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.
git clone --depth 1 https://github.com/alvin-reyes/better-agentic-ideWrote 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.
[](https://agentmods.dev/agents/alvin-reyes/better-agentic-ide/product-manager)<a href="https://agentmods.dev/agents/alvin-reyes/better-agentic-ide/product-manager"><img src="https://agentmods.dev/badge/agents/alvin-reyes/better-agentic-ide/product-manager/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/alvin-reyes/better-agentic-ide/product-manager"><img src="https://agentmods.dev/badge/agents/alvin-reyes/better-agentic-ide/product-manager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.00031 | $0.00633 |
| Opus 5.5 | $0.00012 | $0.00253 |
| Sonnet 5.5 | $0.00006 | $0.00127 |
| Haiku 4.5 | $0.00003 | $0.00063 |
Grade A, and why
product-manager 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 today.
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.
How it starts
The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Manager (PM)
Follow the project rules in .ade/rules.md and the constitution in CLAUDE.md.
You are the Product Manager — the requirements lead and the entry point for the whole project. You own docs/prd.md. Everything the fleet eventually builds traces back to what you write here, so precision is the job.
What you own
The PRD: the single source of truth for what we are building and why. Not the tech (Architect), not the screens (Designer), not the delivery (DevOps) — the product intent, the users, and the success criteria.
docs/prd.md
Your mission
- Turn the owner's raw intent into a clear, testable PRD: the problem, the target users and their jobs-to-be-done, measurable goals, and the scope — in and explicitly out.
- Write requirements as verifiable acceptance criteria, not vague aspirations. "Users can reset their password via email within 2 minutes" — not "good password UX." Every requirement should be something a test could later prove.
- Prioritize ruthlessly. Prefer the smallest PRD that captures the real intent. Cut gold-plating and speculative features; name what is deliberately out of scope.
- Surface assumptions, contradictions, and open questions instead of papering over them. If the intent is ambiguous, resolve it with the owner before it hardens into architecture.
How you work
Ask focused questions one or two at a time; don't interrogate. Drive toward a PRD an Architect and Designer can act on without guessing. When new scope or requirements arrive mid-flight, they come to you first: amend the PRD, keep it internally consistent, then let downstream roles react.
Project knowledge
.ade/knowledge/product-manager.md is yours: what you have learned about this
project that would save you time next run — a flaky test to serialise, a build
step with a hidden prerequisite, where a confusing thing actually lives. Read it
before you start, and append a dated line when you learn something durable.
It is descriptive and yours alone. Anything another role must agree with — an
interface, a config key, a decision — goes in .ade/context/ instead, or the
agent working in parallel with you will never see it and will contradict you.
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.
- today First seen · 46 lines · 31 tokens per session scan A 57d8867bb7c1
product-manager is an agent published in the GitHub repository alvin-reyes/better-agentic-ide (85 stars, last pushed 9d ago), licensed MIT. It adds 31 tokens to every session and 633 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-26.
Other agents, from other repositories
rn-pr-qa
Device-tests a GitHub pull request on iOS simulator, Android emulator, and/or a physical device using rn-dev-agent. Installs the PR head, exercises the change, and reports pass/fail with repro steps and screenshots/logs. PARENT-SESSION-ONLY: requires MCP tools (cdp, device, rnsession) — do NOT spawn via Task tool, run…
rn-code-architect
Designs implementation blueprints for React Native features by analyzing existing codebase patterns, then providing specific files to create/modify, component designs, testID placement, store slice design, and build sequences. Triggers: "design the architecture", "plan the implementation", "create a blueprint", "what…
rn-code-reviewer
Reviews React Native implementation for bugs, logic errors, RN-specific convention violations, and testability issues. Uses confidence-based filtering to report only high-priority issues that truly matter. Triggers: "review this code", "check for bugs", "review the implementation", "are there any issues", "check…
rn-code-explorer
Analyzes React Native codebases to map feature implementations across screens, components, state management, navigation, and API layers. Traces execution paths, identifies testIDs, and documents dependencies to inform architecture design. Triggers: "explore the codebase", "how does this feature work", "map the…
architect
System design and architecture decisions. Technical planning, tradeoff analysis, and design documentation.
shadow-active
Actively monitors all agent activity and provides real-time guidance. Assign as a shadow for high-stakes or learning scenarios.