flatmachines AGENTS.md

A reference guide for FlatAgents and FlatMachines, tools for defining single model calls and multi-step workflows. It also explains model profiles and sign-in connections for Codex and Copilot.

In plain words
What is it for?
Use it when building or reviewing flatagents, flatmachines, model-profile files, prompts, or related configuration.
Why use it?
It helps developers choose the right structure for a simple task or a workflow with branching, retries, parallel work, or background tasks. It also documents how models are selected.

Instructions file for CodexOpenCode

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/memgrafter/flatmachines/agents-md
Clone the repo
git clone --depth 1 https://github.com/memgrafter/flatmachines

Made for: Codex, OpenCode.

Per session 2,185 This file is loaded in full into every session.
When invoked 2,185 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 $0.02185 $0.02185
Opus 5 $0.01092 $0.01092
Sonnet 5 $0.00437 $0.00437
Haiku 4.5 $0.00218 $0.00218

Measured 3d ago against content hash 1566e79fca1a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

flatmachines 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 3d 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 · 217 lines

How it starts

The opening of the file, as written. The whole thing — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.

FlatAgents + FlatMachines Reference

Target: <1000 tokens. LLM-optimized. See flatagent.d.ts, flatmachine.d.ts, profile.d.ts, prompt.d.ts for schemas.

Versioning: All specs and SDKs use lockstep versioning.

Concepts

FlatAgent: Single LLM call. Model + prompts + output schema. No orchestration. FlatMachine: State machine orchestrating agents. States, transitions, conditions, loops, error handling.

Need Use
Single LLM call FlatAgent
Multi-step/branching/retry/errors FlatMachine
Parallel execution machine: [a, b, c]
Dynamic parallelism foreach
Background tasks launch

Model Profiles

# profiles.yml — agents reference by name
spec: flatprofile
spec_version: "4.2.1"
data:
  model_profiles:
    fast: { provider: cerebras, name: zai-glm-4.6, temperature: 0.6 }
    smart: { provider: anthropic, name: claude-3-opus-20240229 }
  default: fast        # Fallback
  # override: smart    # Force all

Agent model field: "fast" | { profile: "fast", temperature: 0.9 } | { provider: x, name: y } Resolution: default → profile → overrides → override

OAuth Backends (Codex / Copilot)

  • backend: codex and backend: copilot are explicit-only (never auto-detected).
  • Backend selection precedence remains: constructor backend → resolved model.backend → auto-detect (litellm/aisuite only).
  • oauth settings are read from resolved model config; works identically whether model came from inline agent config or profile.
  • Auth file precedence:
    • Codex: oauth.auth_file → legacy codex_auth_file → legacy auth.auth_fileFLATAGENTS_CODEX_AUTH_FILE~/.pi/agent/auth.json
    • Copilot: oauth.auth_filecopilot_auth_file → legacy auth.auth_fileFLATAGENTS_COPILOT_AUTH_FILE~/.agents/flatmachines/auth.json
  • Token handling: pre-request refresh on expiry; if refresh fails, re-read auth store once for cross-process refresh; fallback refresh+retry on 401/403.
  • Retries on 429/500/502/503/504 with exponential backoff (no jitter).

Read the full file on GitHub · 217 lines

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. 3d ago First seen · 217 lines · 2,185 tokens per session scan A 1566e79fca1a

Subscribe to this mod's changes

flatmachines AGENTS.md is an instructions file published in the GitHub repository memgrafter/flatmachines (37 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 2,185 tokens to every session, about $0.0109 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.

Related

Other instructions, from other repositories

agentcontrolplane CLAUDE.md

Claude Code instructions for humanlayer/agentcontrolplane, covering agent control plane (acp) - ai assistant instructions, 🚨 the 1500-line minimum read rule - this is not optional, 📋 your 20-point todo list - you need this structure, current todo list (you must maintain 20+ items) and 🚨 mandatory persona selection.

humanlayer/agentcontrolplane · 1,148 tokens

graphiti CLAUDE.md

Instructions for getzep/graphiti, covering claude.md, project overview, development commands, main development commands (run from project root) and install dependencies.

getzep/graphiti · 1,739 tokens

stagehand AGENTS.md

Instructions for browserbase/stagehand: Only a human may request changes to this file. Keep additions rare and limited to durable, repository-wide rules. -->.

browserbase/stagehand · 160 tokens

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

graphiti AGENTS.md

Instructions for getzep/graphiti, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.

getzep/graphiti · 1,656 tokens