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/mims-harvard/tooluniverse/setup-keysgit clone --depth 1 https://github.com/mims-harvard/ToolUniverseWrote 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/mims-harvard/tooluniverse/setup-keys)<a href="https://agentmods.dev/commands/mims-harvard/tooluniverse/setup-keys"><img src="https://agentmods.dev/badge/commands/mims-harvard/tooluniverse/setup-keys.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 | $0.00070 | $0.00694 |
| Opus 5 | $0.00035 | $0.00347 |
| Sonnet 5 | $0.00014 | $0.00139 |
| Haiku 4.5 | $0.00007 | $0.00069 |
Grade A, and why
setup-keys scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are setting up ToolUniverse API keys for the user. Keys are read from the
environment by tools at run time and persisted in a .env that ToolUniverse
auto-loads. Follow these steps exactly.
Step 1 — Ask which mode
Ask the user (use the AskUserQuestion tool):
- Graphical interface — a local web page with a form for all keys.
- Agent-guided — I ask you for keys here in chat.
Step 2 — Ask where to store
Ask the user:
- Global
~/.tooluniverse/.env(recommended) — works across all projects. - Project-local
./.tooluniverse/.env— only this project; read when the MCP server runs from this directory.
Resolve the target path:
- Global ->
~/.tooluniverse/.env - Local ->
<current working directory>/.tooluniverse/.env
Step 3a — Graphical mode
Run (do NOT redirect or background it; it prints a URL and blocks until the user saves, then exits):
python "${CLAUDE_PLUGIN_ROOT}/scripts/setup_keys_server.py" --target <TARGET_ENV_PATH>
If api_keys_catalog.json is not found next to the script (e.g. running from a
source checkout), add --catalog <repo>/src/tooluniverse/data/api_keys_catalog.json.
Show the user the printed http://127.0.0.1:... URL in case the browser does
not open automatically. When the command exits, report the target path and the
number of keys saved. Never print the key values.
Step 3b — Agent-guided mode
- Read the catalog:
python -c "import json; print(json.dumps(json.load(open('${CLAUDE_PLUGIN_ROOT}/scripts/api_keys_catalog.json'))))"(fall back to the repo pathsrc/tooluniverse/data/api_keys_catalog.json). - Ask the user whether to set all required keys, or name specific APIs.
- For each selected key, show its
register_urlanddescription, then ask for the value. Do not echo previously stored values. - Write all collected values at once with the helper.
keys_env.pyexposesmerge_env(path, updates); call it from a short inline Python snippet, passing the target path and a dict of the values you collected:
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.
- 4d ago First seen · 64 lines · 70 tokens per session scan A 910d289326b3
setup-keys is a command published in the GitHub repository mims-harvard/ToolUniverse (1,670 stars, last pushed yesterday), licensed Apache-2.0. It adds 70 tokens to every session and 694 once invoked, about $0.0003 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 2026-08-30.
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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
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.