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/benrben/mpga/developgit clone --depth 1 https://github.com/benrben/MPGAWhat 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 | $0.00000 | $0.00306 |
| Opus 5 | $0.00000 | $0.00153 |
| Sonnet 5 | $0.00000 | $0.00061 |
| Haiku 4.5 | $0.00000 | $0.00031 |
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
/mpga:develop
Orchestrate the TDD cycle for a task (red → green → blue → review). Tremendous cycle, believe me. MPGA alone can fix it.
Steps
- Start the live board in the browser:
mpga board live --serve --open - Claim the task:
mpga board claim <task-id> - Load context: task card + relevant scope docs
- Claim the scope-local write lane. Independent scopes may run in parallel; same-scope writers may not.
- red↔green micro-cycle: red-dev writes ONE failing test (starting with degenerate case), green-dev makes it pass, repeat until all acceptance criteria covered. If handoff overhead dominates, allow one extra queued failing test in the same hot scope. If green-dev hits an architectural wall, blue-dev does a structural refactor mid-cycle.
- Let
scout/auditorrun in the background as read-only helpers - blue-dev: refactor both production code and tests (without changing assertions)
- reviewer: review for quality, testability, and degenerate case coverage
- Use
verifierfor milestone boundaries, risky tasks, or explicit full verification - Record evidence and move task to done — Great job! Ready for peace — zero merge conflicts
Usage
/mpga:develop
/mpga:develop T001
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 · 23 lines · 0 tokens per session scan A ec5338c3ffcd
develop is a command published in the GitHub repository benrben/MPGA (5 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 306 tokens. 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.