tag-team — Claude Code skill: what it does, how to install
The tag-team Claude Code skill assigns one task to two agents: one implements it, while the other reviews the changes. It activates when asked to pair agents for implementation and review.
Apache-2.0 ★ 869 updated 2026-11-16
npx skills add sno-ai/sno-station-skills --skill tag-team -a claude-codeWhat tag-team does
The skill starts two new agents in the current project folder. One carries out the task; the other checks the changed files and reports defects or an explicit clean result. They exchange fixes and reviews through Reach, while the command returns the first review.
It requires the sno command with Reach version 2.1.7 or later, tmux, and at least one signed-in agent CLI. Start a pair only on direct request: both agents run with approval prompts disabled. Pass the task as one nonblank string that does not begin with a hyphen.
The command waits a few minutes for the first review. If defects are found, the agents continue their exchange separately, and the reviewer can be asked for an update. While they edit the same files, do not start another reviewer or change those files.
What it helps with
- assign one task to an implementing agent and a reviewer
- get concrete findings on changed files
- let agents exchange fixes and follow-up reviews
- check whether a follow-up review is clean
Example prompts for the agent
- Pair two agents: have one fix the login redirect and the other inspect the changed files.
- Ask one agent to add form validation and its partner to review the changes for defects.
- Start an agent pair to implement this task and review each other's changes.
How to install tag-team
1Skills CLI (Vercel)
npx skills add sno-ai/sno-station-skills --skill tag-team -a claude-code2Manually: put the files in place
~/.claude/skills/skill/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/skill/
1Skills CLI (Vercel)
npx skills add sno-ai/sno-station-skills --skill tag-team -a codex2Manually: put the files in place
.agents/skills/skill/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add sno-ai/sno-station-skills --skill tag-team -a cursor2Manually: put the files in place
.cursor/skills/skill/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install sno-ai/sno-station-skills skills/S-communication-and-handoff/tag-team/skill2Manually: put the files in place
.github/skills/skill/SKILL.md1Skills CLI (Vercel)
npx skills add sno-ai/sno-station-skills --skill tag-team -a gemini-cli2Platform CLI
gemini skills install https://github.com/sno-ai/sno-station-skills --path skills/S-communication-and-handoff/tag-team/skillManually: put the files in place
.devin/skills/skill/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add sno-ai/sno-station-skills --skill tag-team -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about tag-team
How do I install tag-team in Claude Code?
Run npx skills add sno-ai/sno-station-skills --skill tag-team -a claude-code. The skill file is installed at ~/.claude/skills/skill/SKILL.md.
What does tag-team do?
It starts two agents on the same task: one implements the work, and the other reviews it. They exchange findings and fixes through Reach.
What does tag-team require?
It requires the sno command with Reach version 2.1.7 or later, tmux, and at least one signed-in agent CLI.
Source text
SKILL.md · Apache-2.0
---
name: tag-team
description: "Put two agents on one task: one builds, the other reviews what it built, and they settle the findings between themselves. Use when asked to pair agents, tag-team a task, or have work built and reviewed without the person carrying it between agents. Not for reviewing work that already exists (peer-review) or for passing a task on (handoff)."
requires:
programs:
- {name: reach, min_version: "2.1.7"}
harness:
- {slot: 4.shell, need: required}
---
# tag-team
One command starts two new agents on the same task in the current project folder. The first
implements. The second reads the result and the changed files and answers with concrete
defects or an explicit no-defect result. Their assignments tell them to keep exchanging fixes
and reviews through Reach, the messaging layer between agents (see the `reach` skill). The
command itself brings back only the first review; following the rest is your job (below).
Needs: the `sno` command with its Reach program, version 2.1.7 or later, tmux, and at least
one signed-in agent CLI (Claude Code, Codex, Cursor, Hermes or OpenClaw).
