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/indexnetwork/index/agents-mdgit clone --depth 1 https://github.com/indexnetwork/indexWhat 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 | $0.03125 | $0.03125 |
| Opus 5 | $0.01563 | $0.01563 |
| Sonnet 5 | $0.00625 | $0.00625 |
| Haiku 4.5 | $0.00313 | $0.00313 |
Grade A, and why
index 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 — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
How we build
This is an early-stage product. Everything is provisional and can be rewritten as we learn. Keep the codebase small and direct.
- Build the smallest thing that does what was asked. Use one code path. Do not add options, flags, fallbacks, configuration, or abstractions for a case that does not exist today. Do not handle unreachable states.
- Every changed line traces to the request. No drive-by refactors, renames, reformatting, or incidental improvements. Mention a discovery briefly instead of fixing it without scope.
- Change in place, do not layer. Rewrite the old behavior, update every
caller in this repository, and delete what becomes dead, including tests.
Do not add
legacy*/v2twins, adapters, deprecated re-exports, or compatibility paths. - Compatibility is optional. If preserving an old API, behavior, or data needs a migration, dual read, or parallel path, make the breaking change and state it in the PR. For public protocol changes, follow the release rules below.
- Do not build for later. Record a future idea in one sentence and wait until it is requested. Prefer deleting unused code, tests, docs, and fixtures to retaining them just in case.
If the request appears to require substantially more, state why and deliver the smallest useful version.
Repository map and boundaries
This is a Bun monorepo. The table below is the whole architecture map; commands,
conventions, and workflow appear later in this file. There is no docs/
directory. It was deleted on 2026-08-28 and is not being restored.
| Path | Responsibility |
|---|---|
packages/protocol |
@indexnetwork/protocol: domain graphs, agents, tools, MCP server, and host interfaces. Published to npm and used by external integrators. |
services/api |
Bun HTTP host and workers. Wires infrastructure (Drizzle/Postgres, Redis, OpenRouter) into the protocol. |
apps/web |
Vite + React Router SPA. src/services/*.ts are typed API clients, not business logic. |
apps/mac |
Swift WKWebView shell around a self-contained React bundle. |
packages/cli, packages/claude-plugin, packages/hermes-plugin |
HTTP/MCP clients mirrored to public repositories. Their dependencies must be exact pins; run bun run check:subtree-parity when they change. |
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 · 257 lines · 3,125 tokens per session scan A 901cbcc7edf3
index AGENTS.md is an instructions file published in the GitHub repository indexnetwork/index (132 stars, last pushed 3d ago), licensed MIT. It adds 3,125 tokens to every session, about $0.0156 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
langgraph AGENTS.md
AGENTS.md instructions for langchain-ai/langgraph, covering agents instructions, corridor security analysis, libraries and dependency map.
omnigent copilot-instructions.md
Copilot instructions for omnigent-ai/omnigent, covering copilot code review instructions, e2e test requirement, backend test coverage and frontend test coverage.
AutoAgents AGENTS.md
Instructions for liquidos-ai/AutoAgents, covering autoagents repository guidelines, project structure & module organization, code quality, naming conventions and error handling.
claude-code-karma CLAUDE.md
Instructions for JayantDevkar/claude-code-karma, covering claude.md, project overview, quick start, clone (no submodule init needed — this is a monorepo) and start api (terminal 1).
hatch3r CLAUDE.md
Instructions for hatch3r/hatch3r, covering hatch3r — development instructions, architecture, development commands, two-axis pillar framework (2.0.0) and orchestrator self-discipline (bypass protection).
aeon CLAUDE.md
Instructions for aeonfun/aeon, covering aeon, how aeon works, strategy, voice and soul file hierarchy (read in this order).