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.
git clone --depth 1 https://github.com/olehsvyrydov/AI-development-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/commands/olehsvyrydov/ai-development-team/agents)<a href="https://agentmods.dev/commands/olehsvyrydov/ai-development-team/agents"><img src="https://agentmods.dev/badge/commands/olehsvyrydov/ai-development-team/agents/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/commands/olehsvyrydov/ai-development-team/agents"><img src="https://agentmods.dev/badge/commands/olehsvyrydov/ai-development-team/agents.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 | $0.00011 | $0.01758 |
| Opus 5.5 | $0.00004 | $0.00703 |
| Sonnet 5.5 | $0.00002 | $0.00352 |
| Haiku 4.5 | $0.00001 | $0.00176 |
Grade A, and why
agents 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 1mo 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Development Team — Agent Directory
Two-tier roster. A core team (15) you'll use on most work, plus optional specialists loaded when a task needs them. Technology stacks are not separate agents — a role agent (e.g.
/be) detects the project's stack and loads the matchingreferences/<stack>.md. So "build a FastAPI endpoint" still routes to/be. The exception: core languages (Rust, Java, TypeScript; SQL with dialect branches) are knowledge skills underskills/development/languages/that auto-load from context — no persona, no command.Naming: role commands (
/arch,/be,/fe) are standard; persona aliases (/jorge,/james,/finn) invoke the same agent.
Core team (15)
| Role Command | Alias | Name | Role | Stacks / specializations (as references) |
|---|---|---|---|---|
/po |
/max |
Max | Product Owner — vision, backlog, Epics | — |
/ba |
/anna |
Anna | Business Analyst — research, requirements | — |
/sm |
/luda |
Luda | Scrum Master — board integrity, retrospection | — |
/arch |
/jorge |
Jorge | Solution Architect (MANDATORY gate) | GraphQL |
/secops |
/soren |
Soren | Security Engineer (MANDATORY gate) | — |
/fe |
/finn |
Finn | Frontend Developer | React/Next (default), Angular, Vue, Flutter, JavaFX desktop |
/be |
/james |
James | Backend Developer | Java/Spring (default), Kotlin, Python/FastAPI, PHP/Laravel, Quarkus, Kafka, HMRC MTD, Rust (via the rust language skill) |
/rev |
— | Rev | Code Reviewer | backend (Java/Kotlin), frontend (TS/React), PHP, Rust & SQL (via the language skills) |
/qa |
/rob |
Rob | Test Designer — test cases, BDD specs | — |
/e2e |
/adam |
Adam | E2E Automation — Playwright | Cucumber/BDD |
/ui |
/aura |
Aura | UI/UX Designer — design systems | JavaFX desktop design |
/devops |
— | — | DevOps Engineer — IaC, CI/CD, K8s | Terraform/OpenTofu |
/legal |
/alex |
Alex | Legal Counsel — contracts, GDPR, risk | UK / English & Welsh law (persona Alex) |
/fin |
/inga |
Inga | Accountant & CFO — tax, VAT, forecasting | UK tax (persona Inga), UK self-employment |
/mkt |
/apex |
Apex | Marketing — GTM, positioning | — |
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.
- 1mo ago First seen · 103 lines · 11 tokens per session scan A bf2244cfb3c1
agents is a command published in the GitHub repository olehsvyrydov/AI-development-team (17 stars, last pushed today), licensed MIT. It adds 11 tokens to every session and 1,758 once invoked, about $0.0000 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 2026-08-30.
Other commands, from other repositories
kenspc-task-review
A command that starts a multi-angle code review, including fixes and checks that changes did not cause new problems.
refactor-clean
Refactor provided code for cleanliness, maintainability, and alignment with SOLID principles and modern best practices — no over-engineering.
review
A command for reviewing code with security checks and a check for compliance with MX tags. The available description does not explain what MX tags are.
pr-enhance
Command "pr-enhance" from ruvnet/ruflo, covering pr-enhance, usage, options, examples and enhance pr.
sonarqube
Analyze SonarCloud quality issues for a specific PR.
gh-security-review
Use to perform a dedicated security review of current branch changes before pushing.