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.
/plugin marketplace add atman-33/workhub/plugin install team-commsWrote 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/atman-33/workhub/team-decide)<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.
<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>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 | $0.00048 | $0.00545 |
| Opus 5.5 | $0.00019 | $0.00218 |
| Sonnet 5.5 | $0.00010 | $0.00109 |
| Haiku 4.5 | $0.00005 | $0.00055 |
Grade A, and why
team-decide scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 16d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Record a decision and close the thread
A thread nobody closes keeps showing up as live, and the team stops trusting the list. Closing is cheap — two posts.
Steps
-
Make sure you have the discussion, not just the last message: run
team-catchupif this session is cold. The decision post has to say what was rejected, and that is in the middle of the thread. -
Post the decision:
node "${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.
-
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 listand clear their own focus at the next session start. -
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.
-
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.
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.
- 16d ago First seen · 56 lines · 48 tokens per session scan A 60214d96f233
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.
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…
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.
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.
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…
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.
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.