agentmods.dev

optio CLAUDE.md

Repository guidance for Optio, a system that runs AI coding agents on software tasks. It explains how tasks, isolated Kubernetes pods, and Git worktrees are used to run work and open pull requests.

In plain words
What is it for?
Understanding task triggers, assigning coding agents, creating isolated repository workspaces, streaming run logs, and tracking pull requests.
Why use it?
It clarifies how Optio separates concurrent work and moves a task from an agent run to code review, reducing confusion about its workflow.

Instructions file

1.0k 22d ago B scan 6,856 tokens original MIT
View the source file jonwiggins/optio
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/jonwiggins/optio/claude-md
Clone the repo
git clone --depth 1 https://github.com/jonwiggins/optio
Per session 6,856 This file is loaded in full into every session.
When invoked 6,856 The same file — it is already loaded in full.
Security scan B 1 finding. 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 $0.06856 $0.06856
Opus 5 $0.03428 $0.03428
Sonnet 5 $0.01371 $0.01371
Haiku 4.5 $0.00686 $0.00686

Measured 2d ago against content hash 30973a282aa6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

optio CLAUDE.md scanned grade B with 1 finding 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

- **Vertex AI** (GCP workloads): Routes through Google Cloud Vertex AI. Uses `CLAUDE_VERTEX_PROJECT_ID`, `CLAUDE_VERTEX_REGION`, and optional `CLAUDE_VERTEX_SERVICE_ACCOUNT_KEY` (encrypted, global scope). Falls back to w
CLAUDE.md · 304 lines

How it starts

The opening of the file, as written. The whole thing — 304 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Context and conventions for AI assistants working on the Optio codebase.

What is Optio?

Optio is an orchestration system for AI coding agents. Think of it as "CI/CD where the build step is an AI agent." One primary user-facing concept (Tasks) with one attribute (has a repo) flipping the pipeline, plus shared primitives:

Tasks — a configured unit of agent work. A Task has a Who (agent type), What (prompt or template), When (trigger: manual / schedule / webhook / ticket), optional Where (repo + branch), and Why (description). Tasks come in three flavors:

  • Repo Task — Where is set. The agent clones the repo into a worktree and opens a PR:

    1. Spins up an isolated Kubernetes pod for the repository (pod-per-repo)
    2. Creates a git worktree for the task (multiple run concurrently per repo)
    3. Runs Claude Code, OpenAI Codex, GitHub Copilot, Google Gemini, OpenCode, or Cursor with the prompt
    4. Streams structured logs back to a web UI in real time
    5. Agent stops after opening a PR (no CI blocking)
    6. PR watcher tracks CI checks, review status, and merge state
    7. Auto-triggers code review agent on CI pass or PR open (if enabled)
    8. Auto-resumes agent when reviewer requests changes (if enabled)
    9. Auto-completes on merge, auto-fails on close

    Supported git platforms: GitHub, GitLab (incl. self-hosted via GITLAB_HOSTS), and AWS CodeCommit. CodeCommit auths via AWS access keys (or IRSA / instance profile when running on EKS) and uses the AWS CLI credential helper for clones; PR ops go through @aws-sdk/client-codecommit. CodeCommit has no native CI or issues — getCIChecks returns [] (auto-merge still fires on checksStatus="none"), listIssues returns [], and reviewTrigger="on_pr" is recommended over the default on_ci_pass for CodeCommit repos.

  • Standalone Task — no Where. The agent runs in an isolated pod with no repo checkout, producing logs and side effects (e.g., queries Slack, posts to a database). Scheduled/webhook-driven runs of this flavor are the common case.

Read the full file on GitHub · 304 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. 2d ago First seen · 304 lines · 6,856 tokens per session scan B 30973a282aa6

Subscribe to this mod's changes

optio CLAUDE.md is an instructions file published in the GitHub repository jonwiggins/optio (1,043 stars, last pushed 22d ago), licensed MIT. It adds 6,856 tokens to every session, about $0.0343 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Building agentsCloudDevOps and cloudagentagentsaiclaude-codecopilotgemini
Related

Other instructions, from other repositories

adk-go AGENTS.md

AGENTS.md instructions for google/adk-go, covering agents.md, project overview, skills, setup & core commands and definition of done.

google/adk-go · 2,451 tokens

adk-python AGENTS.md

Instructions for google/adk-python, covering project overview, key components, adk knowledge, architecture, and style, project architecture and development setup.

google/adk-python · 322 tokens

trueforge AGENTS.md

AGENTS.md instructions for truefoundry/trueforge, a project described as: The open-source agent harness - the runtime layer that turns an LLM into a working agent.

truefoundry/trueforge · 1,151 tokens

DevoxxGenieIDEAPlugin GEMINI.md

Instructions for devoxx/DevoxxGenieIDEAPlugin, a project described as: DevoxxGenie is an agentic plugin for IntelliJ IDEA that uses local LLM's (Ollama, LMStudio, GPT4All, Jan and Llama.cpp) and Cloud based LLMs to help review, test, explain your project code. Latest version now also supports Spec Driven Development…

devoxx/DevoxxGenieIDEAPlugin · 257 tokens

codex-settings AGENTS.md

Instructions for feiskyer/codex-settings, covering repository guidelines, repository structure, validation commands, toml syntax and plugin package and marketplace.

feiskyer/codex-settings · 1,236 tokens

agent-skills AGENTS.md

AGENTS.md instructions for tech-leads-club/agent-skills, covering agents.md, workflow orchestration, 1. plan mode default, 2. subagent strategy and 3. verification before done.

tech-leads-club/agent-skills · 1,570 tokens