team-decide

team-decide is a skill for Claude Code from atman-33/workhub. It costs 48 tokens per session (545 once invoked), scanned A, original, MIT.

A way to record the conclusion of a team discussion and mark its thread closed. The decision records what was chosen, what was rejected, why, and what remains open.

In plain words
What is it for?
Use it when a design or implementation question has been settled, when the user states a decision, or when a discussion no longer needs more responses.
Why use it?
It stops finished discussions from appearing active and preserves the reasoning for people who return later. It also checks for conflicting decisions instead of silently choosing one.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the team-comms plugin — 8 skills shipped together

Good fit Use it when a design or implementation question has been settled, when the user states a decision, or when a discussion no longer needs more responses.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add atman-33/workhub
Claude Code
/plugin install team-comms

Made for: Claude Code.

Or install team-comms, the plugin that ships this one along with the rest of its 8 skills.

Wrote 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.

agentmods badge for team-decide

README.md
[![agentmods](https://agentmods.dev/badge/skills/atman-33/workhub/team-decide/github.svg)](https://agentmods.dev/skills/atman-33/workhub/team-decide)
Your own site
<a href="https://agentmods.dev/skills/atman-33/workhub/team-decide"><img src="https://agentmods.dev/badge/skills/atman-33/workhub/team-decide/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.

agentmods 80×15 button for team-decide

Your own site · 80×15
<a href="https://agentmods.dev/skills/atman-33/workhub/team-decide"><img src="https://agentmods.dev/badge/skills/atman-33/workhub/team-decide.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 545 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00048 $0.00545
Opus 5.5 $0.00019 $0.00218
Sonnet 5.5 $0.00010 $0.00109
Haiku 4.5 $0.00005 $0.00055

Measured 16d ago against content hash 60214d96f233, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-29, from the pricing page.

Security

Grade A, and why

team-decide 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 16d 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.

plugins/team-comms/skills/team-decide/SKILL.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Record a decision and close the thread

A thread nobody closes keeps showing up as live, and the team stops trusting the list. Closing is cheap — two posts.

Steps

  1. Make sure you have the discussion, not just the last message: run team-catchup if this session is cold. The decision post has to say what was rejected, and that is in the middle of the thread.

  2. Post the decision:

    node "${CLAUDE_PLUGIN_ROOT}/scripts/comms.mjs" post \
      [--thread <id>] --kind decision \
      --summary "<what was decided, in one line>" [--body-file <path>]
    

    The body carries what a reader in three months needs: what was chosen, the reason, what was rejected and why, and anything left open. That paragraph is the entire value of having discussed it in writing.

  3. Close it:

    node "${CLAUDE_PLUGIN_ROOT}/scripts/comms.mjs" post \
      [--thread <id>] --kind status --state closed --summary "<why it is closed>"
    

    Closed threads drop out of comms list and clear their own focus at the next session start.

  4. Check for a competing decision first. If the thread already has one, the tools report "several decisions" rather than resolving it — because sync delay lets two people each believe theirs was last. Do not add a third silently: say what is already recorded, and let the user settle it.

  5. Carry the conclusion where it belongs. A decision that changes how a repository works belongs in that repository too — an ADR, a rule, or the project's own notes. The thread is the discussion, not the documentation.

Rules

  • Only record what the team actually settled. Writing a decision to tidy away a thread that is still open is worse than leaving it open.
  • Anyone may close a thread and everything stays in the history, so an undo is just another status post. The convention is that whoever opened it closes it.
  • Never close a thread that is waiting on somebody's answer, even if it has gone quiet. Mention them instead.

Read the full file on GitHub · 56 lines

Changes

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.

  1. 16d ago First seen · 56 lines · 48 tokens per session scan A 60214d96f233

Subscribe to this mod's changes

team-decide is a skill published in the GitHub repository atman-33/workhub (2 stars, last pushed 2d ago), licensed MIT. It adds 48 tokens to every session and 545 once invoked, about $0.0002 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 2026-09-13.

Related

Other skills, from other repositories

gonavi-cli

Operate databases through the GoNavi headless CLI — the gonavi executable shipped in verified GitHub Release archives. Covers listing/adding/importing saved connections, running SQL queries against saved connections or ad-hoc connection files, exporting result sets to csv/json/md/html/xlsx, batch-executing SQL files…

Syngnat/GoNavi · 144 tokens

to-tickets

When asked to file tickets, break down approved work, or move a settled plan onto the board, turn the spec, closed decision map, or pressure-tested conversation into verifiable work items with real dependencies and non-ticket blockers.

timharris707/skills · 49 tokens

setup

For a new TeamWorkflow installation, binding refresh, or drift audit after a pack release, inspect and bind the project workflow. Reuse explicit recorded decisions with their sources; ask about missing, conflicting, or changed authority and bindings.

timharris707/skills · 48 tokens

create-task

Create one production-ready task contract from a short request or optional structured brief, optional task ID, repository context, and attached references without implementing it. In the canonical task-first workflow this contract is also the implementable story; use separate story files only in an explicitly legacy…

furkantokkan/agent-foundry · 59 tokens

decision-map

When asked to chart a decision map, work a map ticket, or plan work whose open decisions gate each other, map the unresolved choices before build slices. Use for a new primitive, milestone charter, or integration that cannot yet be specified in one sitting.

timharris707/skills · 54 tokens

tasks

A task-breakdown tool that turns a plan, specification, feature brief, bug report, technical-debt item, or chore into small TASK-NNN work items. Technical debt means postponed cleanup or design work in a codebase.

cryndoc/polisade-orchestrator · 127 tokens