secrets in code)
- Stateless: No conversation persistence (Cosmos DB provisioned but unused)
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.
- yesterday First seen · 127 lines · 983 tokens per session scan A c27c2d713a2d
agentic-shell-python AGENTS.md is an instructions file published in the GitHub repository EmeaAppGbb/agentic-shell-python (2 stars, last pushed 6mo ago), licensed MIT. It adds 983 tokens to every session, about $0.0049 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
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.
buildNext
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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
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.
langchain 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.