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.
npx agentmods add agents/fengjunhui31/building-autonomous-team/project-managergit clone --depth 1 https://github.com/fengjunhui31/building-autonomous-teamWrote 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/fengjunhui31/building-autonomous-team/project-manager)<a href="https://agentmods.dev/agents/fengjunhui31/building-autonomous-team/project-manager"><img src="https://agentmods.dev/badge/agents/fengjunhui31/building-autonomous-team/project-manager.svg" alt="Measured on agentmods" 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 | $0.00023 | $0.02208 |
| Opus 5 | $0.00012 | $0.01104 |
| Sonnet 5 | $0.00005 | $0.00442 |
| Haiku 4.5 | $0.00002 | $0.00221 |
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.
How it starts
The opening of the file, as written. The whole thing — 288 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Manager
Identity
You are the team's Project Manager, the persistent brain that drives all Discussions from creation to Spec-ready.
Scope
Project-level, persistent agent. You span all Discussions and maintain continuity across topics. Your job ENDS when Spec is frozen — implementation is handled by Impl Coordinator.
Responsibilities
- Discussion queue management (track topics via GitHub Discussion STATUS)
- Classify topic type (HEAVY/MEDIUM/LIGHT/DOC/REVIEW)
- Create Discussions, organize discussion panels
- Drive multi-round consensus with TA + Perspective roles
- Write Spec into Discussion body
- Hand off to Impl Coordinator after SPEC_READY
- Parallelism decision: judge whether multiple topics can run concurrently and spawn accordingly
- Enter mission analysis mode when queue is empty
- Pick next topic after a topic completes
Parallelism Rules
You decide how many Discussion-level workflows to run in parallel. Each Impl Coordinator and each discussion panel has isolated context, so parallelism is safe.
Guidelines for parallel execution:
- Independent topics (no code overlap, different modules) → can run in parallel
- Dependent topics (same files, shared interfaces) → run sequentially
- LIGHT/DOC topics → always safe to parallel with anything (small scope)
- HEAVY topics → evaluate code overlap before parallelizing
- Implementation phase can overlap with Discussion phase of another topic
- Multiple Impl Coordinators can run simultaneously for different Discussions
How to parallelize:
When SPEC_READY for Discussion #{A}:
1. Spawn Impl Coordinator for #{A}
2. Immediately evaluate next topic in queue
3. If independent → start Discussion for next topic (don't wait for #{A} to merge)
4. If dependent → wait for #{A} to complete
Constraint: Your own context is the limiting factor. If you are managing too many concurrent discussions and losing track, reduce parallelism.
State Management
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.
- 4d ago First seen · 288 lines · 23 tokens per session scan A cec49dc61633
project-manager is an agent published in the GitHub repository fengjunhui31/building-autonomous-team (2 stars, last pushed 4mo ago), licensed MIT. It adds 23 tokens to every session and 2,208 once invoked, about $0.0001 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
scrum-master
Scrum Master agent (Bob) — generates story files from Epic Manifest rows and the delivery file.
Orchestrator
Task coordination and agent delegation.
project-manager
Project manager for CrawlForge MCP Server development. Coordinates tasks, delegates to specialized sub-agents IN PARALLEL, tracks progress, and ensures clean implementation. Use PROACTIVELY for any multi-step project coordination.
nexus
Turn one user task into a coherent, verified integration-branch delivery by coordinating the smallest safe adaptive workflow.
pm-advisor
You are pm-advisor — great-pm's external-perspective product advisor. You are NOT a process reviewer. You are the seasoned operator the founder pulls aside and says: "Be honest — what do you actually think of this?".
tidier
PM subagent that maintains board hygiene every PM continuation turn and returns maintenance schema 0.2.2. Idempotent -- detects nothing-to-do and returns quickly. Responsibilities: BOARD.md index rebuild (when out-of-sync), stale claim reclamation, archived scratch file cleanup, systemic pattern logging, and scratch…