project-manager

project-manager is an agent for Claude Code from kamiazya/whiteboard. It costs 45 tokens per session (402 once invoked), scanned A, original, Apache-2.0.

A planning review that turns a project initiative into ordered development units and milestones. It considers dependencies, risk, code ownership, and how each unit will be verified.

In plain words
What is it for?
Breaking work into acceptance-based slices, choosing sequential or parallel implementation paths, identifying the riskiest area, and defining tests and completion gates.
Why use it?
It makes large changes easier to deliver by separating foundation work from user-facing behavior and showing what must happen first.

Agent for Claude Code

Part of the whiteboard plugin — 18 skills, 18 agents, 3 hooks, 1 MCP server shipped together

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/kamiazya/whiteboard/project-manager
Clone the repo
git clone --depth 1 https://github.com/kamiazya/whiteboard

Made for: Claude Code.

Or install whiteboard, the plugin that ships this one along with the rest of its 18 skills, 18 agents, 3 hooks, 1 MCP server.

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 project-manager

README.md
[![agentmods](https://agentmods.dev/badge/agents/kamiazya/whiteboard/project-manager.svg)](https://agentmods.dev/agents/kamiazya/whiteboard/project-manager)
Your own site
<a href="https://agentmods.dev/agents/kamiazya/whiteboard/project-manager"><img src="https://agentmods.dev/badge/agents/kamiazya/whiteboard/project-manager.svg" alt="Measured on agentmods" height="20"></a>
Per session 45 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 402 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 $0.00045 $0.00402
Opus 5 $0.00023 $0.00201
Sonnet 5 $0.00009 $0.00080
Haiku 4.5 $0.00005 $0.00040

Measured 4d ago against content hash 5ca506b2c14e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

project-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 4d 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/project-manager.md · 22 lines

What it actually says

You are the PROJECT MANAGER perspective on a planning panel for the whiteboard project. Turn the initiative into a deliverable, sequenced plan. Ground slicing in the real code surface.

Cover:

  • Slicing: break into units each with ONE acceptance boundary and ~ONE write scope (so each can run as a single dev-loop task). Foundation/interface/schema/test-harness separated from user-facing behavior; mock/connection separated from real-data wiring.
  • Dependencies & order: what must land first; what can run in parallel worktrees; where reconcile is needed. Say which shape each group is: slices that must land in dependency order are a stack (one PR per layer, merged bottom-up in one atomic operation), slices with disjoint write scope are parallel worktrees. Order a stack by architecture-map.md's dependency direction — composition roots (mcp-server, apps/web) are always its top layer, never its base. Only propose a stack when each lower layer is worth reviewing on its own.
  • Risk: which slice is highest-risk (spike it first); rollback/fallback per slice.
  • Milestones & gates: per-slice verification (nearest-layer tests, smoke, manual dogfood), and what "done" means.
  • Owned files / do-not-edit per parallel slice to avoid collisions.
  • Open questions for humans: scope/priority/sequencing trade-offs needing a decision.

Optimize for small, safe, reviewable increments over big-bang. Output the sliced plan (ordered), parallelizable set, risks, and openQuestions.

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. 4d ago First seen · 22 lines · 45 tokens per session scan A 5ca506b2c14e

Subscribe to this mod's changes

project-manager is an agent published in the GitHub repository kamiazya/whiteboard (6 stars, last pushed today), licensed Apache-2.0. It adds 45 tokens to every session and 402 once invoked, about $0.0002 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 2026-08-31.

Related

Other agents, from other repositories

codemap

Defines agent personalities (Orchestrator, Explorer, Librarian, etc.) and manages their configuration lifecycle. This directory implements the Agent Factory Pattern, where each agent is a specialized sub-agent with distinct capabilities, permissions, and routing rules. The Orchestrator agent (src/agents/index.ts)…

alvinunreal/oh-my-opencode-slim · 0 tokens

grasshopper-scripter

Use proactively for building, editing, or solving Grasshopper definitions on the user's canvas — placing components, wiring them up, setting slider values, and running the solver.

mcneel/RhinoAI · 39 tokens

ad-tech-protocol-expert

Expert on ad tech protocols (OpenRTB, IAB VAST/VPAID, MRAID, DBCFM, AdCP, TMP). Use when evaluating protocol-level changes — new task definitions, schema additions, field semantics, cross-protocol compatibility, or spec ambiguities.

adcontextprotocol/adcp · 65 tokens

red-team-reviewer

Adversarial reviewer that audits epic Success Criteria → story Done Definition coverage and attacks preplanning story maps for cross-story blind spots, implicit assumptions, and interaction gaps across 8 taxonomy categories. Requires opus.

navapbc/digital-service-orchestra · 46 tokens

foundation_architecture

Status: Draft Purpose: Define the minimal viable system architecture and cross‑reference OpenHands SDK capabilities with Tier 0 questions to guide incremental development. Related: ./openhandsinsightsandprioritization.md, ./implementationquestions.md, ./design/multiagentorchestration.md.

kivo360/OmoiOS · 0 tokens

chainaware-token-launch-auditor

Audits a new token launch for launchpads by combining rug pull detection on the contract with fraud and behavioral analysis on the deployer wallet. Returns a composite Launch Safety Score, a APPROVED / CONDITIONAL / REJECTED listing verdict, a public-facing safety badge, and specific conditions the launchpad should…

ChainAware/behavioral-prediction-mcp · 247 tokens