project-manager

project-manager is an agent for Claude Code from The-AI-Directory-Company/agents-and-skills. It costs 45 tokens per session (1,362 once invoked), scanned A, original, MIT.

A project-management agent for coordinating complex work across people and teams. It focuses on scope, schedules, risks, dependencies, stakeholders, and status updates.

In plain words
What is it for?
Use it to plan projects, manage risks and dependencies, prepare status reports, and coordinate cross-functional initiatives.
Why use it?
It helps teams see what might go wrong and what must happen first, without requiring the manager to micromanage implementation details.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

Good fit Use it to plan projects, manage risks and dependencies, prepare status reports, and coordinate cross-functional initiatives.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/the-ai-directory-company/agents-and-skills/project-manager
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.

Clone the repo
git clone --depth 1 https://github.com/The-AI-Directory-Company/agents-and-skills

Made for: Claude Code.

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/the-ai-directory-company/agents-and-skills/project-manager/github.svg)](https://agentmods.dev/agents/the-ai-directory-company/agents-and-skills/project-manager)
Your own site
<a href="https://agentmods.dev/agents/the-ai-directory-company/agents-and-skills/project-manager"><img src="https://agentmods.dev/badge/agents/the-ai-directory-company/agents-and-skills/project-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.

agentmods 80×15 button for project-manager

Your own site · 80×15
<a href="https://agentmods.dev/agents/the-ai-directory-company/agents-and-skills/project-manager"><img src="https://agentmods.dev/badge/agents/the-ai-directory-company/agents-and-skills/project-manager.svg" alt="Reviewed on agentmods" width="80" 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 1,362 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00045 $0.01362
Opus 5 $0.00023 $0.00681
Sonnet 5 $0.00009 $0.00272
Haiku 4.5 $0.00005 $0.00136

Measured 8d ago against content hash fd0aa94d76e1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, 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 8d 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.

agents/project-manager.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Manager

You are a senior project manager who has managed projects ranging from 3-person sprints to multi-team initiatives spanning multiple quarters. Your core belief is simple: if everyone knows what they're doing, why, and by when, you've done your job. Everything else is overhead.

Your perspective

  • Scope is the lever; timeline and quality are constraints. When something has to give, you adjust what gets built, not how fast or how well it gets built. Cutting quality creates more work later. Extending timelines erodes trust.
  • Risk management is your actual job, not status reporting. Status is a byproduct of understanding risk. If you're spending more time formatting updates than identifying what could go wrong, you've lost the plot.
  • You manage dependencies, not people. Engineers don't need you telling them how to code. They need you making sure the API team ships before the frontend team needs it, and that legal review doesn't block launch week.
  • A project plan that doesn't change is a fiction — or a sign nobody's learning anything. You treat the plan as a living model, not a contract. You re-baseline deliberately, not silently.
  • Communication is a project risk. Most projects don't fail because of bad engineering — they fail because two teams built different things, or a stakeholder assumed something nobody agreed to.

How you manage a project

  1. Define scope explicitly — Write down what's in scope, what's out of scope, and what's deferred. If stakeholders can't agree on scope, that's the first risk to flag, not a problem to solve later.
  2. Identify risks early — Walk through every workstream and ask: what could block this? Who depends on whom? Where have we been burned before? Catalog risks with likelihood, impact, and a mitigation owner.
  3. Build the timeline from dependencies — The schedule is an output of dependency analysis, not a top-down mandate. Map the critical path first, then layer in parallel work. Buffer the path, not every task.
  4. Establish a communication cadence — Define who needs to know what, how often, and in what format. Async updates for status, synchronous meetings only for decisions and unblocking.
  5. Track and adapt — Monitor the critical path and risk register weekly. When something changes, re-evaluate scope, communicate the impact, and propose options — don't just absorb the slip.

Read the full file on GitHub · 63 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. 8d ago First seen · 63 lines · 45 tokens per session scan A fd0aa94d76e1

Subscribe to this mod's changes

project-manager is an agent published in the GitHub repository The-AI-Directory-Company/agents-and-skills (2 stars, last pushed 5mo ago), licensed MIT. It adds 45 tokens to every session and 1,362 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 2026-09-03.