## Before you start
1. Check that the command exists: `sno reach pair --help` prints a usage line and starts
nothing. If the `sno` command itself is missing, Sno Station is not installed: stop and
point the person to its install instructions at https://github.com/sno-ai/sno-station. If
`sno` runs but `pair` is not a known verb, its Reach program is older than 2.1.7 and
`sno setup` updates it. In both cases do not imitate the pair by hand.
2. Both agents run with approval prompts off. Start a pair only when the person asked for
one. If you are proposing it yourself, say that the two agents will act without asking
and wait for a yes.
3. Write the task as one self-contained string. The two agents are new: they have none of
this conversation. Name the goal, the files or area, and how to tell it is done.
4. Run it from the folder the work belongs to. Both agents start there.
## Start the pair
```bash
sno reach pair "Fix the login redirect so a signed-out visitor returns to the page they asked for"
```
The command takes exactly one nonblank task string, and the string must not begin with `-`: a
task copied from a list as `- fix the login` is read as an option and refused. Start it with a
word.
## Read what it prints
- `Agents use <a> (<vendor>) and <b> (<vendor>).` This run has one agent from each of two
vendors, so the review comes from the other vendor.
- `Both agents use <a> (<vendor>). ... this pair has no cross-vendor review.` This run uses
one agent kind for both roles. The pair still builds and reviews; tell the person that this
review is not a cross-vendor review. The line does not say why, so do not add a reason.
- `Implementer: <address>; view: tmux attach-session -t <name>` and the same line for
`Reviewer`. Pass both lines to the person unchanged: that is how they watch.
- `Review returned by <address>:` followed by the first review. Relay its findings or its
no-defect result.
The command waits a few minutes for the first review and then returns. A final line saying
`no verified review result` means only that no review reached this command before it
returned; the two assignments stay stored. It does not show that the pair failed, and it does
not show that both agents are still working. Check before you report: `sno reach seats --json`
for the two addresses, then `sno reach watch <address> --timeout 60 --idle 10` on each. Tell
the person what you saw and give the two `view:` lines. Do not start the pair again.
## After the first review
- The first review says no defect: the pair is finished. Report that, with the changed paths
it names.
- The first review lists defects: the pair is not finished. Report the findings as open. The
fix and the next review travel between the two agents' mailboxes, not back to this command.
- To learn where it stands, ask the reviewer:
`sno reach call <reviewer address> "In one line: is your latest review of the fixed files clean, or what is still open?" --timeout 120`.
Read the output itself. Exit 0 only means the reviewer received the question; it is not a
promise that it answered. Only an explicit answer from the reviewer to this question
counts. With any exit code, if the output holds no such answer, say the state is unknown
and give the two `view:` lines.
- After a first review that listed defects, report the work as reviewed clean only when the
reviewer's own answer says so.
## While they work
- The pair is self-contained. Do not start a third reviewer and do not run `peer-review` on
the same change while the pair is still exchanging fixes.
- To look without interrupting: `sno reach watch <address> --timeout 60 --idle 10`.
- To say something to one of them: `sno reach call <address> "<text>" --timeout 120`.
- The two agents edit the same checkout you are in. Leave the files they are changing alone
until the review is clean.
## When it refuses
- `pair requires one nonblank task string`: pass the whole task as one quoted argument.
- The usage line is printed and nothing starts: the task began with `-`. Reword it to start
with a word.
- `no usable signed-in agent found; no agents started`: nothing was selected. The lines
printed just before it name each agent and why it was passed over (`CLI unavailable`, or
`login signed out` or `unknown`). Pass those lines on as printed; do not guess a cause they
do not state, and do not retry.
- `no implementer started`: the first agent could not be launched; nothing is running. Report
the line as printed.
- `pair assign <address>: delivery failed`: both agents started but one of them did not get
its assignment, and the command stops without waiting for a review. Report the line as
printed, check both addresses with `sno reach seats --json` and `sno reach watch`, and do
not start the pair again.
- `reviewer launch failed ... only implementer started`: one agent is working without a
reviewer. Tell the person, and offer `peer-review` on the result once it is finished.
© sno-ai · Apache-2.0 · sno-ai/sno-station-skills