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/massdriver-cloud/claude-plugins/developgit clone --depth 1 https://github.com/massdriver-cloud/claude-pluginsWhat 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 | $0.00014 | $0.00422 |
| Opus 5 | $0.00007 | $0.00211 |
| Sonnet 5 | $0.00003 | $0.00084 |
| Haiku 4.5 | $0.00001 | $0.00042 |
Grade A, and why
develop 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 yesterday.
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
Bundle Development
Start the bundle-dev agent to guide you through creating and testing a Massdriver infrastructure bundle.
What This Does
- Setup - Verify MCP auth (
get_viewer) and select/create the target project + environment (MCPcreate_project/create_environment) - Gather requirements - Understand your use case, developer UX needs, and compliance strategy
- Scaffold bundle - Create massdriver.yaml, Terraform code, and supporting files
- Publish bundle (CLI) -
mass bundle publish --development - Add to project blueprint (MCP) -
add_component(once per project) - Pin development channel (MCP) -
update_instancewith versionlatest+dev - Deploy & iterate (MCP) -
create_deployment+get_deployment_logs follow:true, re-publishing and redeploying as code changes - Remediate compliance - Fix Checkov findings according to your strategy
- Journal results (MCP) - Record what was tested via
update_environment
Usage
Provide a description of what bundle you want to create:
/massdriver:develop PostgreSQL database for application backends with dev/staging/prod presets
/massdriver:develop S3 bucket for static asset storage with CloudFront CDN
/massdriver:develop EKS cluster with managed node groups and cluster autoscaler
Instructions
Use the Task tool to spawn the bundle-dev agent with the user's use case description. The agent will handle the interactive workflow, starting with credential/environment setup.
If no use case was provided in the command arguments, ask the user what bundle they want to develop.
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.
- yesterday First seen · 48 lines · 14 tokens per session scan A 661957a82a99
develop is a command published in the GitHub repository massdriver-cloud/claude-plugins (2 stars, last pushed 5d ago), licensed Apache-2.0. It adds 14 tokens to every session and 422 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 2026-08-31.
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.
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.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.