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/hieutrtr/ralphmad/helpgit clone --depth 1 https://github.com/hieutrtr/ralphmadWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/hieutrtr/ralphmad/help)<a href="https://agentmods.dev/commands/hieutrtr/ralphmad/help"><img src="https://agentmods.dev/badge/commands/hieutrtr/ralphmad/help.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.00007 | $0.01006 |
| Opus 5 | $0.00003 | $0.00503 |
| Sonnet 5 | $0.00001 | $0.00201 |
| Haiku 4.5 | $0.00001 | $0.00101 |
Grade A, and why
help 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RalphMAD Plugin Help
Please explain the following to the user:
What is RalphMAD?
RalphMAD is an autonomous BMAD-METHOD workflow execution plugin for Claude Code. It combines:
- Ralph Loop — The self-referential AI loop technique (by Geoffrey Huntley) where the same prompt is repeatedly fed to Claude until a task completion promise is detected
- BMAD Workflows — Structured SDLC workflows from the BMAD methodology (Business Analyst, PM, Architect, etc.)
- Template System — Project-agnostic templates that auto-populate with your project's context
Key Innovation: Unlike hardcoded ralph-prompts, RalphMAD templates read your project's _bmad/bmm/config.yaml and existing artifacts to automatically build context-rich prompts. One plugin works with ANY BMAD-enabled project.
Available Commands
/ralphmad-loop WORKFLOW_NAME [--max-iterations N]
Run a BMAD workflow autonomously. This is the main command.
Workflow names:
product-brief— Create product brief from product concept (Phase 1)prd-create— Create PRD from product brief (Phase 2)ux-design— Create UX design specification (Phase 2)architecture— Create architecture decisions (Phase 3)epics-stories— Create epics and user stories (Phase 3)test-design— Create test design with risk assessment (Phase 3)testarch-framework— Set up test framework (Phase 3)testarch-ci— Set up CI/CD pipeline (Phase 3)sprint-planning— Generate sprint status tracking (Phase 4)testarch-test-design-epic— Test design for specific epic (Phase 4)epic-dev— Implement all stories in an epic (Phase 4)correct-course— Manage sprint changes (Phase 4)
Usage:
/ralphmad-loop product-brief
/ralphmad-loop prd-create --max-iterations 10
/ralphmad-loop architecture
/ralphmad-status
Show the status of all workflows — which are DONE, READY, or BLOCKED (with missing prerequisites).
/ralphmad-cancel
Cancel an active RalphMAD loop.
How It Works
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.
- 4d ago First seen · 103 lines · 7 tokens per session scan A ab6adca18928
help is a command published in the GitHub repository hieutrtr/ralphmad (39 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 7 tokens to every session and 1,006 once invoked, about $0.0000 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
git
Git operations with intelligent commit messages and workflow optimization.
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.