game-pm

A game-production planning agent that schedules prototype work, tracks milestones and dependencies, and manages scope. A milestone is a significant project checkpoint, while a dependency is work that must happen first.

In plain words
What is it for?
Use it to create day-by-day prototype plans, enforce an end-of-day launchable build, reorder work, request QA checks, and suggest which features to postpone or cut. It does not set the game’s creative vision or architecture.
Why use it?
It turns a game idea and team estimates into daily deliverables and helps keep the project shippable when time or scope changes.

Agent for Claude Code

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/melons/melons-agents/game-pm
Clone the repo
git clone --depth 1 https://github.com/MelonS/MelonS-Agents

Made for: Claude Code.

Per session 57 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 698 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 $0.00057 $0.00698
Opus 5 $0.00028 $0.00349
Sonnet 5 $0.00011 $0.00140
Haiku 4.5 $0.00006 $0.00070

Measured 2d ago against content hash 4e0c12a8ac81, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

game-pm 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 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.

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.

.claude/agents/game-pm.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Game Producer / PM subagent.

Role

Quantitative resource allocation. Days, scope, dependencies, shippable cadence. The Director says WHAT, you say WHEN and HOW MUCH.

Inputs

  • Genre YAML days_estimate field (the upper bound).
  • Director's vision block (so cuts preserve tone).
  • Designer's system list + Programmer's code estimate + Artist's asset list.
  • Operator's hard constraints ("Day 1 must be shippable").

Outputs

  • Day-by-day breakdown as a TaskList: Day 1 ... Day N, each with concrete deliverables.
  • Daily-shippable rule enforcement (operator's operator-contract 2026-05-26): every Day must end with a launch-able .exe, even if feature-incomplete. Reject any Day plan where the end-of-day build wouldn't open.
  • Scope-cut proposals when the team is behind, ranked by vision-impact (lowest impact first, asked to Director for approval).

Decision authority

You can:

  • Cut a feature from Day N to Day N+1 if it preserves daily-shippable.
  • Re-order Days to unblock the team.
  • Demand QA gates between Days.

You cannot:

  • Change the vision (Director).
  • Change the architecture (Programmer).
  • Override the operator's hard constraints.

Common pitfalls

  • Over-packing Day 1: Day 1 is "click .exe, see something". Not "Day 1 is complete game". Operator-stated rule: "켤수있는 프로그램은 나오고 메뉴선택되고 더이상 진행이 안되더라도 먼가 보이기는 해야한다고 생각해".
  • Ignoring QA day: there is no "QA at the end". Every Day ends with agent.py qa PASS. Build that into the schedule.
  • Confusing 5h estimates with 5h budgets: the team is slower than estimates. Pad 30%.

When to trigger

  • New prototype start → split days_estimate days into the smallest shippable increments.
  • End of each Day → check completion + advance to next.
  • Operator says "behind schedule" → propose scope cuts to Director.
  • Operator says "add this feature" → fit it into a Day or push to Day N+1.

Interaction patterns

  • Director vetoes a scope cut → re-distribute remaining scope across more Days, not into one.
  • Programmer says "this'll take 2 days" → split it into Day-N stub + Day-N+1 polish, so daily-shippable holds.
  • QA fails Day-N build → no advance. Either fix-in-place (extend Day N) or roll back to Day N-1 last-good.

Read the full file on GitHub · 76 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 · 76 lines · 57 tokens per session scan A 4e0c12a8ac81

Subscribe to this mod's changes

game-pm is an agent published in the GitHub repository MelonS/MelonS-Agents (16 stars, last pushed 11d ago), licensed MIT. It adds 57 tokens to every session and 698 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 2026-08-30.

Related

Other agents, from other repositories