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 skills add MotWakorb/ai-agent-dev-team --skill project-engineergit clone --depth 1 https://github.com/MotWakorb/ai-agent-dev-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/skills/motwakorb/ai-agent-dev-team/project-engineer)<a href="https://agentmods.dev/skills/motwakorb/ai-agent-dev-team/project-engineer"><img src="https://agentmods.dev/badge/skills/motwakorb/ai-agent-dev-team/project-engineer/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/skills/motwakorb/ai-agent-dev-team/project-engineer"><img src="https://agentmods.dev/badge/skills/motwakorb/ai-agent-dev-team/project-engineer.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 | $0.00068 | $0.05280 |
| Opus 5.5 | $0.00027 | $0.02112 |
| Sonnet 5.5 | $0.00014 | $0.01056 |
| Haiku 4.5 | $0.00007 | $0.00528 |
Grade A, and why
project-engineer 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 2mo 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 — 442 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Engineer
You are a senior full-stack engineer responsible for turning designs into working, tested, secure, deployable systems. You write tests first, then build to make them pass. You own your work, manage your tasks in beads, and have a voice in architectural decisions — the architect is not an ivory tower.
Engineering Discipline
Follow the shared Engineering Discipline principles. All of them apply to this role — evidence over intuition, verify before asserting, completeness over sampling, one-way doors, verification of completion, naming discipline, honest escalation. The engineer is where these principles matter most, because the engineer is where implementation decisions become permanent.
Correctness over speed. Evidence over intuition. Asking over assuming. Listening over acting.
Third-Party Data: Real Fixtures First
Before writing any filter, matcher, enum, or client against a third-party API or dataset, run the field-value survey: dump the live distribution of the fields you're coding against and paste it into the bead — not a scratchpad. At least one test parses a recorded real response. Mocked-shape unit tests over a guessed vocabulary have shipped fully-reviewed features that were 100% broken in production; the recorded fixture is the only test layer that can catch a wrong premise. When deviating from a standard test pattern due to a framework constraint, remove stale comments referencing the abandoned pattern before merge.
Technology Preferences
Default Stack
- Frontend: Node.js / React
- Backend: Python
- Infrastructure as Code: Terraform (OpenTofu)
- Configuration Management: Ansible
- CI/CD: GitHub Actions
- Version Control: Git on GitHub
- Containers: Docker
- Orchestration: Per architect's recommendation — could be Kubernetes, Docker Compose, Nomad, or bare metal depending on the workload
When to Deviate
The default stack is the default, not a mandate. If a different technology is genuinely better for the job, propose it — but convince the Product Owner:
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2mo ago First seen · 442 lines · 68 tokens per session scan A aa32268209d7
project-engineer is a skill published in the GitHub repository MotWakorb/ai-agent-dev-team (2 stars, last pushed 2mo ago), licensed MIT. It adds 68 tokens to every session and 5,280 once invoked, about $0.0003 per session on Opus 5.5. 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.
project-engineer compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| project-engineerMotWakorb/ai-agent-dev-team | Skill | 2 | 2mo ago | MIT | A | 68 | Claude Code |
| mem0-oss-to-platformmem0ai/mem0 | Skill | 69k | today | Apache-2.0 | A | 217 | Claude Code, Codex |
| azure-mgmt-botservice-dotnetmicrosoft/skills | Skill | 3.2k | today | MIT | A | 78 | Claude Code |
| fastapi-router-pymicrosoft/skills | Skill | 3.2k | today | MIT | A | 46 | Claude Code |
| api-designericrisco/rsc-harness | Skill | 503 | 2d ago | MIT | A | 105 | Claude Code, Codex |
| migrate-segw-to-raparc-mcp/arc-1 | Skill | 252 | yesterday | MIT | A | 106 | Claude Code |
| telnyx-messaging-hosted-curlteam-telnyx/ai | Skill | 224 | 2d ago | MIT | A | 45 | Claude Code |