implementation

A coding workflow for making small, well-defined changes to a GPT-RAG codebase, including tests and documentation. GPT-RAG is a system that retrieves relevant documents before generating answers.

In plain words
What is it for?
Use it to investigate affected code, implement the smallest coherent change, update behavioural tests and documentation, run project validation, and report the files, results, dependencies, and risks.
Why use it?
It helps turn an agreed issue or plan into a controlled code change while preserving existing contracts and deployment behaviour. It also makes validation, documentation updates, and remaining risks explicit.

Agent

Install

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.

agentmods
npx agentmods add agents/azure/gpt-rag/implementation
Clone the repo
git clone --depth 1 https://github.com/Azure/GPT-RAG
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 210 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00030 $0.00210
Opus 5 $0.00015 $0.00105
Sonnet 5 $0.00006 $0.00042
Haiku 4.5 $0.00003 $0.00021

Measured yesterday against content hash a7a822101d0b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

implementation 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.

.github/agents/implementation.agent.md · 25 lines

What it actually says

GPT-RAG implementation

Follow AGENTS.md, .github/copilot-instructions.md, and all scoped instructions that apply to the changed files.

Investigate the current implementation and tests, make the smallest coherent change, and preserve contracts and deployment behavior by default. Reuse existing modules, templates, scripts, and configuration paths.

Before editing, confirm acceptance criteria, affected repositories, security and compatibility risks, and documentation impact. Add or adjust behavioral tests, update affected documentation in the correct repository or branch, and run the existing validation specific to the change.

Input handoff: an issue, plan, or ADR with high-impact decisions resolved.

Output handoff: delivered behavior, changed files, commands and results, cross-repository dependencies, documentation status, and residual risks.

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. yesterday First seen · 25 lines · 30 tokens per session scan A a7a822101d0b

Subscribe to this mod's changes

implementation is an agent published in the GitHub repository Azure/GPT-RAG (1,169 stars, last pushed 14d ago), licensed MIT. It adds 30 tokens to every session and 210 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.