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.
git clone --depth 1 https://github.com/TribeAI/claude-cowork-brand-voice-pluginWrote 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/tribeai/claude-cowork-brand-voice-plugin/enforce-voice)<a href="https://agentmods.dev/commands/tribeai/claude-cowork-brand-voice-plugin/enforce-voice"><img src="https://agentmods.dev/badge/commands/tribeai/claude-cowork-brand-voice-plugin/enforce-voice/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/commands/tribeai/claude-cowork-brand-voice-plugin/enforce-voice"><img src="https://agentmods.dev/badge/commands/tribeai/claude-cowork-brand-voice-plugin/enforce-voice.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 | $0.00006 | $0.00421 |
| Opus 5 | $0.00003 | $0.00211 |
| Sonnet 5 | $0.00001 | $0.00084 |
| Haiku 4.5 | $0.00001 | $0.00042 |
Grade A, and why
enforce-voice 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 13d 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.
This is a copy
100% identical to enforce-voice — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
MANDATORY FIRST STEP — do this before anything else, including loading guidelines or processing the content request. Check whether the user has a working folder selected for this session. You must verify this before starting any enforcement 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 load saved guidelines from a previous session, and any guidelines generated in this conversation won't be saved for future sessions either. Please select a working folder and re-run this command. If you'd like to proceed anyway (guidelines will only be usable in this session), let me know." Wait for the user to confirm before continuing.
Load the user's brand guidelines and apply them to the content request provided in $ARGUMENTS.
Find brand guidelines using this sequence (stop as soon as found):
- Session context — check if guidelines were generated earlier in this conversation
- Local guidelines file — check for
.claude/brand-voice-guidelines.mdinside the user's working folder. Do NOT use a relative path from the agent's current working directory (in Cowork, the agent runs from a plugin cache directory). If no working folder is set, skip this step. - If not found, ask the user to run
/brand-voice:discover-brand,/brand-voice:generate-guidelines, or paste guidelines directly
Once guidelines are loaded, follow the brand-voice-enforcement skill instructions to:
- Analyze the content request (type, audience, key messages, requirements)
- Apply voice constants ("We Are / We Are Not") and flex tone for context (formality, energy, technical depth)
- Generate content applying voice, tone, messaging, and terminology guidelines
- Validate output against brand do's and don'ts
- Present the content with a brief explanation of brand choices made
- Note any open questions from guidelines that affect this content
- Offer to refine based on feedback
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.
- 13d ago First seen · 23 lines · 6 tokens per session scan A ab67acc3ab40
enforce-voice is a command published in the GitHub repository TribeAI/claude-cowork-brand-voice-plugin (35 stars, last pushed 3mo ago), licensed MIT. It adds 6 tokens to every session and 421 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to enforce-voice, differing in 0 lines, and is treated as a copy.
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.