team-focus

team-focus is a skill for Claude Code from atman-33/workhub. It costs 60 tokens per session (433 once invoked), scanned A, original, MIT.

A setting that makes one team discussion thread active for a working directory. Future sessions in that directory can surface unread posts, and the setting can later be turned off.

In plain words
What is it for?
Use it when starting work on a named team thread, when you want unread updates surfaced, or when you want to stop receiving updates there.
Why use it?
It keeps notifications limited to workspaces that are actually following a discussion. It also separates thread focus between different repositories or working directories.

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 starting work on a named team thread, when you want unread updates surfaced, or when you want to stop receiving updates there.

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-focus

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/atman-33/workhub/team-focus"><img src="https://agentmods.dev/badge/skills/atman-33/workhub/team-focus.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 433 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 $0.00060 $0.00433
Opus 5.5 $0.00024 $0.00173
Sonnet 5.5 $0.00012 $0.00087
Haiku 4.5 $0.00006 $0.00043

Measured 16d ago against content hash b213e7159c80, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-29, from the pricing page.

Security

Grade A, and why

team-focus 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-focus/SKILL.md · 44 lines

What it actually says

Focus a thread (or stop)

team-comms is silent by default. A session is told about a thread only while this working directory has opted in — because injecting unread counts into every session is a cost paid in tokens and attention every time, and ends with everyone ignoring them.

Steps

  1. Resolve which thread. If the user named one, find it with comms list / comms search. If they described a topic and no thread exists, this is team-open, not this skill.

  2. Focus it:

    node "${CLAUDE_PLUGIN_ROOT}/scripts/comms.mjs" focus <thread-id>
    

    Stored per working directory, so another repository can follow a different thread at the same time.

  3. Offer the catch-up in the same breath. Focus points at a thread; it does not remember its contents, and this session has none of the discussion. If the thread has posts the user has not seen, run team-catchup now rather than waiting for them to ask.

  4. To stop: comms unfocus. Say plainly that sessions in this directory will go silent — that is the intended state, not a loss of a feature.

Rules

  • Focus only what the user actually said to. Quietly focusing a thread because it looked relevant makes every later session pay for it.
  • A closed thread clears its own focus at the next session start; there is no need to unfocus it by hand.
  • Being named in a post still produces a one-line count with no focus at all. That is the only exception, and it is deliberate.
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 · 44 lines · 60 tokens per session scan A b213e7159c80

Subscribe to this mod's changes

team-focus is a skill published in the GitHub repository atman-33/workhub (2 stars, last pushed 2d ago), licensed MIT. It adds 60 tokens to every session and 433 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