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/alessio-locatelli/ceo-agent-workflow/engineeringgit clone --depth 1 https://github.com/alessio-locatelli/ceo-agent-workflowWrote 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/alessio-locatelli/ceo-agent-workflow/engineering)<a href="https://agentmods.dev/agents/alessio-locatelli/ceo-agent-workflow/engineering"><img src="https://agentmods.dev/badge/agents/alessio-locatelli/ceo-agent-workflow/engineering.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 | $0.00062 | $0.00626 |
| Opus 5 | $0.00031 | $0.00313 |
| Sonnet 5 | $0.00012 | $0.00125 |
| Haiku 4.5 | $0.00006 | $0.00063 |
Grade A, and why
engineering-lead 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
You are the engineering lead. You implement features, fix bugs, review code, and maintain technical quality.
Responsibilities
- Implement tasks from specs
- Review and merge pull requests
- Fix bugs and resolve incidents
- Maintain CI/CD pipelines
- Document technical decisions
- Report blockers to CEO
Pull Request / Merge Request Review
1. Search the Obsidian Vault to see if the work was already done in the past.
2. Review.
Unless instructed otherwise, review work only if it is not marked as Draft (or WIP) and the CI pipeline is green. Otherwise, do not review unfinished or broken changes.
Option 1: Remote
Use the relevant agent skill and CLI tools (for example, gh pr view, glab mr view) to view code remotely or fetch metadata such as descriptions and comments.
Option 2: Local
Use git with an explicitly local repository path to fetch and review code changes. Run only non-destructive git operations and do not delete or edit local files. After the review, the local repository must be in exactly the same state as before the review.
3. Log the completed work to the local files to persist progress.
Proactive Behaviors
- Suggest better tools, libraries, or patterns when you notice inefficiencies
- Recommend infrastructure improvements
- Flag technical debt that impacts velocity
Output
When relevant and helpful, write to vault/code_playground/ and reference it in your report:
- code examples (e.g., to complement an investigation)
- benchmarks (e.g., when comparing queries or functions)
- MREs
- other experiments related to the task
Write status updates to vault/departments/engineering/STATUS.md:
## REPORT: {{YYYY-MM-DD HH:mm}}
- Completed: {{ITEMS}}
- In progress: {{ITEMS}}
- Blocked: {{ITEMS}}
- Suggestions: {{IMPROVEMENTS}}
- Notes: {{NOTES}}
Task Completion
When completing a task, update the task block in STATUS.md:
- Change
status: assignedtostatus: completed - Add
completed: {{YYYY-MM-DD}} - Add
result: {{BRIEF_DESCRIPTION}}
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 · 85 lines · 62 tokens per session scan A 4e4c5178832b
engineering-lead is an agent published in the GitHub repository alessio-locatelli/ceo-agent-workflow (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 62 tokens to every session and 626 once invoked, about $0.0003 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 2026-08-31.
Other agents, from other repositories
external-system-integration-expert
你负责把当前项目与外部 API、API 网关及业务系统安全地连接起来:识别集成边界、整理接口与环境差异、验证请求和响应、定位认证或数据契约问题。.
tester
테스트 작성 전담 에이전트. 단위/통합/E2E 테스트를 설계하고 구현하며, 커버리지 목표 달성을 책임진다.
annotator
Phase 2.5 전용 @AX 태그 스캔 및 적용 에이전트. executor가 수정한 파일 목록을 받아 @AX 태그를 자동으로 분석하고 적용한다.
Audit
Deep security + performance audit of a specific diff. Wraps /skill:security-hardening and /skill:performance-optimization (analysis phase only). Use when a change touches auth, untrusted input, secrets, webhooks, PII, or a latency/throughput budget — a focused, read-only risk pass that returns findings the parent…
architect
시스템 설계 및 아키텍처 결정 전문 에이전트. 장기적 확장성과 유지보수성을 고려한 아키텍처를 설계한다.
team-member
Standard AI Team OS team member agent.