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/setup-team-comms)<a href="https://agentmods.dev/skills/atman-33/workhub/setup-team-comms"><img src="https://agentmods.dev/badge/skills/atman-33/workhub/setup-team-comms/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/setup-team-comms"><img src="https://agentmods.dev/badge/skills/atman-33/workhub/setup-team-comms.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 | $0.00069 | $0.00752 |
| Opus 5.5 | $0.00028 | $0.00301 |
| Sonnet 5.5 | $0.00014 | $0.00150 |
| Haiku 4.5 | $0.00007 | $0.00075 |
Grade A, and why
setup-team-comms 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 11d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Set up team-comms
Point this working directory at a shared folder the team already syncs
(Google Drive shared drive, OneDrive, a file server), so agents can hold one
asynchronous discussion in it. See ${CLAUDE_PLUGIN_ROOT}/docs/design.html.
Steps
-
Get the two things
initneeds. Ask only for what you cannot read off the machine:- the path to the comms folder as it appears on this machine (a synced local path, not a web URL);
- an agent id,
<person>-<machine>, lowercase ASCII — e.g.atman-desktop. Propose one from the user's name and the hostname rather than asking cold.
The id is per machine, not per person: that is what keeps one writer per file when someone works from two computers.
--personis what readers see, so both machines show up as one human. -
Run init:
node "${CLAUDE_PLUGIN_ROOT}/scripts/comms.mjs" init \ --root "<path to the comms folder>" \ --agent-id <person>-<machine> --person <person> --display "<how to show it>"It creates the space skeleton if missing, writes
.claude/team-comms.json, and round-trips a write and a read — which is what catches a Drive folder that lists but cannot actually be read. -
Act on what it reports.
- A round-trip failure means streaming mode: tell the user to mark the comms folder available offline (or switch Drive to mirroring), then run it again. Do not work around it.
- A duplicate-id warning means somebody already registered that id. Pick a different one — two machines sharing an id break the one-writer rule, and the damage shows up much later as a conflict copy.
-
Say what happens next, briefly. Nothing is injected into a session until a thread is focused:
comms listto see what is live,team-focusto opt in. This is the part people are surprised by, so state it. -
Do not touch
.gitignore.initalready keeps.claude/team-comms.jsonout of git through.git/info/exclude. In a workhub vault.gitignoreis owned by the app's template: a line added to it disappears on the next template update, and the vault's auto-backup then commits this machine's Drive path and agent id (T-0381). Ifinitwarns that the file is already tracked, run thegit rm --cachedcommand it prints — an exclude does nothing for a tracked file.
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.
- 11d ago Changed · +5 lines dc2db2e614f0
- 16d ago First seen · 58 lines · 69 tokens per session scan A e454ba316ee0
setup-team-comms is a skill published in the GitHub repository atman-33/workhub (2 stars, last pushed 2d ago), licensed MIT. It adds 69 tokens to every session and 752 once invoked, about $0.0003 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.