AGENT_AUTONOMY

An automated development workflow where agents read GitHub Issues, a project's task list, then implement work and open pull requests. GitHub Issues are tracked work requests, and a pull request is a proposed change for review.

In plain words
What is it for?
Use it to source tasks for backend, frontend, and DevOps work, run project checks, and submit completed changes for review.
Why use it?
It reduces the need for a person to repeatedly assign tasks and coordinate routine development work.

Agent

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/team-commonly/commonly/agent_autonomy
Clone the repo
git clone --depth 1 https://github.com/Team-Commonly/commonly
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 2,312 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 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 $0.00000 $0.02312
Opus 5 $0.00000 $0.01156
Sonnet 5 $0.00000 $0.00462
Haiku 4.5 $0.00000 $0.00231

Measured yesterday against content hash b1ee9ca4a93b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

AGENT_AUTONOMY scanned grade A 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 yesterday.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s -H "Authorization: Bearer ${GITHUB_PAT}" \
docs/agents/AGENT_AUTONOMY.md · 223 lines

How it starts

The opening of the file, as written. The whole thing — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Autonomy System

Purpose: Dev agents (Theo/Nova/Pixel/Ops) autonomously source tasks from GitHub, implement them with acpx_run, and open PRs — without human direction.

Last Updated: March 26, 2026


Current Implementation (March 2026)

Dev Team Architecture

GitHub Issues
     ↓
  Theo (PM) — reads issues every 30min heartbeat
     ↓  writes board to Dev Team pod PVC
     ↓
  /state/pods/69b7ddff0ce64c9648365fc4/memory/memory.md
     ↓
  Nova (backend) ──── reads board ──── acpx_run ──── git clone / npm test / gh pr create
  Pixel (frontend) ── reads board ──── acpx_run ──── git clone / npm test / gh pr create
  Ops (devops) ─────  reads board ──── acpx_run ──── git clone / helm test / gh pr create

Task Board Format

Stored at /state/pods/{devPodId}/memory/memory.md on the gateway PVC. Written by commonly_write_memory(devPodId, "memory", content). Read by commonly_read_memory(devPodId, "memory").

# Dev Team Task Board

## Backend Tasks
- [ ] TASK-001: GH#1 — Add basic unit tests for backend functions — dep: none
- [x] TASK-000: GH#0 — Initial setup — PR #1

## Frontend Tasks

## DevOps Tasks

## Done

Format rules:

  • ### Section Name → column name in Board tab UI
  • - [ ] TASK-NNN: → pending task
  • - [x] TASK-NNN: → done task (move from section to Done)
  • Section names containing "backend" → Nova (blue); "frontend" → Pixel (purple); "devops" → Ops (orange)

Theo's Heartbeat Loop (PM Agent)

Every 30 minutes:

  1. Read Dev Team pod messages — check for human work requests
  2. Read task board (commonly_read_memory(devPodId, "memory"))
  3. Check recent GitHub PRs (search open PRs for nova/, pixel/, ops/ branches)
  4. Update board: mark PRs merged/closed → move tasks to Done
  5. If board has NO pending tasks AND no human work requests: auto-source from GitHub:
    curl -s -H "Authorization: Bearer ${GITHUB_PAT}" \
      "https://api.github.com/repos/Team-Commonly/commonly/issues?state=open&per_page=10" \
      | python3 -c "import sys,json; [print(f'#{i[\"number\"]}: {i[\"title\"]}') for i in json.load(sys.stdin) if 'pull_request' not in i]"
    
  6. Post ONE message to Dev Team pod summarizing assignments
  7. Reply HEARTBEAT_OK if nothing to do

Read the full file on GitHub · 223 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. yesterday First seen · 223 lines · 0 tokens per session scan A b1ee9ca4a93b

Subscribe to this mod's changes

AGENT_AUTONOMY is an agent published in the GitHub repository Team-Commonly/commonly (1,323 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,312 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.