What is nanoclaw_flexagents AGENTS.md?

A project instruction file for NanoClaw FlexAgents, a personal assistant that can run Claude, Codex, and Gemini agent software. It records the fork's scope, architecture choices, important files, and runtime configuration.

Use it when changing or reviewing FlexAgents' multi-runtime support, provider integrations, architecture, or deployment configuration.

It explains which upstream changes are intentionally not adopted and which features are outside the project's goals. This helps contributors avoid incompatible rebases or unsupported marketplace integrations.

How chiptoe-svg/nanoclaw_flexagents configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to chiptoe-svg/nanoclaw_flexagents. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/chiptoe-svg/nanoclaw_flexagents/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/chiptoe-svg/nanoclaw_flexagents

Made for: Codex, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/chiptoe-svg/nanoclaw_flexagents/agents-md/github.svg)](https://agentmods.dev/instructions/chiptoe-svg/nanoclaw_flexagents/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/chiptoe-svg/nanoclaw_flexagents/agents-md"><img src="https://agentmods.dev/badge/instructions/chiptoe-svg/nanoclaw_flexagents/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/chiptoe-svg/nanoclaw_flexagents/agents-md"><img src="https://agentmods.dev/badge/instructions/chiptoe-svg/nanoclaw_flexagents/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,233 This file is loaded in full into every session.

When invoked 2,233 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.02233	$0.02233
Opus 5	$0.01117	$0.01117
Sonnet 5	$0.00447	$0.00447
Haiku 4.5	$0.00223	$0.00223

Measured 9d ago against content hash e2f117fa811f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

nanoclaw_flexagents 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 9d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

nanoclaw_flexagents GEMINI.md — 86% identical, 26 lines differ

AGENTS.md · 167 lines

How it starts

The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.

NanoClaw FlexAgents

Multi-runtime personal assistant built on NanoClaw. Supports Claude, Codex (OpenAI), and Gemini agent SDKs.

Scope and Non-goals

FlexAgents is based on nanoclaw v1 with multi-runtime support added in trunk. Upstream qwibitai/nanoclaw has since released a v2 architecture; this fork evaluated adopting it and chose not to (2026-04-18).

Non-goals:

Rebasing onto nanoclaw v2. Session DBs, module registries, Chat SDK bridge, richer user/role schemas. Multi-runtime in trunk is this fork's primary feature and isn't improved by adopting v2. The divergence is deliberate, not a pending rebase.
Skill-marketplace compatibility (/add-* feature skills). Divergence makes git merge upstream/skill/* conflict-prone; marketplace skills are reference material, not installable here. Most are channel integrations we don't need anyway.
Upstream's richer entity model (users / user_roles / pending_approvals / agent_destinations). Single-user / small-team deployments don't need it.

Upstream contributions flow the other direction: provider-level work goes back as standalone PRs (e.g., the Codex app-server provider). Architecture changes stay in this fork.

For active institutional deployment (FERPA-aware, MS365-integrated, department operations), see chiptoe-svg/CUagent — a specialized downstream fork.

Architecture

Four-layer system:

App Shell — channels, state, scheduling, IPC (src/index.ts)
Runtime Boundary — provider-neutral host adapters with runtimeOptions (src/runtime/)
Runtime Setup + Container Launch — credential resolution, provider mounts, container spawning
In-Container Agent Runner — SDK-specific agent loops with provider-driven MCP/tools/docs

All SDKs run inside the same container image. The agent-runner detects the runtime from ContainerInput.runtime and uses the appropriate SDK. SDKs self-register via a registry pattern (same as channels).

External services (MS365, Google Workspace, IMAP) are configured as provider JSON files — no code changes needed to add or remove a provider. Provider tokens are only mounted for authorized groups.

Read the full file on GitHub · 167 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.

9d ago First seen · 167 lines · 2,233 tokens per session scan A e2f117fa811f

Subscribe to this mod's changes

nanoclaw_flexagents AGENTS.md is an instructions file published in the GitHub repository chiptoe-svg/nanoclaw_flexagents (5 stars, last pushed 4mo ago), licensed MIT. It adds 2,233 tokens to every session, about $0.0112 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.

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

nanoclaw_flexagents: Instructions file for Codex