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/generate-guidelinesgit 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/generate-guidelines)<a href="https://agentmods.dev/commands/anthropics/knowledge-work-plugins/generate-guidelines"><img src="https://agentmods.dev/badge/commands/anthropics/knowledge-work-plugins/generate-guidelines.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 | $0.00015 | $0.00506 |
| Opus 5 | $0.00008 | $0.00253 |
| Sonnet 5 | $0.00003 | $0.00101 |
| Haiku 4.5 | $0.00002 | $0.00051 |
Grade A, and why
generate-guidelines 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:
- generate-guidelines — 100% identical, 0 lines differ
What it actually says
MANDATORY FIRST STEP — do this before anything else, including reading sources or processing arguments. Check whether the user has a working folder selected for this session. You must verify this before starting any guideline generation work. If there is no working folder, stop and warn the user: "You don't have a working folder selected. Without one, I can't save guidelines to a file — they'll only exist in this conversation and won't persist to future sessions. Please select a working folder and re-run this command. If you'd like to proceed anyway, let me know." Wait for the user to confirm before continuing.
Generate comprehensive, LLM-ready brand voice guidelines from whatever sources the user provides — brand documents, conversation transcripts, a discovery report from /brand-voice:discover-brand, or direct input.
Process the sources specified in $ARGUMENTS. If none specified, check:
- Whether a discovery report was generated in this session
.claude/brand-voice.local.mdfor known brand material locations- Connected platforms (Notion, Confluence, Google Drive, Box, SharePoint, Gong) for existing materials
- If nothing is available, suggest running
/brand-voice:discover-brandfirst
Follow the guideline-generation skill instructions to:
- Identify and classify all available sources (discovery report, documents, transcripts)
- Delegate to document-analysis and conversation-analysis agents as needed
- Synthesize findings into unified guidelines with "We Are / We Are Not" table and tone-by-context matrix
- Assign confidence scores per section
- Surface open questions with agent recommendations for any ambiguity
- Present key findings and offer next steps
- Save guidelines to
.claude/brand-voice-guidelines.mdinside the user's working folder (archiving any existing file first). Do NOT use a relative path from the agent's current working directory — in Cowork, the agent runs from a plugin cache directory, not the user's project.
After generation, guidelines are saved locally so /brand-voice:enforce-voice can automatically find them in future sessions.
Supported document formats: PDF, PowerPoint, Word, Markdown, plain text. Supported transcript sources: Gong (MCP), Granola (MCP), Notion meeting notes, manual uploads.
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 · 29 lines · 15 tokens per session scan A 86bd7b41be99
generate-guidelines is a command published in the GitHub repository anthropics/knowledge-work-plugins (23,849 stars, last pushed 2d ago), licensed Apache-2.0. It adds 15 tokens to every session and 506 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
git
Git operations with intelligent commit messages and workflow optimization.
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.