mini-openclaw-langchain: Instructions file for Codex

AGENTS.md

mini-openclaw-langchain AGENTS.md is an instructions file for Codex, OpenCode from kaiqiangh/mini-openclaw-langchain. It costs 940 tokens per session, scanned A, original, MIT.

Repository instructions for Mini-OpenClaw, a local-first workspace with a FastAPI backend, a Next.js web interface, and a command-line tool. It also describes its agent workspaces, configuration, Docker setup, and tests.

In plain words
What is it for?
Use them to navigate the repository, find backend and frontend code, work with agent templates and runtime settings, and run the project's core commands.
Why use it?
They help coding agents understand which part owns a change and how the backend, frontend, configuration, and deployment files fit together.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md; built for openclaw.

This is kaiqiangh/mini-openclaw-langchain's own configuration. It tells Codex and OpenCode how to work on mini-openclaw-langchain itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mini-openclaw-langchain configures →

Reuse

Borrowing it

Nothing to install: this file belongs to kaiqiangh/mini-openclaw-langchain. 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/kaiqiangh/mini-openclaw-langchain/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/kaiqiangh/mini-openclaw-langchain

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.

agentmods badge for mini-openclaw-langchain AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/kaiqiangh/mini-openclaw-langchain/agents-md/github.svg)](https://agentmods.dev/instructions/kaiqiangh/mini-openclaw-langchain/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/kaiqiangh/mini-openclaw-langchain/agents-md"><img src="https://agentmods.dev/badge/instructions/kaiqiangh/mini-openclaw-langchain/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.

agentmods 80×15 button for mini-openclaw-langchain AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/kaiqiangh/mini-openclaw-langchain/agents-md"><img src="https://agentmods.dev/badge/instructions/kaiqiangh/mini-openclaw-langchain/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 940 This file is loaded in full into every session.
When invoked 940 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00940 $0.00940
Opus 5.5 $0.00376 $0.00376
Sonnet 5.5 $0.00188 $0.00188
Haiku 4.5 $0.00094 $0.00094

Measured 2mo ago against content hash 493817cc5347, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mini-openclaw-langchain 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 2mo 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 · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Guidance for coding agents that modify this repository.

Project overview

Mini-OpenClaw is a local-first multi-agent workspace with:

  • a FastAPI backend in backend/
  • a Next.js frontend in frontend/
  • a repo-local CLI in ./oml and ./oml.ps1
  • per-agent workspaces under backend/workspaces/<agent_id>/

The backend owns runtime config, tool policy, scheduler behavior, template loading, and persistence. The frontend owns the operator UI and API client behavior.

Repository map

  • backend/app.py: FastAPI entrypoint, middleware, health/readiness, optional frontend proxy
  • backend/config.py: runtime schema, config parsing, LLM profile/default loading
  • backend/config.json: canonical repo-level runtime and provider config
  • backend/agent_templates/: shipped template presets
  • backend/tests/backend/: backend unit and API coverage
  • frontend/src/app/: Next.js routes
  • frontend/src/lib/api.ts: typed frontend API wrappers
  • frontend/src/components/: UI components
  • docker-compose.yml: Docker entrypoint for prod and dev profiles
  • docker/nginx/default.conf: public edge routing for the production-like Docker profile

Core commands

Local

./oml start
./oml stop
./oml status

Backend

cd backend
./.venv/bin/pytest -q

Frontend

cd frontend
npm run test:run
npm run build

Docker

cp .env.example .env
docker compose --profile prod up --build -d
docker compose --profile dev up --build -d

# Stop the containers.
# Do NOT add "-v" unless explicitly removing volumes and reset all persisted data by user's prompt.
docker compose --profile prod down
docker compose --profile dev down

Change boundaries

  • Do not treat root AGENTS.md as a runtime prompt file. It is contributor guidance only.
  • Do not confuse root docs with generated workspace files under backend/workspaces/.../workspace/.
  • Keep backend/config.json as the source of truth for repo-level runtime defaults and provider configuration.
  • Keep agent templates limited to runtime_config patches. Do not place secrets, llm_profiles, llm_defaults, or agent_llm_overrides in template files.
  • Preserve current ./oml local workflows when adding Docker or docs changes.

Read the full file on GitHub · 120 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. 2mo ago First seen · 120 lines · 940 tokens per session scan A 493817cc5347

Subscribe to this mod's changes

mini-openclaw-langchain AGENTS.md is an instructions file published in the GitHub repository kaiqiangh/mini-openclaw-langchain (11 stars, last pushed 3mo ago), licensed MIT. It adds 940 tokens to every session, about $0.0038 per session on Opus 5.5. 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

mini-openclaw-langchain AGENTS.md compared with instructions from other repositories

mini-openclaw-langchain AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
mini-openclaw-langchain AGENTS.mdkaiqiangh/mini-openclaw-langchainInstructions file113mo agoMITA940Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode