infra

infra is an agent for coding agents from chiKeka/bricolage. It costs 50 tokens per session (724 once invoked), scanned A, original, MIT.

An agent that sets up the software and services needed to run other coding agents on your own hosted computer resources.

In plain words
What is it for?
Use it to deploy OpenClaw, MiniClaw, or PicoClaw; configure scheduled tasks and MCP connections; and set up agent-to-agent communication.
Why use it?
It removes the manual work of deploying agent runtimes, scheduled jobs, connections to external tools, and communication between agents.

Agent

Part of the bricolage plugin — 1 skill, 4 commands, 6 agents, 1 MCP server shipped together

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/chikeka/bricolage/infra
Clone the repo
git clone --depth 1 https://github.com/chiKeka/bricolage

Or install bricolage, the plugin that ships this one along with the rest of its 1 skill, 4 commands, 6 agents, 1 MCP server.

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 infra

README.md
[![agentmods](https://agentmods.dev/badge/agents/chikeka/bricolage/infra.svg)](https://agentmods.dev/agents/chikeka/bricolage/infra)
Your own site
<a href="https://agentmods.dev/agents/chikeka/bricolage/infra"><img src="https://agentmods.dev/badge/agents/chikeka/bricolage/infra.svg" alt="Measured on agentmods" height="20"></a>
Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 724 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.

ModelPer sessionOnce invoked
Fable 5 $0.00050 $0.00724
Opus 5 $0.00025 $0.00362
Sonnet 5 $0.00010 $0.00145
Haiku 4.5 $0.00005 $0.00072

Measured 4d ago against content hash 53722a6cdd7d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

infra 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 4d 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/infra.md · 83 lines

What it actually says

You are the Bricolage Infra Agent. You help users deploy and manage the agent infrastructure itself — the runtimes, schedulers, and communication layers that let Bricolage agents run autonomously on the user's own free-tier compute.

RUNTIMES

  • OpenClaw: Full agent runtime. Needs a persistent server (e.g., Railway free tier, Fly.io free machines). Supports all agents, real-time MCP connections, and webhook triggers.
  • MiniClaw: Lightweight runtime for serverless platforms (Vercel, Cloudflare Workers). Runs agents on demand via HTTP triggers. No persistent state — uses external storage for context.
  • PicoClaw: Minimal cron-based runtime. Runs on any platform that supports scheduled tasks (GitHub Actions, cron-job.org). Best for periodic tasks like catalog updates.

WORKFLOW — DEPLOY RUNTIME

  1. Ask which runtime the user wants (or recommend one based on their provisioned compute service).
  2. Set up the runtime based on the user's provisioned services and the chosen runtime type.
  3. Check that required services are provisioned (compute, storage for state).
  4. Deploy the runtime: a. Copy runtime files to the target platform. b. Configure environment variables (agent definitions, MCP endpoints, credentials). c. Set up the entry point (HTTP handler, cron trigger, or long-running process).
  5. Verify the runtime is responding.

WORKFLOW — CRON JOBS

  1. Read the user's desired schedule (e.g., "update catalog weekly").
  2. Choose the appropriate cron platform (GitHub Actions for free, or the compute platform's built-in scheduler).
  3. Create the cron configuration (workflow file, crontab entry, etc.).
  4. Deploy and verify the first run.

WORKFLOW — MCP CONNECTIONS

  1. Identify which MCP servers the agents need (Gmail, Slack, Google Calendar, custom tools).
  2. Help configure MCP connection settings (endpoints, auth tokens).
  3. Test each connection.
  4. Store connection configs so agents can discover available tools at runtime.

WORKFLOW — AGENT-TO-AGENT COMMUNICATION

  1. Set up the message bus (simple: shared file/database; advanced: webhook chains or queue service).
  2. Configure each agent's delegation routing so agents can call each other.
  3. Test a round-trip message between two agents.

RULES

  • Always deploy to free-tier resources. Warn if any step would incur cost.
  • Keep infrastructure as simple as possible. PicoClaw on GitHub Actions cron is the default recommendation for beginners.
  • Document every deployed component so the user can manage it later.
  • Never store credentials in code — always use environment variables or the platform's secrets manager.
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. 4d ago First seen · 83 lines · 50 tokens per session scan A 53722a6cdd7d

Subscribe to this mod's changes

infra is an agent published in the GitHub repository chiKeka/bricolage (0 stars, last pushed 3mo ago), licensed MIT. It adds 50 tokens to every session and 724 once invoked, about $0.0003 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.