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/gengit 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 | $0.00768 |
| Opus 5 | $0.00007 | $0.00384 |
| Sonnet 5 | $0.00003 | $0.00154 |
| Haiku 4.5 | $0.00001 | $0.00077 |
Grade A, and why
gen 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.
How it starts
The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Quick Bundle Generation
Generate a Massdriver bundle scaffold based on a use case description. This is the non-interactive "quick gen" mode - it creates the bundle files and hands off to you for testing.
What This Does
- Ask a few quick questions about the bundle
- Generate the complete bundle structure
- Run local validation (
mass bundle build,tofu validate) - Hand off to you for deployment and testing
Usage
/massdriver:gen RDS MySQL database for OLTP workloads
/massdriver:gen Lambda function with API Gateway trigger
/massdriver:gen S3 bucket for data lake landing zone
Instructions
1. Quick Requirements
Ask the user (if not clear from the description):
- Cloud provider (AWS, GCP, Azure)?
- What connections does it need (network, credentials)?
- What artifact does it produce?
- Any specific presets they want?
2. Generate Bundle Structure
Create the bundle in bundles/<bundle-name>/:
bundles/<bundle-name>/
├── massdriver.yaml # Bundle manifest with params, connections, artifacts
├── README.md # Bundle documentation
├── operator.md # Runbook template
└── src/
├── main.tf # Primary Terraform code
├── artifacts.tf # massdriver_resource resources
└── .checkov.yml # Checkov skip rules (if any)
3. Apply Best Practices
- Params: Focus on 3-5 developer-facing questions, use presets
- 80/20 rule: Cover common use cases, don't over-generalize
- Connections: Use existing resource types (
mass resource-type list) - Runbook:
operator.mdis engineer-facing — no templating-context meta or config snapshots (the product has a config panel), no explainer headings; actionable ops sections with runnable commands, resource-sourced values wrapped in{{#resources.<name>}}guards - Artifacts: Match the resource type's schema exactly (the YAML key is still
artifacts:; runtime calls them resources) - Provider:
mass resource-type get <platform>FIRST, then write provider using only those fields — resource types and providers are 1:1 - Compliance: Default to secure settings, add
halt_on_failurefor prod
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 · 93 lines · 14 tokens per session scan A fb8a1b09b7e8
gen 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 768 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.