Knowledge Work Plugins is an open-source collection of Claude extensions organized around roles such as productivity, sales, and customer support. Each plugin combines role-specific guidance, connectors, commands, and sub-agents so knowledge workers can use Claude with their team’s tools and processes. The catalogue entries are examples of, or workflows from, this plugin collection.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/anthropics/knowledge-work-plugins/discover-brandgit clone --depth 1 https://github.com/anthropics/knowledge-work-pluginsWrote 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/commands/anthropics/knowledge-work-plugins/discover-brand)<a href="https://agentmods.dev/commands/anthropics/knowledge-work-plugins/discover-brand"><img src="https://agentmods.dev/badge/commands/anthropics/knowledge-work-plugins/discover-brand.svg" alt="Measured on agentmods" 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 | $0.00011 | $0.00544 |
| Opus 5 | $0.00005 | $0.00272 |
| Sonnet 5 | $0.00002 | $0.00109 |
| Haiku 4.5 | $0.00001 | $0.00054 |
Grade A, and why
discover-brand 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 yesterday.
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.
Copies of this mod
1 near-identical copy found in the catalogue:
- discover-brand — 100% identical, 0 lines differ
What it actually says
Discover brand materials across the user's connected enterprise platforms. Search Notion, Confluence, Google Drive, Box, SharePoint, Figma, Gong, Granola, and Slack for brand guidelines, style guides, messaging frameworks, templates, and conversation transcripts.
If $ARGUMENTS includes a company name, use it for targeted searches. If platforms are specified, limit search to those platforms.
Before doing anything else, briefly orient the user on what's about to happen: the process will search their connected platforms, produce a discovery report, and then (optionally) generate and save brand guidelines to .claude/brand-voice-guidelines.md in the working folder. Nothing is saved until they explicitly approve. Keep the orientation to 2-3 sentences — don't recite the full workflow.
Follow the discover-brand skill instructions to:
- Check
.claude/brand-voice.local.mdfor settings (company name, enabled platforms, search depth) - Validate platform coverage (stop if no document platforms, warn if gaps)
- Briefly confirm scope with the user (which platforms, include transcripts?)
- Delegate to the discover-brand agent for autonomous 4-phase search
- Present the structured discovery report with sources, brand elements, conflicts, and open questions
- Offer next steps: generate guidelines, resolve open questions, save report, or expand search
Platform validation:
- If no platforms are connected, inform the user which MCP servers the plugin supports (Notion, Atlassian Confluence, Box, Figma, Gong, Granola, Microsoft 365) and that Google Drive and Slack are available as native Claude integrations.
- If no document platforms (Notion, Confluence, Google Drive, Box, Microsoft 365) are connected — only supplementary platforms like Slack, Gong, Granola, or Figma — stop and tell the user: "You don't have any document storage platforms connected. Brand guidelines and style guides almost always live on Google Drive, SharePoint, Notion, Confluence, or Box. Please connect at least one before running discovery."
- If no primary file storage (Google Drive, Microsoft 365, Box) is connected, warn: "None of your primary file storage platforms are connected. Brand documents frequently live on these. Discovery will proceed but results may have significant gaps."
- If only one platform is connected, warn: "Discovery works best with 2+ platforms for cross-source validation. Results from a single platform will have lower confidence scores."
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.
- yesterday First seen · 25 lines · 11 tokens per session scan A 9749f7e23b0b
discover-brand is a command published in the GitHub repository anthropics/knowledge-work-plugins (23,877 stars, last pushed today), licensed Apache-2.0. It adds 11 tokens to every session and 544 once invoked, about $0.0001 per session on Opus 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 2026-09-03.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.