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 skills add bpinheiroms/claude-office --skill setupgit clone --depth 1 https://github.com/bpinheiroms/claude-officeWrote 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/skills/bpinheiroms/claude-office/setup)<a href="https://agentmods.dev/skills/bpinheiroms/claude-office/setup"><img src="https://agentmods.dev/badge/skills/bpinheiroms/claude-office/setup.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 | $0.00011 | $0.00473 |
| Opus 5 | $0.00005 | $0.00236 |
| Sonnet 5 | $0.00002 | $0.00095 |
| Haiku 4.5 | $0.00001 | $0.00047 |
Grade B, and why
setup scanned grade B with 1 finding 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 7d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
Read `~/.claude/settings.json` and check if `statusLine.command` is already configured. What it actually says
You are setting up the Claude Office statusline plugin. Follow these steps precisely:
Step 1: Verify Bun is installed
Run bun --version to confirm Bun is available. This plugin requires Bun.
Step 2: Find the plugin directory
The plugin directory is the directory containing this skills/setup/SKILL.md file — two levels up from skills/setup/.
Verify by checking that package.json exists in that directory.
Store this absolute path as PLUGIN_DIR.
Step 3: Test the statusline
Run a quick test to verify it works:
echo '{}' | bun run PLUGIN_DIR/src/statusline/index.ts
It should produce output (possibly just a newline if no data is available). It must not error.
Step 4: Check for existing statusline
Read ~/.claude/settings.json and check if statusLine.command is already configured.
- If another statusline is found, inform the user:
"You currently have
<existing command>configured as your statusline. Shall I replace it with Claude Office?" Wait for confirmation before proceeding. If the user declines, stop here. - If no statusline is configured, proceed directly.
Step 5: Apply configuration
Update ~/.claude/settings.json to set the statusline command. Read the file first, merge the new config, and write it back to preserve all existing settings:
{
"statusLine": {
"type": "command",
"command": "bun run PLUGIN_DIR/src/statusline/index.ts"
}
}
Replace PLUGIN_DIR with the actual absolute path found in Step 2.
Step 6: Confirm
Tell the user:
Claude Office statusline is now configured! It will appear at the bottom of your Claude Code sessions. You can switch back at any time by editing
~/.claude/settings.json.The statusline shows:
- Plan: Max, Pro, or Team
- Quota: 5-hour and 7-day rate limit utilization bars
- Costs: Today, week, and month estimated spend
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.
- 7d ago First seen · 60 lines · 11 tokens per session scan B bb0796d0011c
setup is a skill published in the GitHub repository bpinheiroms/claude-office (7 stars, last pushed 4mo ago), licensed MIT. It adds 11 tokens to every session and 473 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
ensembl-database
Query Ensembl genome database REST API for 250+ species. Gene lookups, sequence retrieval, variant analysis, comparative genomics, orthologs, VEP predictions, for genomic research.
colab-finetuning
Fine-tune LLMs on Google Colab GPUs directly from openscience. Connects to Colab runtimes via WebSocket bridge for remote training with Unsloth. Supports SFT, GRPO, DPO, vision, and TTS workflows on free T4 to Pro A100 GPUs.
swarm-pr-review
Run a graph-guided, tool-augmented PR review using context packing, parallel exploration, mandatory repository-agnostic risk-family coverage with dispatch scaled to diff size and risk, independent reviewer validation, critic challenge, and metrics writeback. Use for deep pull request review with low false-positive…
loop
Full execution protocol for MODE: LOOP — the compound-engineering loop: brainstorm → plan → build → review → improve, iterating under defense-in-depth stop conditions with generator/critic separation, durable resumable state, and mandatory compounding learning capture. Loaded on demand by the architect when the loop…
restore-internals-seams-in-finally-blocks-after-each-test
When delegating a task affected by this skill, include.
google-meet
Google Meet via gws: create spaces, fetch join links, list recordings.