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/paulpreibisch/agentvibes/hidegit clone --depth 1 https://github.com/paulpreibisch/AgentVibesWrote 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/paulpreibisch/agentvibes/hide)<a href="https://agentmods.dev/commands/paulpreibisch/agentvibes/hide"><img src="https://agentmods.dev/badge/commands/paulpreibisch/agentvibes/hide.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 5.1 | $0.00016 | $0.00629 |
| Opus 5 | $0.00008 | $0.00315 |
| Sonnet 5 | $0.00003 | $0.00126 |
| Haiku 4.5 | $0.00002 | $0.00063 |
Grade A, and why
hide scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
You are about to hide all AgentVibes slash commands from the Claude Code interface.
What this does:
- Moves all AgentVibes commands from
.claude/commands/agent-vibes/to.claude/.agentvibes-backup/ - Keeps only the
show.mdandhide.mdcommands visible - Creates a flag file to track hidden state
- Does NOT affect MCP functionality - you can still use AgentVibes through MCP tools
IMPORTANT IMPLEMENTATION STEPS:
-
Check if already hidden:
- Check if
.claude/.agentvibes-hidden.flagexists - If it exists, respond: "⚠️ AgentVibes commands are already hidden. Use /agent-vibes:show to restore them."
- Stop execution
- Check if
-
Create backup directory:
mkdir -p .claude/.agentvibes-backup -
Move all command files EXCEPT hide.md and show.md:
cd .claude/commands/agent-vibes # Move all files except hide.md and show.md for file in *.md *.json; do if [ "$file" != "hide.md" ] && [ "$file" != "show.md" ]; then mv "$file" ../../.agentvibes-backup/ fi done -
Create the hidden state flag:
touch .claude/.agentvibes-hidden.flag -
Display success message:
✅ AgentVibes commands hidden successfully! 📦 Backed up to: `.claude/.agentvibes-backup/` 🔄 Please reload Claude Code to see changes: Press Ctrl+Shift+P → "Developer: Reload Window" 💡 To restore commands, use: /agent-vibes:show ℹ️ MCP functionality is unaffected - AgentVibes MCP tools still work normally.
Files that will be hidden:
- add.md
- agent-vibes.md
- agent.md
- agent-health-coach.md
- agent-motivator.md
- agent-negotiator.md
- bmad.md
- get.md
- language.md
- learn.md
- list.md
- personality.md
- preview.md
- provider.md
- replay-target.md
- replay.md
- sample.md
- sentiment.md
- set-favorite-voice.md
- set-language.md
- set-pretext.md
- set-speed.md
- switch.md
- target-voice.md
- target.md
- update.md
- version.md
- whoami.md
- commands.json
Files that will remain visible:
- hide.md (this command)
- show.md (to restore commands)
Now execute the hiding process following the steps above.
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.
- 2d ago First seen · 92 lines · 16 tokens per session scan A 80ac0970d257
hide is a command published in the GitHub repository paulpreibisch/AgentVibes (153 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 16 tokens to every session and 629 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
email-domains
Apply the CLI runtime and safety contract before executing a command. Runtime --help is authoritative.
email-providers
Apply the CLI runtime and safety contract before executing a command. Runtime --help is authoritative.
open
Apply the CLI runtime and safety contract before executing a command. Runtime --help is authoritative.
whoami
Apply the CLI runtime and safety contract before executing a command. Runtime --help is authoritative.
workflow-manager
Process automation with TodoWrite planning and Task execution.
t_metaprompt_workflow
Based on the High Level Prompt follow the Workflow, to create a new prompt in the Specified Format. Before you start, WebFetch everything in the Documentation.