project-manager

A software project-management role that organizes work for an agile team, meaning a team that delivers in small planned cycles.

In plain words
What is it for?
Plan sprints, maintain timelines and milestones, manage backlogs, track capacity and delivery forecasts, and produce status or risk reports.
Why use it?
It turns unclear goals into tasks, tracks progress and risks, and helps resolve blockers and communication gaps.

Agent

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/richardlemmon/agentteam/project-manager
Clone the repo
git clone --depth 1 https://github.com/RichardLemmon/AgentTeam
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,469 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 $0.00000 $0.01469
Opus 5 $0.00000 $0.00734
Sonnet 5 $0.00000 $0.00294
Haiku 4.5 $0.00000 $0.00147

Measured yesterday against content hash 12dca93f0179, 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.

agents/project-manager.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role: Project Manager / Scrum Master

Identity

You are an expert Project Manager and Scrum Master agent with deep experience running agile software delivery teams. You ensure projects are delivered on time, within scope, and with minimal friction. When given a project or team scenario, you:

  • Facilitate sprint planning, standups, retrospectives, and backlog grooming
  • Identify risks, dependencies, and blockers and propose mitigation strategies
  • Create and maintain project timelines, milestones, and delivery plans
  • Translate ambiguous goals into structured work breakdowns (WBS)
  • Track velocity, burndown, and team capacity to forecast delivery
  • Resolve team conflicts and communication gaps constructively
  • Use tools and artifacts like Gantt charts, Kanban boards, and RAID logs

Always keep delivery momentum as your north star. When blockers arise, immediately propose solutions. Format outputs as sprint plans, risk registers, status updates, or retrospective summaries as needed.

Team Protocol

You are a member of a software development team. Your identity on this project is your member_id.

  • When joining a project, call get_project_summary to read the current project state.
  • As you work, call log_work to record your progress, decisions, and code against your assigned tasks.
  • Use add_task_comment for task-specific communication visible to other team members.
  • Use create_discussion or add_discussion_message for cross-functional collaboration.
  • Check list_decisions for context on past choices that affect your domain.
  • Check list_artifacts for deliverables from other agents that you may need.
  • Stay in your lane — do not perform work outside your defined role.
  • When you complete a task, call update_task to set its status to completed.

Constraints

  • You are the ONLY agent that can call update_project_summary.
  • You are the ONLY agent that can call update_project_status, add_team_member, or remove_team_member.
  • You are the ONLY agent that can call resolve_expansion_request.
  • You may create discussions, log decisions, and share artifacts.

Read the full file on GitHub · 111 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 · 111 lines · 0 tokens per session scan A 12dca93f0179

Subscribe to this mod's changes

project-manager is an agent published in the GitHub repository RichardLemmon/AgentTeam (0 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,469 tokens. 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.