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/symfony/ai-demo/agents-mdgit clone --depth 1 https://github.com/symfony/ai-demoWrote 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/symfony/ai-demo/agents-md)<a href="https://agentmods.dev/instructions/symfony/ai-demo/agents-md"><img src="https://agentmods.dev/badge/instructions/symfony/ai-demo/agents-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 | $0.01810 | $0.01810 |
| Opus 5 | $0.00905 | $0.00905 |
| Sonnet 5 | $0.00362 | $0.00362 |
| Haiku 4.5 | $0.00181 | $0.00181 |
Grade A, and why
ai-demo 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 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
AI agent guidance for the Symfony AI demo application.
Project Overview
Symfony 8.0 demo application showcasing the Symfony AI components: RAG over the Symfony blog, streaming chat, multi-agent orchestration, voice/speech, image cropping, webcam video captioning, YouTube transcript Q&A, Wikipedia-grounded answers, a demo MCP server, and the AI Mate development CLI.
Development Commands
Setup
docker compose up -d # Start PostgreSQL (pgvector)
composer install
echo "OPENAI_API_KEY='sk-...'" > .env.local # HUGGINGFACE_API_KEY only if you wire HF agents
# Vector store must be set up before indexing
symfony console ai:store:setup ai.store.postgres.symfony_blog
symfony console ai:store:index blog -vv
symfony console ai:store:retrieve blog "Week of Symfony"
symfony serve -d # https://localhost:8000/
Testing and Quality
vendor/bin/phpunit # All tests (config in phpunit.xml)
vendor/bin/phpunit tests/SmokeTest.php # Single test file
vendor/bin/phpunit --testsuite e2e # Panther browser tests, local only (see README.md)
vendor/bin/phpstan analyse # Static analysis (phpstan.dist.neon)
# There is no enforced formatter in this package — php-cs-fixer is configured at the monorepo root.
The e2e suite drives all ten use cases in a real browser and asserts the Symfony AI panel of the
profiler (platform calls, tools, tool calls, token usage). It runs the app in the dev environment,
calls the AI platforms for real, and is excluded from the default suite — never add it to CI.
MCP Server
- Demo MCP server (
symfony/mcp-bundle):symfony console mcp:serverexposes tools/prompts/resources/resource-templates fromsrc/Mcp/. Start it manually when demoing. Test with{"method":"tools/list","jsonrpc":"2.0","id":1}.
AI Mate
symfony/ai-mate (dev only) is a plain CLI, not a server: run ./vendor/bin/mate tools:list and ./vendor/bin/mate tools:call <tool>. Extensions are registered in mate/extensions.php, config in mate/config.php, custom tools in mate/src/.
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 · 97 lines · 1,810 tokens per session scan A 85901bf86e5d
ai-demo AGENTS.md is an instructions file published in the GitHub repository symfony/ai-demo (47 stars, last pushed 5d ago), licensed MIT. It adds 1,810 tokens to every session, about $0.0090 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 2026-08-30.
Other instructions, from other repositories
UltraRAG AGENTS.md
AGENTS.md instructions for OpenBMB/UltraRAG, covering agents.md, 1) project identity, 2) repository map (what matters most), 3) mental model of the system and 4) two-phase execution lifecycle.
OpenDocuments AGENTS.md
Instructions for joungminsung/OpenDocuments, covering agents.md, project overview, monorepo structure, common commands and 특정 패키지만.
oh-my-knowledge AGENTS.md
AGENTS.md instructions for lizhiyao/oh-my-knowledge, covering agents.md - agent 入场清单, 开工先做, 高效交付, 自主 cr 与完成定义 and cr 运行产物隔离.
ai-mate AGENTS.md
AGENTS.md instructions for symfony/ai-mate, covering agents.md, component overview, architecture, core classes and attributes.
statewave-grounded-shop-assistant AGENTS.md
Instructions for smaramwbc/statewave-grounded-shop-assistant, covering agents.md — guide for contributors and coding agents, setup, build, test, layout, conventions and pull requests.
obsidian-semantic-mcp CLAUDE.md
Claude Code instructions for artificemachine/obsidian-semantic-mcp, covering obsidian semantic mcp, build & run, full stack (postgres, ollama, mcp-server, dashboard), rebuild after code changes and wipe all data and re-index from scratch.