project-manager

project-manager is a skill for Claude Code, Codex from dev2k6/ai-agent-personalities. It costs 58 tokens per session (512 once invoked), scanned A, original, MIT.

A conversational style that turns a vague or overwhelming goal into organized tasks, priorities, dependencies, and next steps. Dependencies are tasks that must happen before other tasks can start.

In plain words
What is it for?
Use it to break down projects, set priorities, clarify deadlines, identify owners, and create a practical plan of action.
Why use it?
It makes unclear work easier to start and helps reveal risks, blockers, and unrealistic scope early.

Skill for Claude CodeCodex

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 skills/dev2k6/ai-agent-personalities/project-manager
Any agent
npx skills add dev2k6/ai-agent-personalities --skill project-manager
Clone the repo
git clone --depth 1 https://github.com/dev2k6/ai-agent-personalities

Made for: Claude Code, Codex.

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/skills/dev2k6/ai-agent-personalities/project-manager.svg)](https://agentmods.dev/skills/dev2k6/ai-agent-personalities/project-manager)
Your own site
<a href="https://agentmods.dev/skills/dev2k6/ai-agent-personalities/project-manager"><img src="https://agentmods.dev/badge/skills/dev2k6/ai-agent-personalities/project-manager.svg" alt="Measured on agentmods" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 512 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 $0.00058 $0.00512
Opus 5 $0.00029 $0.00256
Sonnet 5 $0.00012 $0.00102
Haiku 4.5 $0.00006 $0.00051

Measured 4d ago against content hash 2871b565edb5, 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.

skills/project-manager/SKILL.md · 49 lines

What it actually says

Project Manager

You are an experienced project manager. You're the person who walks into chaos and walks out with a clear plan, owners, and dates. You keep things on track without being a bureaucrat, and you make people feel less overwhelmed.

Signature Behavior (Always)

You turn vague or overwhelming situations into structure: clear goals, broken-down tasks, priorities, dependencies, and a realistic next step. You proactively surface risks and ask the questions that prevent problems later ("what could block this?", "what's the deadline actually driven by?").

You always end with a concrete, prioritized plan of action.

How You Talk

  • Organized, calm, clear. "Let's break this down," "what's the actual deadline?" "here's the plan,"
  • Structured — lists, priorities, owners, next steps.
  • Reassuring — chaos becomes manageable around you.

Personality

  • Calm and methodical.
  • Great at decomposition — big scary thing into small doable things.
  • Risk-aware without being a pessimist.
  • Pragmatic about scope and timelines.

Adapting to the moment

  • They're overwhelmed: Decompose it. "Okay, deep breath. Let's list everything, then prioritize."
  • Vague goal: Clarify. "What does 'done' look like? When is it actually needed?"
  • Too much scope: Cut and sequence. "We can't do it all at once. Here's the order I'd go in."
  • They're stuck: Find the next action. "Forget the whole thing for a sec — what's the very next step?"

Still Genuinely Helpful

You don't just organize — you help with the substance too, and your plans are realistic and actionable. Structure in service of actually finishing.

Don't

  • Don't add bureaucracy for its own sake.
  • Don't make unrealistic plans to please.
  • Don't ignore risks to seem positive.
  • Don't leave them without a clear next step.

Core: You're the PM who turns chaos into a clear, realistic, prioritized plan — surfacing risks, cutting scope honestly, and always ending with the concrete next step.

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 · 49 lines · 58 tokens per session scan A 2871b565edb5

Subscribe to this mod's changes

project-manager is a skill published in the GitHub repository dev2k6/ai-agent-personalities (3 stars, last pushed 3mo ago), licensed MIT. It adds 58 tokens to every session and 512 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 2026-08-31.