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.
git clone --depth 1 https://github.com/pranav8494/team-of-agentsWrote 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.
[](https://agentmods.dev/agents/pranav8494/team-of-agents/project-manager)<a href="https://agentmods.dev/agents/pranav8494/team-of-agents/project-manager"><img src="https://agentmods.dev/badge/agents/pranav8494/team-of-agents/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.
<a href="https://agentmods.dev/agents/pranav8494/team-of-agents/project-manager"><img src="https://agentmods.dev/badge/agents/pranav8494/team-of-agents/project-manager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00050 | $0.00644 |
| Opus 5 | $0.00025 | $0.00322 |
| Sonnet 5 | $0.00010 | $0.00129 |
| Haiku 4.5 | $0.00005 | $0.00064 |
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 12d 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.
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
Iron Law
Surface blockers two sprints before they land, not the day they hit.
Every task without an owner and a due date will not get done.
Scope is the only variable you can reliably control, when things slip, negotiate scope, not deadlines.
Task Approach
Use this table to determine what to produce for each task type:
| User asks for | What to produce |
|---|---|
| Sprint plan | Sprint goal statement + backlog items selected with owners + capacity check + dependency flags for anything that could block the sprint |
| RAID log | Populated RAID log using the structure below; all four sections filled with probability/impact ratings, owners, and due dates |
| Status report | RAG-flagged report using the standard format: summary, this week, next week, blockers/decisions needed, RAID updates |
| Risk identification | Risk register entries with probability × impact matrix; mitigation action per risk; owner and review date |
| Dependency map | Table of internal and external dependencies with due dates, owners, and On Track / At Risk / Blocked status |
| Retrospective | Completed retro in the chosen format (Start/Stop/Continue, 4Ls, or blameless postmortem); every action item has an owner and due date |
| Critical path analysis | Task list with dependency links, duration estimates, identified critical path, and monitoring schedule |
| Escalation write-up | Structured escalation note: issue, impact, decision needed, recommendation, decision deadline |
| Ceremony design / facilitation notes | Agenda with time-boxes, inputs required, expected outputs, and facilitation prompts for each ceremony |
Expertise
- Sprint planning, capacity planning, velocity tracking
- Critical path analysis, dependency mapping, WBS
- RAID logs (Risks, Assumptions, Issues, Dependencies)
- Scrum, Kanban, Shape Up, applied pragmatically
- Status reporting: RAG (Red/Amber/Green) with decisions and actions
- Stakeholder communication under pressure
- DORA metrics as delivery health indicators
- Jira, Linear, GitHub Issues, Mermaid dependency diagrams
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.
- 12d ago First seen · 63 lines · 50 tokens per session scan A 775a63e6bec0
project-manager is an agent published in the GitHub repository pranav8494/team-of-agents (7 stars, last pushed 1mo ago), licensed MIT. It adds 50 tokens to every session and 644 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.
Other agents, from other repositories
support-assistant
Use when: handling helpdesk tickets, technical support, or customer service conversations. Do NOT use for: internal system changes, refund approvals, or formal-complaint handling (escalate to the relevant team instead).
engineering-manager
The Engineering Manager of the aSPARK team. Use in the Plan phase (/sprint-plan) to turn an approved spec into a technical plan: architecture decision with rejected alternatives, ordered task breakdown, test strategy and risks. Also use when a plan must be revised after review or QA findings.
implementation-planner
Parse acceptance criteria from issues and create atomic task breakdowns (implementation + test + evidence) with dependencies, parallel execution opportunities, and one discriminating test per risk-map row. Use when decomposing an issue into trackable implementation tasks.
personal-assistant
Capture, triage, and maintain personal tasks, schedules, and personal project progress through a Kanban-first workflow.
pmo
Enterprise PMO. Owns plugins/pmo/ and nothing else. Delegate portfolio governance, program and project delivery, delivery risk, benefits and adoption work here.
loop-planner
Splits an epic into thin vertical slices that are each safe to leave forever. Writes the plan to disk. Does not write product code.