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/cortexlm/cortex/agents-mdgit clone --depth 1 https://github.com/CortexLM/cortexWhat 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 | $0.02325 | $0.02325 |
| Opus 5 | $0.01162 | $0.01162 |
| Sonnet 5 | $0.00465 | $0.00465 |
| Haiku 4.5 | $0.00232 | $0.00232 |
Grade A, and why
cortex 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Cortex control plane
Short contract for agents and operators. Prefer linking over restating runbooks.
Product: Cortex (CortexLM/cortex) — Bittensor subnet control plane for decentralized collaborative AI research via multiple challenges. Naming split (Cortex vs leftover base / BASE_*): docs/NAMING.md.
Monorepo map
| Path | Role |
|---|---|
bins/ |
Runnable processes (validator, gateway, updater, challenges, …) |
crates/ |
Libraries shared by binaries |
xtask/ |
Repo gates and maintenance tasks |
deploy/ |
Compose matrix, Terraform, pins, secrets helpers, remote deploy |
docs/ |
Architecture, frozen specs, runbooks, completeness |
config/ |
Shared non-secret configuration |
Working branch: main. Prod ships from annotated tags v*.*.* cut on main.
Non-negotiables
- Digest-only images in deploy paths — no floating tags in prod pins/compose.
- Secrets via age + files under
deploy/env//deploy/secrets/— never baked into images or cloud-init. - Gateway runs on master only (
--profile master/role-master.yml). Validators point at the master gateway over VPC. evil-gatewayis test-only — never enable on prod hosts; assert withdeploy/scripts/assert-evil-gateway-not-default.sh.- Platform is DigitalOcean Droplets + Docker Compose, not App Platform / DOKS.
- Do not rename
BASE_*env vars, deployed paths, or crypto domain tags. They are measured into miner CVMapp-compose.jsonand live on droplets / RTMR3 pin continuity.CORTEX_*is an accepted alias incrates/configonly. Seedocs/NAMING.md. - Frozen specs (
docs/BUNDLE_SPEC.md,docs/DESIGN_CHALLENGE.md) are pinned by xtask. Do not weaken gates or rewrite incentive / scoring / consensus semantics. unsafe_code = forbid. Nounwrap/expectin non-test code.
Wallet / key roles (do not conflate)
| Key | Who | Needed for |
|---|---|---|
gateway_sk |
Gateway | Bundle seal signatures (POST /v1/admin/seal) |
gateway_admin_token |
Gateway + seal scripts | Bearer for /v1/admin/* (seal, backends, attest-grant). Required when BASE_GATEWAY_REQUIRE_OWNER=1 |
prism_sk / design_sk |
Challenge / smoke | Signed leaves (POST /v1/weights/raw); pubs must match trust root |
Gateway owner wallet + BASE_GATEWAY_REQUIRE_OWNER |
Gateway | Master-only identity check (live/prod). Not required to seal or serve /v1/weights/latest |
| Validator wallet | Validator | On-chain weight submit only — validators fetch sealed weights; they do not need a gateway wallet |
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 · 126 lines · 2,325 tokens per session scan A 6a4d84492c5a
cortex AGENTS.md is an instructions file published in the GitHub repository CortexLM/cortex (160 stars, last pushed 2d ago), licensed Apache-2.0. It adds 2,325 tokens to every session, about $0.0116 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
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.
buildNext
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).
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.
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).
spec-kit 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.
langchain 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.