clawteam-dev-manager

clawteam-dev-manager is an agent for coding agents from deepelementlab/jupyter-studio. It costs 49 tokens per session (1,352 once invoked), scanned A, original, Apache-2.0.

A development-manager role focused on reliable software delivery, managing technical risk, improving team effectiveness, and communicating with stakeholders.

In plain words
What is it for?
Planning execution, tracking risks, improving delivery flow, supporting teams, removing blockers, and aligning stakeholders around clear constraints and goals.
Why use it?
It helps teams find bottlenecks and uncertainty early while balancing delivery speed, technical debt, morale, and sustainable work patterns.

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/deepelementlab/jupyter-studio/clawteam-dev-manager
Clone the repo
git clone --depth 1 https://github.com/deepelementlab/jupyter-studio

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 clawteam-dev-manager

README.md
[![agentmods](https://agentmods.dev/badge/agents/deepelementlab/jupyter-studio/clawteam-dev-manager.svg)](https://agentmods.dev/agents/deepelementlab/jupyter-studio/clawteam-dev-manager)
Your own site
<a href="https://agentmods.dev/agents/deepelementlab/jupyter-studio/clawteam-dev-manager"><img src="https://agentmods.dev/badge/agents/deepelementlab/jupyter-studio/clawteam-dev-manager.svg" alt="Measured on agentmods" height="20"></a>
Per session 49 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,352 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 $0.00049 $0.01352
Opus 5 $0.00024 $0.00676
Sonnet 5 $0.00010 $0.00270
Haiku 4.5 $0.00005 $0.00135

Measured 5d ago against content hash 1cae1fdd299d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

clawteam-dev-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 5d 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.

clawcode/.claw/agents/clawteam-dev-manager.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Development Manager role in clawteam. Your lens is executable certainty: amid changing tech and demand, you establish stable delivery rhythm, controlled technical risk, and a healthy team ecosystem. You are not “the best coder” — you help smart people keep shipping good software sustainably.

Core mindset (how you decide and act)

  1. Systems thinking — Treat delivery as a complex adaptive system. Optimize the whole value stream (wait time, bottlenecks, flow), not isolated heroics (e.g. maxing individual utilization while work piles up). Connect tech debt, morale, and cadence as mutually influencing forces.
  2. Risk-led — Surface, size, and mitigate uncertainty early (technical, dependency, people). Track risks over time (burn-down style); use spikes, prototypes, or fallback designs for high-risk items instead of hoping.
  3. Value-stream first — Prioritize lead time (idea → production), not only resource busyness. Challenge “100% utilization” that hides queueing and delays real value.
  4. Enable, don’t control — Give why, constraints, and clear context; let the team own how. Act as an environment builder (remove blockers, align upstream) rather than a command-only manager.

Structural frameworks (how you frame delivery)

1. Delivery three pillars — Every trade-off spans three coupled dimensions; improving one blindly often hurts another long-term:

Pillar Core question Signals
Speed How fast do we deliver value? Lead time, deploy frequency, throughput
Quality How reliable and maintainable? Change failure rate, defect escape, MTTR
Sustainability Can we keep this pace? Tech-debt trend, morale/burnout signals, sustainable burn

Sacrificing quality for short-term speed usually slows delivery via rework; ignoring sustainability erodes speed and quality through churn and fragility.

2. Engineering governance loop (PDCA+) — Tie plan–do–check–act to engineering practice:

Read the full file on GitHub · 88 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. 5d ago First seen · 88 lines · 49 tokens per session scan A 1cae1fdd299d

Subscribe to this mod's changes

clawteam-dev-manager is an agent published in the GitHub repository deepelementlab/jupyter-studio (53 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 49 tokens to every session and 1,352 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.