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 olehsvyrydov/AI-development-team --skill ai-dev-teamgit 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/skills/olehsvyrydov/ai-development-team/ai-dev-team)<a href="https://agentmods.dev/skills/olehsvyrydov/ai-development-team/ai-dev-team"><img src="https://agentmods.dev/badge/skills/olehsvyrydov/ai-development-team/ai-dev-team/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/olehsvyrydov/ai-development-team/ai-dev-team"><img src="https://agentmods.dev/badge/skills/olehsvyrydov/ai-development-team/ai-dev-team.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 | $0.00084 | $0.01647 |
| Opus 5 | $0.00042 | $0.00823 |
| Sonnet 5 | $0.00017 | $0.00329 |
| Haiku 4.5 | $0.00008 | $0.00165 |
Grade A, and why
ai-dev-team 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 9d 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The AI Dev Team contract
A team of specialist agents plus an enforced, proportional workflow. Open-source, vendor-neutral, editor-neutral, free by default.
This is the always-on layer. When the framework is installed as a plugin there is no global
CLAUDE.md, so what a session needs to know about how work runs here lives in this skill.
Principles
- Proportional process. Right-size the workflow to the change — a typo is not a feature. Don't over-process; don't skip what matters.
- TDD. Behaviour → failing test → minimal code → green → refactor → commit. Targets: >80% unit, >60% integration.
- Behaviour-only tickets. Stories say WHAT, not HOW — no file paths or line numbers.
- OSS-first, no lock-in. Defaults need zero paid accounts; everything else is an optional adapter.
- Reusable skills. Agent skills hold universal knowledge. Project-specific facts belong in
that project's own
.claude/skills/, never in a framework skill.
Skills describe judgement and capability, never a product
Process and role skills must stay tool-free. A skill states what qualifies, what to decide, and
what to emit — never which vendor supplies it. verify-landed is the model: it is valuable
precisely because it needs nothing but a grep and a test run.
A concrete backend — tracker, memory store, design tool, knowledge base — is an optional
adapter. Name it only in a references/ adapter file or in docs/, never in a skill's
frontmatter, trigger, or core contract. Those decide when a skill loads and what it promises, and
neither may depend on a vendor.
The framework must work correctly with no adapter configured at all. A skill whose input is absent reports that plainly and stops; it does not degrade into guessing. If wiring up an adapter would require editing the skill itself, the contract is too narrow — generalise the contract rather than teaching the skill about one backend.
This is a boundary that erodes by drift: one concrete example becomes a schema, then a required field, then a dependency. Check it when reviewing any skill that reads from outside the repository.
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.
- 9d ago First seen · 127 lines · 84 tokens per session scan A b1e1024af464
ai-dev-team is a skill published in the GitHub repository olehsvyrydov/AI-development-team (16 stars, last pushed 1mo ago), licensed MIT. It adds 84 tokens to every session and 1,647 once invoked, about $0.0004 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 skills, from other repositories
implement
Use in the Implement phase whenever writing or editing production Java code, or fixing a bug, in a Spring/Spring Boot project. Enforces test-first (red-green-refactor), executes the approved plan step by step, and honors the project's path-scoped tech-stack rules and the task's enforcement set. Preloaded into…
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
test-driven-development
TDD: enforce RED-GREEN-REFACTOR, tests before code.
workflow-patterns
Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understanding the verification protocol.
strict-tdd
Strict RED->GREEN->REFACTOR test-driven development with enforcement. Never write production code before a failing test. Atomic commits per TDD cycle.
test-driven-development
Strict RED-GREEN-REFACTOR cycle enforcement. Tests are never skipped or deferred. Run mode only, never watch mode. Exit code evidence mandatory.