What is openclaw-operator?

An integration setup for OpenClaw, a command-line workspace for running coding agents, with AINL, a system for compiling repeatable workflows. It connects environment settings, a small SQLite database, scheduled jobs, and cached files.

Use it to configure an OpenClaw workspace, install AINL integration, set up three scheduled jobs, store workflow and budget records, and define cache locations.

It provides a documented way to install and coordinate these parts in one workspace. It also keeps rolling budget information available for status checks and scheduled reports.

openclaw-operator — Agent by sbhooley

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 agents/sbhooley/ainativelang/openclaw-operator

Clone the repo

git clone --depth 1 https://github.com/sbhooley/ainativelang

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 2,628 The whole file, excluding the scripts and references it only reads on demand.

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.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.02628
Opus 5	$0.00000	$0.01314
Sonnet 5	$0.00000	$0.00526
Haiku 4.5	$0.00000	$0.00263

Measured 3d ago against content hash f2e63061943e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

openclaw-operator 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

openclaw-quickstart-local-preserved — 89% identical, 24 lines differ

docs/agents/openclaw-operator.md · 149 lines

How it starts

The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OpenClaw + AINL — 5-minute quickstart

This path wires gateway env.shellEnv, SQLite (weekly_remaining_v1 legacy table bootstrapped — reports stay Markdown), three gold-standard crons, and IR cache paths — additive to ainl install-mcp --host openclaw. Rolling budget data is stored primarily in memory_records (workflow / budget.aggregate / weekly_remaining_v1); ainl status reads the legacy table when set, else falls back to that aggregate. For tuning (caps, schedules, verification cadence), use docs/operations/OPENCLAW_AINL_GOLD_STANDARD.md.

Prerequisites

Python 3.10+ and ainl on PATH (pip install ainativelang; current PyPI v1.8.0, or editable install).
OpenClaw CLI on PATH (openclaw --help works).
Optional: set OPENCLAW_WORKSPACE before commands so ainl status resolves the same workspace as your agents (otherwise default is ~/.openclaw/workspace when that directory exists, else current working directory).

One-command setup

Pick a workspace root (your OpenClaw workspace, often ~/.openclaw/workspace):

ainl install openclaw --workspace ~/.openclaw/workspace

Preview changes without writing config, SQLite, crons, or restarting the gateway:

ainl install openclaw --workspace ~/.openclaw/workspace --dry-run

What this does (non–dry-run):

Writes aiNativeLang.yml in the workspace if missing — copies from aiNativeLang.example.yml (repo root or tooling/) when present; otherwise safe defaults inline.
Merges env.shellEnv keys directly into <workspace>/.openclaw/openclaw.json (OpenClaw CLI config set rejects AINL-specific keys — file merge is authoritative), including OPENCLAW_BOOTSTRAP_PREFER_SESSION_CONTEXT=true, AINL_WEEKLY_TOKEN_BUDGET_CAP=100000, OPENCLAW_WORKSPACE, AINL_MEMORY_DB, MONITOR_CACHE_JSON, AINL_IR_CACHE_DIR, and related paths.
Idempotently creates weekly_remaining_v1 under AINL_MEMORY_DB (CREATE TABLE IF NOT EXISTS). (Rolling budget values are published to memory_records; see gold standard §c.)
Registers three crons if missing (same name or same payload message → skipped): AINL Context Injection (every 5 min), AINL Session Summarizer, AINL Weekly Token Trends — matching the gold-standard doc.
Runs openclaw gateway restart (skipped when --dry-run).
Prints a markdown health table (workspace, aiNativeLang.yml, env merge, schema, crons, drift, restart, IR cache).

Read the full file on GitHub · 149 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.

3d ago First seen · 149 lines · 0 tokens per session scan A f2e63061943e

Subscribe to this mod's changes

openclaw-operator is an agent published in the GitHub repository sbhooley/ainativelang (671 stars, last pushed 2mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,628 tokens. 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.

Building agents Databases agent-orchestration ai-agents claude-code compiler deterministic-execution domain-specific-language

code-analyst

Investigates code-level issues in the agency's Python stack (Django, FastAPI, SQLAlchemy) — debugging, log analysis, query optimization, test-coverage gaps. Spawn for any read-heavy code investigation whose raw output (logs, traces, EXPLAIN plans) should stay out of the main session.

bks-lab/open-bridge · 68 tokens

deploy-engineer

Runs and verifies deployments for the agency's two client stacks — BigCorp on AWS (Terraform, Lambda, RDS) and StartupXYZ on Vercel — including CI pipelines, migrations, and secret management. Spawn for deploy execution, rollback prep, or infrastructure checks.

bks-lab/open-bridge · 58 tokens

order-inquiry-agent

Sen OrderInquiryAgent'sın. Sipariş sorgularını işlersin.

ahmettugur/agentic-customer-support-bot · 0 tokens

db-architect

Senior Database Architect specialising in schema design, query optimisation, migrations, and data integrity. Use when: designing a database, "add a table", "schema design", "write a migration", "my query is slow", "index this", "normalise my schema", "PostgreSQL", "Prisma", "Drizzle", "SQL optimization", "NoSQL vs…

Ghosteken/agent-harness · 103 tokens

software-engineer

Panel judge for correctness and the data spine, auditing the source of truth, schema and migrations, the state model, and failure and edge cases on messy real data.

gbotev1/cc-autopilot · 37 tokens

data-engineer

Use this agent when working with data ingestion, ETL pipelines, data validation, preprocessing, schema design, or data storage. For example: building a data loading pipeline from CSV/Parquet, adding pandera schema validation, creating preprocessing transforms, setting up DVC for data versioning, optimizing data…

xvirobotics/metaskill · 76 tokens