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/lovablelabs/mcp/buildgit clone --depth 1 https://github.com/lovablelabs/mcpWhat 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 | $0.00013 | $0.00221 |
| Opus 5 | $0.00006 | $0.00111 |
| Sonnet 5 | $0.00003 | $0.00044 |
| Haiku 4.5 | $0.00001 | $0.00022 |
Grade A, and why
build 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
Build a new Lovable app described as: $ARGUMENTS
Use the Lovable MCP tools to do this end to end:
- Call
list_workspacesto find the target workspace. If the user belongs to more than one, ask which to use. - Confirm with the user before spending credits. Then call
create_projectin that workspace with an initial build prompt derived from the description above. - Follow the agent's progress with
send_message/get_messageuntil the initial build completes. - Call
get_projectand share the editor URL and preview URL with the user. - Ask whether to publish. If yes, call
deploy_projectand return the live URL.
Notes:
create_projectandsend_messageconsume Lovable build credits — always confirm first.deploy_projectpublishes a publicly reachable URL on Free/Pro plans.
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 · 19 lines · 13 tokens per session scan A af9566700c86
build is a command published in the GitHub repository lovablelabs/mcp (3 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 13 tokens to every session and 221 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 2026-08-30.
Other commands, from other repositories
release
Run the cabloy release workflow. Use when the user asks to "release", "publish", "deploy", "bump version", "create release", "release patch", "release minor", or "release major". Handles version bump, AI changelog generation, npm publish, and GitHub release creation.
goham
End-to-end workflow for working on tasks from a connected Hamster brief. All tasks from the brief are worked on in a single branch, with one PR created at the end.
pr-comments
Fix PR review comments: PR # $ARGUMENTS.
help
Command "help" from eyaltoledano/claude-task-master, covering task master ai command help, quick navigation, command categories, quick start examples and getting started.
complexity-report
Display the task complexity analysis report.
learn
Learn about Task Master capabilities through interactive exploration.