Is the Tandem Agentic Engineering skill free?

Yes. The skill itself is free from Maxmedawar/tandem. SkillProof publishes the install command and an independent test verdict at no cost.

How do I install Tandem Agentic Engineering?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Tandem Agentic Engineering with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Tandem Agentic Engineering

Opinionated multi-agent build workflow: spec, parallel research, concurrent revi

by Maxmedawar · Maxmedawar/tandem

Tested · Didn't pass

Read why it failed Download source ↗

Test report

Verdict: Tested · Didn't pass
Tested: Jul 25, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Jul 30, 2026 · b822cdc

⚠ This skill is no longer available upstream. Our re-check on Aug 10, 2026 couldn't find it any more (repo unreachable/deleted). The test below is what we measured on Jul 25, 2026 and we're leaving it up as a record — but there is nothing left to install, so we've removed the command.

Reads as an agentic-engineering manifesto rather than a runnable tool: its whole mechanism presupposes a 'Claude Code Agent Teams' stack it never ships or links to installing (agent-organizer, multi-agent-coordinator, /full-stack-feature, '275+ plugin agents'), so on a vanilla install you get generic process advice plus a mandatory five-hedgehog emoji on every message. The transferable core (spec, concurrent review, reproduce-fix-verify) is sound but showed no measurable delta over a competent baseline on a small task, and the emoji and forced multi-loop ceremony are pure overhead when the agent roster isn't present.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 4/5
Output vs. baseline 4/10
Docs & honesty 3/5

What Tandem Agentic Engineering does

A workflow manifesto for driving a team of Claude Code sub-agents through a feature build: parallel research spawn, a written spec, a concurrent reviewer, an adversarial devil's-advocate pass, parallel test writing, and a reproduce-fix-verify loop. Triggers broadly on development, debugging and feature work, and prepends a five-hedgehog emoji to every response while it is active.

How to install Tandem Agentic Engineering

Nothing to install: the source repository no longer has this skill. If the author brings it back, our daily re-check will pick it up and the command will reappear here.

Commands — how to trigger Tandem Agentic Engineering

/tandem-agentic-engineering Opinionated multi-agent build workflow: spec, parallel research, concurrent revi

It also activates on plain-language prompts like these:

Assemble an agent team to build this feature with review loops
Run the tandem workflow: spec, parallel research, devil's advocate
Coordinate multiple agents to build and test this feature end to end

Frequently asked questions

Is the Tandem Agentic Engineering skill free?: Yes. The skill itself is free from Maxmedawar/tandem. SkillProof publishes the install command and an independent test verdict at no cost.
Does Tandem Agentic Engineering work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 25, 2026. Verdict: Tested · Didn't pass. Reads as an agentic-engineering manifesto rather than a runnable tool: its whole mechanism presupposes a 'Claude Code Agent Teams' stack it never ships or links to installing (agent-organizer, multi-agent-coordinator, /full-stack-feature, '275+ plugin agents'), so on a vanilla install you get generic process advice plus a mandatory five-hedgehog emoji on every message. The transferable core (spec, concurrent review, reproduce-fix-verify) is sound but showed no measurable delta over a competent baseline on a small task, and the emoji and forced multi-loop ceremony are pure overhead when the agent roster isn't present.
How do I install Tandem Agentic Engineering?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Tandem Agentic Engineering with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.