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/atharva-again/samvaad/agents-mdgit clone --depth 1 https://github.com/atharva-again/samvaadWhat 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 | $0.00756 | $0.00756 |
| Opus 5 | $0.00378 | $0.00378 |
| Sonnet 5 | $0.00151 | $0.00151 |
| Haiku 4.5 | $0.00076 | $0.00076 |
Grade A, and why
samvaad 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 2d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PROJECT KNOWLEDGE BASE
Generated: 2026-01-12T17:12:56Z Commit: 5b9b2c1 Branch: docs/update
OVERVIEW
Samvaad is a full-stack RAG (Retrieval-Augmented Generation) application with voice and text modes. The backend is built with FastAPI and Python, while the frontend is a Next.js application.
STRUCTURE
.
├── samvaad/ # Core backend logic (FastAPI, Pipeline, DB)
│ ├── api/ # API routes and entry points
│ ├── core/ # Authentication, memory, and shared logic
│ ├── db/ # Database models and services (Supabase/PostgreSQL)
│ ├── pipeline/ # RAG pipeline (Ingestion, Retrieval, Deletion)
│ ├── prompts/ # AI persona and mode definitions
│ └── utils/ # Citations, text processing, and hashing utilities
├── frontend/ # Next.js/React frontend application
├── tests/ # Unit and integration test suites
├── data/ # Document storage and local data
└── PLANS/ # Project roadmap and technical designs
WHERE TO LOOK
| Task | Location | Notes |
|---|---|---|
| API Endpoints | samvaad/api/main.py |
FastAPI app definition |
| Database Ops | samvaad/db/service.py |
Core DB service logic |
| AI Prompting | samvaad/prompts/ |
Persona and style definitions |
| RAG Pipeline | samvaad/pipeline/ |
Document ingestion and retrieval |
| UI Components | frontend/components/ |
React components |
| Auth Logic | samvaad/core/auth.py |
Backend authentication |
CODE MAP
| Symbol | Type | Location | Role |
|---|---|---|---|
app |
Variable | samvaad/api/main.py |
FastAPI application |
DBService |
Class | samvaad/db/service.py |
Primary database interface |
TextMessageRequest |
Class | samvaad/api/main.py |
Schema for text chat requests |
VoiceModeRequest |
Class | samvaad/api/main.py |
Schema for voice session setup |
CONVENTIONS
- Python: Uses
uvfor dependency management. Strict typing withmypy. - Formatting:
Black(88 char) for Python,Biomefor Frontend. - Linting:
Rufffor Python,ESLintandBiomefor Frontend. - Testing:
pytestfor backend unit and integration tests.
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.
- 2d ago First seen · 71 lines · 756 tokens per session scan A c2d1209e12f0
samvaad AGENTS.md is an instructions file published in the GitHub repository atharva-again/samvaad (2 stars, last pushed 5mo ago), licensed MIT. It adds 756 tokens to every session, about $0.0038 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
vscode buildNext.instructions.md
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).
spec-kit AGENTS.md
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.
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.
langchain AGENTS.md
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.
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).
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.