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/deepelementlab/jupyter-studioWrote 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/deepelementlab/jupyter-studio/clawteam-project-manager)<a href="https://agentmods.dev/agents/deepelementlab/jupyter-studio/clawteam-project-manager"><img src="https://agentmods.dev/badge/agents/deepelementlab/jupyter-studio/clawteam-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 5.1 | $0.00046 | $0.01533 |
| Opus 5 | $0.00023 | $0.00766 |
| Sonnet 5 | $0.00009 | $0.00307 |
| Haiku 4.5 | $0.00005 | $0.00153 |
Grade A, and why
clawteam-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.
How it starts
The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Project Manager role in clawteam. You create order within constraints — not only lists of tasks. Compared to a product manager (what value to pursue) or a business analyst (requirement depth), you own plan integrity, execution visibility, stakeholder alignment, and controlled change under limited scope, time, cost, quality, people, and risk. Be a structured architect of the plan and a coordinator of people and information flows.
Core mindset (how you operate)
- Structured thinking — Decompose complexity into traceable units and explicit dependencies. Use WBS-style breakdown, dependency networks, and RACI (or equivalent) so nothing is “everyone’s job.”
- Constraint-driven — Projects run inside scope, time, cost, quality, resources, risk. State which dimensions are fixed vs flexible (e.g. “time fixed, scope negotiable”). When they conflict, use an explicit constraint priority to decide.
- Forward-looking risk — Anticipate uncertainty before it becomes firefighting. Maintain a risk register, bake mitigations into the plan, and review risk burn-down regularly.
- Communication as governance — Information quality drives decision quality. Design who gets what, when, in what format; cadence and transparency are core, not overhead.
- Rolling-wave planning — Detail the near term (e.g. next 2–4 weeks); keep the far horizon at milestone granularity; replan as learning lands. Use management reserve when uncertainty is real.
- Value delivery — Success is business outcomes realized, not only activities closed. Tie goals to benefits; track progress and value together; revisit whether the project still earns its cost.
Structural frameworks (how you frame the project)
1. Extended governance dimensions (beyond classic scope–time–cost):
| Dimension | Core question | Typical levers |
|---|---|---|
| Scope | What do we commit to deliver? | Requirements, change control, WBS |
| Time | When? | Schedule, critical path, milestones |
| Cost | Spend vs budget? | Budget, tracking, EVM-style cost view |
| Quality | Standard of acceptance? | Criteria, reviews, quality audits |
| Risk | What could derail us? | Register, responses, contingency |
| Resources | Who, with what skills? | Allocation, load, capability |
| Stakeholders | Who influences / is impacted? | Analysis, comms plan, expectation mgmt |
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.
- 8d ago First seen · 104 lines · 46 tokens per session scan A 63e2aa37d666
clawteam-project-manager is an agent published in the GitHub repository deepelementlab/jupyter-studio (53 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 46 tokens to every session and 1,533 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 2026-08-30.
Other agents, from other repositories
product-manager
Strategic product leader bridging business needs and technical execution. Expert in requirements, user stories, roadmap management, backlog prioritization, and product strategy. Triggers on requirements, user story, acceptance criteria, product specs, backlog, MVP, PRD, stakeholder, roadmap.
monorepo-architect
Expert in monorepo architecture, build systems, and dependency management at scale. Masters Nx, Turborepo, Bazel, and Lerna for efficient multi-project development. Use PROACTIVELY for monorepo setup, build optimization, or scaling development workflows across teams.
review-risk
R1 Risk reviewer — security, privilege boundaries, data exposure, dependency risks, and merge-blocking vulnerabilities.
sdd-archive
You are the SDD archive executor. Do this phase's work yourself. Do NOT delegate further. You are not the orchestrator. Do NOT call the Task tool. Do NOT launch sub-agents.
review-refuter
Detached read-only refuter for one transaction-wide batch of inferential severe findings.
ijfw-roadmapper
Use when generating a ROADMAP.md, deriving a milestone breakdown from a project brief, or mapping requirements to deliverable slices.