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 agents/azure/gpt-rag/architecturegit clone --depth 1 https://github.com/Azure/GPT-RAGWrote 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/agents/azure/gpt-rag/architecture)<a href="https://agentmods.dev/agents/azure/gpt-rag/architecture"><img src="https://agentmods.dev/badge/agents/azure/gpt-rag/architecture.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 | $0.00041 | $0.00233 |
| Opus 5 | $0.00020 | $0.00117 |
| Sonnet 5 | $0.00008 | $0.00047 |
| Haiku 4.5 | $0.00004 | $0.00023 |
Grade A, and why
architecture 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 4d 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.
What it actually says
GPT-RAG architecture
Follow AGENTS.md and load the engineering-principles and
architecture-decision skills.
Start from the operator or user outcome, constraints, and a small set of measurable architectural characteristics. Compare alternatives in the context of GPT-RAG's multi-repository release model, Azure identity and network boundaries, document-level authorization, cost, operability, migration, and reversibility.
Treat manifest.json, versioned contracts, infrastructure parameters, and
runtime component behavior as executable sources of truth. Do not turn a
framework or Azure service preference into a requirement without evidence.
Record significant decisions under docs/adr/.
Output handoff to implementation: decision, affected repositories,
boundaries, contracts, fitness functions, risks, migration and rollback, and
open questions.
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.
- 4d ago First seen · 27 lines · 41 tokens per session scan A a473df3a16ca
architecture is an agent published in the GitHub repository Azure/GPT-RAG (1,169 stars, last pushed 16d ago), licensed MIT. It adds 41 tokens to every session and 233 once invoked, about $0.0002 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 agents, from other repositories
triager
Triage old stale issues for obsolescence and recommend closures.
fixer
Fix and verify issues in app.
Codebase-Explorer
Help engineers learn about the codebase and programming concepts of this project.
AGENTS
In-depth tutorials on LLMs, RAGs and real-world AI agent applications.
bestmode
You are an agent - please keep going until the user’s query is completely resolved, before ending your turn and yielding back to the user.
ask-smoke
Run a live smoke test of the /ask endpoint (SSE-streamed RAG). Boots fireseqsearchserver via tests/runlogseq.sh, runs tests/testask.py (protocol/invariant assertions) and tests/testendpoints.py --ask against a user-supplied question, and reports on answer grounding, citation validity, source quality, streaming…