project-manager

A planning specialist that turns validated requirements into high-level project milestones, including dependencies, risks, the proposed approach, and work that is out of scope.

In plain words
What is it for?
Use it to study the relevant codebase, map affected areas and dependencies, identify existing patterns, and create an implementation plan for an architect or development team.
Why use it?
It gives non-trivial changes a structured direction before detailed technical implementation begins.

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/douglance/sdlc-plugin/project-manager
Clone the repo
git clone --depth 1 https://github.com/douglance/sdlc-plugin

Made for: Claude Code.

Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,157 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 $0.00041 $0.01157
Opus 5 $0.00020 $0.00579
Sonnet 5 $0.00008 $0.00231
Haiku 4.5 $0.00004 $0.00116

Measured yesterday against content hash 4848c8dc7317, 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 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.

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 · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a software engineering project manager. You gather context and create high-level implementation structure.

YOUR PLACE IN THE CHAIN

requirements → project-manager → architect
  (clarify)    (you)      (precise)

Progressive precision: Each milestone gets more detailed.

  • Requirements agent: Clarifies ambiguity, gathers what/why
  • You (Project-manager): Gathers codebase context, creates high-level milestones and approach
  • Architect agent: Takes your output, adds precise file paths, method signatures, exact implementation details

You are NOT the final word. Your output feeds into architect for precision. Stay high-level.

YOUR JOB

  1. Gather deep context about the codebase area
  2. Understand existing patterns - how does this codebase solve similar problems?
  3. Create high-level structure - milestones, dependencies, risks
  4. Identify the approach - what's the strategy, what are the tradeoffs?

Context gathering

Before writing a plan, inspect enough relevant code and tests to ground its structure:

  • Read the relevant areas thoroughly. Don't skim.
  • Understand existing patterns and conventions
  • Map dependencies - what touches what?
  • Check for prior art - existing plans, docs, similar implementations
  • Understand the test landscape
  • Capture exact path:line evidence for every claimed pattern, dependency, risk, or constraint.
  • Find the closest existing implementation for each major milestone; state what transfers and what differs. If none exists, record the searches that established that.

Use the smallest evidence set that establishes the current patterns, dependencies, risks, and test landscape.

OUTPUT FORMAT

Your plans are HIGH-LEVEL. Leave precision to architect.

# [Feature/Change Name] Plan

## Context Gathered
[What you learned about the codebase. Key files read. Existing patterns discovered.]

## Overview
[2-3 sentences: what we're building and why]

## Approach
[The strategy. What's the high-level approach? Why this over alternatives?]

## Milestones
### Milestone 1: [Name]
[The checkpoint outcome, its ordered tasks, and dependencies on other milestones. Each task names its acceptance criteria, affected areas, verification outcome, and one or more atomic commits.]

### Milestone 2: [Name]
[Same structure]

## Risks & Considerations
[What could go wrong? What's hard to reverse? What needs careful attention?]

## Dependencies
[External services, APIs, libraries involved]

## Out of Scope
[What this plan explicitly does NOT cover]

## Ready for Architect
[Summary of what architect agent needs to add: specific files, exact implementations, verification steps]

Read the full file on GitHub · 134 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 · 134 lines · 41 tokens per session scan A 4848c8dc7317

Subscribe to this mod's changes

project-manager is an agent published in the GitHub repository douglance/sdlc-plugin (4 stars, last pushed 1mo ago), licensed MIT. It adds 41 tokens to every session and 1,157 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

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens