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/plangit 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 | $0.00384 |
| Opus 5 | $0.00000 | $0.00192 |
| Sonnet 5 | $0.00000 | $0.00077 |
| Haiku 4.5 | $0.00000 | $0.00038 |
Grade A, and why
plan 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:plan
Generate an evidence-based implementation plan for the active milestone. Evidence First — no fake docs. Build the wall between modules!
Steps
- Start the live board in the browser:
mpga board live --serve --open - Read
MPGA/INDEX.mdfor active milestone - Read the milestone's PLAN.md:
cat MPGA/milestones/<id>/PLAN.md - Read relevant scope documents based on milestone objective
- Spawn
researcherplus any needed read-onlyscoutagents in parallel ifconfig.agents.researchBeforePlanis true - Break work into bite-sized tasks (2-10 min each):
- Each task MUST cite exact files to modify (with evidence links)
- Each task MUST cite expected test file locations
- Each task MUST have mechanically verifiable acceptance criteria
- Each task should declare its scope so independent scopes can run in parallel
- One write lane per scope
- Create task cards on the board:
mpga board add "<title>" --priority <p> --scope <scope> --column todo - Write the plan to
MPGA/milestones/<id>/PLAN.md - Show board:
mpga board show
Usage
/mpga:plan
/mpga:plan M001-auth-system
Plan quality criteria
- Each task references specific files with evidence links
- Acceptance criteria are checkboxes, not prose
- No task is more than 10 minutes of work
- Dependencies between tasks are explicit
- Evidence links expected for each task are listed
- Parallel-safe tasks are separated from same-scope write conflicts — Lock her up! (the race condition!)
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 · 38 lines · 0 tokens per session scan A de3eb074a467
plan 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 384 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.