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-share)<a href="https://agentmods.dev/skills/atman-33/workhub/team-share"><img src="https://agentmods.dev/badge/skills/atman-33/workhub/team-share/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-share"><img src="https://agentmods.dev/badge/skills/atman-33/workhub/team-share.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 | $0.00066 | $0.00543 |
| Opus 5.5 | $0.00026 | $0.00217 |
| Sonnet 5.5 | $0.00013 | $0.00109 |
| Haiku 4.5 | $0.00007 | $0.00054 |
Grade A, and why
team-share scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 16d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Share research into a thread
This is the skill the plugin exists for. What used to be "export it, send it, they paste it into their agent" becomes "it is in the thread".
Steps
-
Pick the thread. The focused one by default; otherwise
comms list/comms search. No thread fits →team-openfirst. -
Split the material in two. This split is the whole point:
Goes in the post Goes in an attachment What you found, in one or two lines The full research output The recommendation and why Comparison tables, long reasoning What is still open Diagrams, exports, generated files If the full report goes in the post body, every agent on the thread reads all of it every time — the handover you removed comes straight back as token cost. The summary is what lets a reader decide whether to open the rest.
-
Write the attachment to a real file (Markdown, SVG, PDF, HTML — a scratch path is fine), then post:
node "${CLAUDE_PLUGIN_ROOT}/scripts/comms.mjs" post \ --kind share --summary "<what you found, and what you recommend>" \ [--body-file <path>] [--attach <path>]... [--thread <id>] [--mention <agent-id>]Attachments land in a folder beside the post and are immutable like it.
-
Keep attachments sensible. Around 10 MB per file; anything larger goes elsewhere on the drive with a link in the body. No build output, no video.
-
Report where it went, and remind the user that people only see it if they are following the thread — mention someone, or tell them.
Rules
- Share what a teammate can act on, not a transcript of the session.
- Never attach credentials, tokens, or customer data. The comms space is as visible as the shared drive it sits in.
- Attachments are immutable, same as posts: a corrected report is a new post.
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 · 52 lines · 66 tokens per session scan A 1bcc79988e8d
team-share is a skill published in the GitHub repository atman-33/workhub (2 stars, last pushed 2d ago), licensed MIT. It adds 66 tokens to every session and 543 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.