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/ruslan-korneev/claude-pluginsWrote 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/plugins/ruslan-korneev/claude-plugins/tech-lead)<a href="https://agentmods.dev/plugins/ruslan-korneev/claude-plugins/tech-lead"><img src="https://agentmods.dev/badge/plugins/ruslan-korneev/claude-plugins/tech-lead/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/plugins/ruslan-korneev/claude-plugins/tech-lead"><img src="https://agentmods.dev/badge/plugins/ruslan-korneev/claude-plugins/tech-lead.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
tech-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 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.
What it actually says
{
"name": "tech-lead",
"version": "2.0.0",
"description": "Architecture design, code review (Review Pyramid), full-cycle TDD development, and structured feature specifications.",
"author": { "name": "Ruslan Korneev" },
"repository": "https://github.com/ruslan-korneev/claude-plugins",
"keywords": ["python", "architecture", "code-review", "tdd", "planning", "features", "adr"]
}
What it installs
The manifest is a name and a version. 14 commands, 9 agents travel with it, and installing the plugin installs all of them — 427 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Command dev A 27 tokens
- Command execute A 22 tokens
- Command arch:review A 21 tokens
- Command deps A 12 tokens
- Command design A 13 tokens
- Command features:design A 14 tokens
- Command modernize A 14 tokens
- Command adr A 9 tokens
- Command diagram A 11 tokens
- Command features:add A 14 tokens
- Command features:status A 12 tokens
- Command features:analyze A 15 tokens
- Command features:graph A 14 tokens
- Command features:init A 12 tokens
- Agent dependency-analyzer A 14 tokens
- Agent architecture-reviewer A 10 tokens
- Agent code-reviewer A 34 tokens
- Agent execution-agent A 33 tokens
- Agent feature-designer A 22 tokens
- Agent codebase-analyzer A 23 tokens
- Agent planning-agent A 24 tokens
- Agent codebase-explorer A 26 tokens
- Agent quick-reviewer A 31 tokens
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 · 9 lines scan A 1ad4a59201bd
tech-lead is a plugin published in the GitHub repository ruslan-korneev/claude-plugins (5 stars, last pushed 7mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
shipyard
Ship software systematically: project lifecycle, TDD, parallel agents, code review, security auditing, and infrastructure validation.
engineering-skills
Cross-platform engineering skills across the software lifecycle, with auditable documents, task-sized workflows and self-contained Codex installation.
superpowers-orchestrator
Agentic development framework for Claude Code — disciplined workflow routing, TDD enforcement, safety hooks, systematic debugging, and code review.
deep-plan
AI-assisted deep planning with research, interview, external LLM review, and TDD approach.
deep-implement
Implement code from /deep-plan sections with TDD, code review, and git workflow.
rageatc-code-oss
Scale-adaptive software development — TDD, verification, perspective-based review, interface design, and tool capabilities (browser automation, PDFs, YouTube transcripts, local-LLM and Codex delegation).