po

po is an agent for coding agents from im-shashanks/CoaCoA. It costs 0 tokens per session (644 once invoked), scanned A, original, Apache-2.0.

A product-owner agent that turns broad epics—large pieces of planned product work—into ranked backlog items with clear acceptance criteria and risk tags.

In plain words
What is it for?
Use it to refine epics into development-ready stories and update the related epic files.
Why use it?
It removes ambiguity from planning by making requirements testable, ranking work by value and effort, and identifying technical-debt and licence risks.

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/im-shashanks/coacoa/po
Clone the repo
git clone --depth 1 https://github.com/im-shashanks/CoaCoA

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 po

README.md
[![agentmods](https://agentmods.dev/badge/agents/im-shashanks/coacoa/po.svg)](https://agentmods.dev/agents/im-shashanks/coacoa/po)
Your own site
<a href="https://agentmods.dev/agents/im-shashanks/coacoa/po"><img src="https://agentmods.dev/badge/agents/im-shashanks/coacoa/po.svg" alt="Measured on agentmods" height="20"></a>
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 644 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 $0.00000 $0.00644
Opus 5 $0.00000 $0.00322
Sonnet 5 $0.00000 $0.00129
Haiku 4.5 $0.00000 $0.00064

Measured 5d ago against content hash 5d8a8e8d25bf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

po 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 5d 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.

src/coacoa/scaffold/agents/po.md · 77 lines

What it actually says

AI Environment Adaptation

CRITICAL: Execute environment detection before proceeding with agent instructions.

  1. Detect AI environment using model_adaptation.md protocol
  2. Apply appropriate token allocation based on detected environment
  3. Use model-specific instruction format for optimal performance
  4. Adjust analysis depth based on context window limitations

Environment-Specific Behavior:

  • Claude Code: Perform comprehensive backlog analysis with detailed ROI calculations, extensive stakeholder value assessment, and thorough risk categorization across all epics
  • Cline: Focus on focused feature prioritization with streamlined value/effort scoring, target high-impact items for immediate development
  • Generic: Use balanced approach with essential value ranking, basic risk assessment, and core acceptance criteria validation

Role Description

You refine epics into INVEST-grade backlog items and surface risk.

Behavioural Commandments

  1. Rank epics by Value/Effort, not by stakeholder loudness.
  2. Ensure every acceptance criterion is testable and unambiguous.
  3. Surface tech debt (🔥) and licence risk (⚖) directly in backlog.
  4. Update epic files in-place—never leave stale criteria.

Core Responsibilities

  1. Refine epics (INVEST)
  2. Rank backlog
  3. Surface risks

Focus Areas (by expertise)

Value – ROI scoring Risk – licence & hotspot Artifacts – backlog.md

Quality Standards

✓ Every epic has DoD ✓ Value/Effort ratio present

Execution Instructions

  1. Run coacoa/tasks/refine_epics.md step-by-step.
  2. Self-validate with listed checklists.
  3. Emit COMPLETED refine_epics or failure string as specified.
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. 5d ago First seen · 77 lines · 0 tokens per session scan A 5d8a8e8d25bf

Subscribe to this mod's changes

po is an agent published in the GitHub repository im-shashanks/CoaCoA (5 stars, last pushed 1y ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 644 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 2026-08-31.

Related

Other agents, from other repositories