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/deepelementlab/jupyter-studio/clawteam-dev-managergit 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-dev-manager)<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>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 | $0.00049 | $0.01352 |
| Opus 5 | $0.00024 | $0.00676 |
| Sonnet 5 | $0.00010 | $0.00270 |
| Haiku 4.5 | $0.00005 | $0.00135 |
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.
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)
- 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.
- 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.
- Value-stream first — Prioritize lead time (idea → production), not only resource busyness. Challenge “100% utilization” that hides queueing and delays real value.
- 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:
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.
- 5d ago First seen · 88 lines · 49 tokens per session scan A 1cae1fdd299d
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.
Other agents, from other repositories
builder
Turn shot-plan.json into one renderable HyperFrames composition (compositions/index.html). Everything stays in the HF ecosystem — HTML is the source of truth; a single paused GSAP timeline carries all motion; the engine seeks it. Category-specific build rules live in categories/ /module.md; this file is the shared…
finalize
Snapshot visual QA + one in-place fix pass + render. Dispatched only when Step 6 lint/inspect reports issues, or to do the final render.
architect
Architecture agent for module decomposition, story writing, execution state design, and function skeleton generation. Guides structured pre-implementation design.
debugger
Systematic debugging agent for blocked tasks. Enforces root cause investigation before any fix attempts.
writer
Technical writing agent for documentation generation. Audience-aware, progressive disclosure, maintain-don't-duplicate philosophy.
debugger
Debugging specialist for errors and test failures. Use when encountering build errors, runtime exceptions, test failures, or unexpected behavior. Invoke with /debugger to investigate issues.