What is clawops AGENTS.md?

A set of project instructions for clawops, a TypeScript command-line tool that deploys and manages self-hosted OpenClaw installations on cloud services or local virtual machines. It also describes the project's folders, rules, and interfaces.

Use it when working on clawops commands, cloud providers, infrastructure deployment, its MCP server, SSH transport, configuration, or machine-readable specifications.

It gives an AI coding assistant the context and constraints needed to change the clawops codebase safely and consistently.

clawops AGENTS.md — Instructions file by dfridkin

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/dfridkin/clawops/agents-md

Clone the repo

git clone --depth 1 https://github.com/dfridkin/clawops

Made for: Codex, OpenCode.

Per session 1,554 This file is loaded in full into every session.

When invoked 1,554 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.

Model	Per session	Once invoked
Fable 5	$0.01554	$0.01554
Opus 5	$0.00777	$0.00777
Sonnet 5	$0.00311	$0.00311
Haiku 4.5	$0.00155	$0.00155

Measured 2d ago against content hash d3af0174b141, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

clawops 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

clawops CLAUDE.md — 86% identical, 24 lines differ

AGENTS.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

clawops

clawops is a TypeScript CLI that generates and applies infrastructure to deploy self-hosted OpenClaw across AWS, GCP, Azure, and local VMs. It uses the Pulumi Automation API (embedded engine, not user-installed) and exposes its operations as both a CLI surface and an MCP server so Claude Code, Cursor, and other agents can drive deployments deterministically.

Directory map

src/cli/ citty-based commands (one file per verb in commands/)
src/providers/ one folder per cloud; each implements ProviderAdapter (src/providers/types.ts, GENERATED from spec/providers.schema.json)
src/pulumi/ Pulumi components + Automation API wrapper. URN convention: clawops:<cat>:<Name> where category ∈ {infra, build, net, app, state}
src/mcp/ MCP server, tool definitions auto-generated from spec/mcp-tools.yaml
src/transport/ SSH (uses ssh2). Never shell out to /usr/bin/ssh
src/plan/ Maker plan generation, validation (ajv against spec/deploy-plan.schema.json), apply
src/config/ ~/.clawops/config.json management (no secrets — see R6)
spec/ machine-readable specs (JSON Schema, YAML). Treat as ground truth (R-meta-1)
docs/ narrative architecture, ADRs, per-provider guides
.claude/skills/ invokable procedures (/add-provider, /release, /openclaw-config, /tdd)
.claude/rules/ path-scoped rules loaded on demand

Commands

pnpm dev run CLI from src
pnpm build tsup build to dist/
pnpm test vitest, parallel
pnpm test:changed vitest --changed; use this during edit loops
pnpm typecheck tsc --noEmit
pnpm lint eslint --max-warnings=0
pnpm gen:schemas emit src/providers/types.ts and src/mcp/tools/_generated.ts from spec/
pnpm gen:schemas --check CI check that committed generated files match spec
pnpm changeset record a release note (see /release skill)

Invariants — YOU MUST follow these

Read the full file on GitHub · 95 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.

2d ago First seen · 95 lines · 1,554 tokens per session scan A d3af0174b141

Subscribe to this mod's changes

clawops AGENTS.md is an instructions file published in the GitHub repository dfridkin/clawops (1 stars, last pushed 1mo ago), licensed MPL-2.0. It adds 1,554 tokens to every session, about $0.0078 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.

Cloud DevOps and cloud

clawops AGENTS.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

Copies of this mod

How it starts

clawops

Directory map

Commands

Invariants — YOU MUST follow these

What this file has done since we first saw it

Other instructions, from other repositories

apex-accelerator iac-bicep-best-practices.instructions.md

awsmux AGENTS.md

terraform-provider-pipefy AGENTS.md

plan-forge azd.instructions.md

plan-forge terraform.instructions.md

plan-forge naming.instructions.md