agentmods.dev

agentis AGENTS.md

Repository instructions for setting up Agentis, a system that coordinates AI agents. They document its command-line setup, API-key creation, agent roles, workspaces, and supported connections to coding tools.

In plain words
What is it for?
Use them to start Agentis, create an API key, bootstrap an agent, choose its role, select a workspace, and connect tools such as Codex or Claude Code.
Why use it?
They help an agent configure Agentis consistently and avoid creating more than one main coordinator for a workspace. They also keep connection secrets out of source files.

Instructions file for CodexOpenCode

5 6d ago A scan 468 tokens original Apache-2.0
View the source file agentis-labs/agentis
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 instructions/agentis-labs/agentis/agents-md
Clone the repo
git clone --depth 1 https://github.com/agentis-labs/agentis

Made for: Codex, OpenCode.

Per session 468 This file is loaded in full into every session.
When invoked 468 The same file — it is already loaded in full.
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 $0.00468 $0.00468
Opus 5 $0.00234 $0.00234
Sonnet 5 $0.00094 $0.00094
Haiku 4.5 $0.00047 $0.00047

Measured 2d ago against content hash 881ac93b9f11, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agentis 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.

AGENTS.md · 68 lines

What it actually says

Agentis - Agent Setup Instructions

This file is for AI agents configuring Agentis from inside this repository. If you are a human, start with README.md.

Quick start

Installed CLI:

agentis bootstrap --url http://127.0.0.1:3737 --api-key <key> --name "The Brain" --adapter claude_code

Repo-local CLI:

pnpm exec tsx packages/cli/src/index.ts bootstrap --url http://127.0.0.1:3737 --api-key <key> --name "The Brain" --adapter claude_code

Get an API key

  1. Start Agentis: pnpm exec tsx packages/cli/src/index.ts up
  2. Open the URL printed by the server.
  3. Sign in as the operator user.
  4. Create an API key in Settings.

Bootstrap rules

  • Check for an existing orchestrator first with GET /v1/agents?role=orchestrator.
  • Only one orchestrator should exist per workspace.
  • If an orchestrator already exists, bootstrap as --role manager or --role specialist instead.
  • The CLI resolves the first available workspace automatically unless --workspace-id is provided.
  • Valid adapter values are claude_code, codex, hermes_agent, openclaw, cursor, and http.
  • Pass channel secrets through environment variables, never hardcode them.

Reflect an existing setup

Generate a portable config:

agentis bootstrap generate-config --from claude_code --output ./agentis-config.json
agentis export-config --from codex --output ./agentis-config.json

Import that config into Agentis:

agentis bootstrap --url http://127.0.0.1:3737 --api-key <key> --import ./agentis-config.json

API

Direct bootstrap:

POST /v1/bootstrap
Authorization: Bearer <key>
x-agentis-workspace: <workspace-id>

Config import:

POST /v1/bootstrap/import
Authorization: Bearer <key>
x-agentis-workspace: <workspace-id>
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. 2d ago First seen · 68 lines · 468 tokens per session scan A 881ac93b9f11

Subscribe to this mod's changes

agentis AGENTS.md is an instructions file published in the GitHub repository agentis-labs/agentis (5 stars, last pushed 6d ago), licensed Apache-2.0. It adds 468 tokens to every session, about $0.0023 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.

Backend and APIsDocumentsOrchestrationProductivityagentic-aiagentisagentsai-agentsautomation
Related

Other instructions, from other repositories

agent-framework copilot-instructions.md

Instructions for microsoft/agent-framework, covering github copilot instructions, repository structure and architectural decision records (adrs).

microsoft/agent-framework · 211 tokens

agent-framework python.instructions.md

Instructions for microsoft/agent-framework: See AGENTS.md for project structure and package documentation. Detailed conventions are in the agent skills under .github/skills/.

microsoft/agent-framework · 110 tokens

hindsight CLAUDE.md

Instructions for vectorize-io/hindsight, covering claude.md, project overview, development commands, local development (api + ui) and start both api server and control plane ui.

vectorize-io/hindsight · 4,846 tokens

codedb AGENTS.md

AGENTS.md instructions for justrach/codedb, covering codedb agent guidelines, what codedb is (and isn't), review guidelines, pre-merge verification and security-sensitive areas.

justrach/codedb · 509 tokens

relay AGENTS.md

Instructions for AgentWorkforce/relay, covering git workflow rules, never push directly to main, correct workflow, ... do work .. and stop here - let user merge.

AgentWorkforce/relay · 2,083 tokens

claude-code-settings copilot-instructions.md

Instructions for feiskyer/claude-code-settings, covering claude.md, environment setup, required dependencies, configuration and skills.

feiskyer/claude-code-settings · 649 tokens