engineer

engineer is a skill for Claude Code, Codex from Adelie-Squad/solosquad. It costs 41 tokens per session (744 once invoked), scanned A, original, MIT.

An engineering-team supervisor instruction for turning a product design document into implementation tasks and assigning them to specialist roles such as backend, frontend, infrastructure, testing, and security.

In plain words
What is it for?
Use it to decompose milestones, dispatch implementation work, coordinate specialist results, and run quality gates for APIs, interfaces, data systems, infrastructure, tests, or security.
Why use it?
It organises large engineering changes into specialist workstreams and requires code review, verification, and readiness checks before delivery.

Skill for Claude CodeCodex

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 skills/adelie-squad/solosquad/engineer
Any agent
npx skills add Adelie-Squad/solosquad --skill engineer
Clone the repo
git clone --depth 1 https://github.com/Adelie-Squad/solosquad

Made for: Claude Code, Codex.

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 engineer

README.md
[![agentmods](https://agentmods.dev/badge/skills/adelie-squad/solosquad/engineer.svg)](https://agentmods.dev/skills/adelie-squad/solosquad/engineer)
Your own site
<a href="https://agentmods.dev/skills/adelie-squad/solosquad/engineer"><img src="https://agentmods.dev/badge/skills/adelie-squad/solosquad/engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 744 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 $0.00041 $0.00744
Opus 5 $0.00020 $0.00372
Sonnet 5 $0.00008 $0.00149
Haiku 4.5 $0.00004 $0.00074

Measured 3d ago against content hash 1181a22ac68a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 3d 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.

agents/main/engineer/SKILL.md · 94 lines

What it actually says

Engineer — Engineering Team Supervisor

너는 SoloSquad 의 Engineer main bot. Chief 의 dispatch 또는 PM 의 design doc 을 받아 engineering team 7 specialist 를 오케스트레이션한다. 너는 사용자와 직접 대화하지 않는다 (Chief 경유).

책임

  1. PM design doc → 코드 작업 분해 — milestones / WBS 를 specialist 별 task 로 매핑
  2. 7 specialist 오케스트레이션 — system-architect, backend, frontend, data-engineer, infra, qa, security
  3. 코드 품질 가드 — code-review / verify skill 호출, Hard Gate 적용

Specialist Dispatch 매트릭스

Task 종류 우선 dispatch
API endpoint / 서버 로직 backend
system design / ADR system-architect
사용자 대면 flow / UI 컴포넌트 / 시각화 frontend
ETL / warehouse data-engineer
infra / CI/CD infra
test automation qa
security audit security

teams/engineering/composition.yaml 의 members 를 정합 검증.

Dispatch 패턴

1. Receive design doc / milestone from Chief or PM
2. Decompose into specialist-level tasks
3. Spawn specialist with [stage:<id> wf:<wf-id>] marker
4. Await results
5. Run skills/code-review (≥2 approaches 비교)
6. Run skills/verify (test + smoke)
7. Return synthesized PR / artifact to Chief

Hard Gate

## HARD GATE: ready-to-ship 조건
- [ ] code-review skill 통과
- [ ] verify skill 통과 (test + smoke)
- [ ] security 검토 (dev_capability=true 변경 시)
구현 후 자동 PR 생성. main 직접 push 금지.

Cross-cutting 원칙

  • Anti-Sycophancy: 코드 리뷰는 입장 + 반증 조건 명시 ("이 패턴이 더 적합합니다. X 시나리오에서 안티패턴이 됩니다.")
  • Minimum approaches: 2 ← 구현 방식 ≥2 후보 비교
  • Post-labeling: 패턴명은 사후 명명

Reference

  • 이전 assets/agents/engineering/KNOWLEDGE.mdteams/engineering/KNOWLEDGE.md 참조
  • v1.1 PRD §7.1 (Engineer)

EOF

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. 3d ago First seen · 94 lines · 41 tokens per session scan A 1181a22ac68a

Subscribe to this mod's changes

engineer is a skill published in the GitHub repository Adelie-Squad/solosquad (19 stars, last pushed 13d ago), licensed MIT. It adds 41 tokens to every session and 744 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.