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 instructions/larscowe/bmalph/claude-mdgit clone --depth 1 https://github.com/LarsCowe/bmalphWrote 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/instructions/larscowe/bmalph/claude-md)<a href="https://agentmods.dev/instructions/larscowe/bmalph/claude-md"><img src="https://agentmods.dev/badge/instructions/larscowe/bmalph/claude-md.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 | $0.01360 | $0.01360 |
| Opus 5 | $0.00680 | $0.00680 |
| Sonnet 5 | $0.00272 | $0.00272 |
| Haiku 4.5 | $0.00136 | $0.00136 |
Grade A, and why
bmalph CLAUDE.md 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 5d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
bmalph
Integration layer between BMAD-METHOD and Ralph.
What is bmalph?
bmalph bundles and installs two AI development systems:
- BMAD-METHOD — Planning agents and workflows (Phases 1-3)
- Ralph — Autonomous implementation loop (Phase 4)
Architecture
Phases 1-3 (Planning): BMAD agents + workflows (interactive, command-driven)
Phase 4 (Implementation): Ralph loop (autonomous, bash-driven)
bmalph: CLI + transition logic
Directory structure after bmalph init
project-root/
├── _bmad/ # BMAD agents, workflows, core, lite workflows
├── .ralph/ # Ralph runtime (loop, libs, specs, logs, drivers)
│ ├── drivers/ # Platform driver scripts (claude-code, codex, opencode, copilot, cursor)
│ ├── lib/ # Shell libraries (circuit breaker, response analysis, etc.)
│ └── templates/ # Prompt, agent, fix plan, review, and ralphrc templates
├── bmalph/ # bmalph state (config.json with platform, state/)
└── <instructions file> # Varies by platform (CLAUDE.md, AGENTS.md, etc.)
The instructions file depends on the configured platform — see src/platform/ for the mapping.
CLI Commands
| Command | Action |
|---|---|
bmalph init |
Install BMAD + Ralph, configure project |
bmalph upgrade |
Update bundled assets to current version |
bmalph doctor |
Check installation health |
bmalph check-updates |
Check for upstream updates |
bmalph status |
Show project installation status |
bmalph implement |
Transition BMAD artifacts to Ralph format |
bmalph run |
Start Ralph loop with live dashboard |
bmalph run --swarm N |
Run N parallel workers in git worktrees (default: 2, max: 6) |
bmalph reset |
Remove all bmalph files from the project |
bmalph watch |
(deprecated) Use bmalph run instead |
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.
- 5d ago First seen · 108 lines · 1,360 tokens per session scan A daa2c7af71ea
bmalph CLAUDE.md is an instructions file published in the GitHub repository LarsCowe/bmalph (405 stars, last pushed 6d ago), licensed MIT. It adds 1,360 tokens to every session, about $0.0068 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 instructions, from other repositories
claude-code-bmad-skills CLAUDE.md
Claude Code instructions for aj-geddes/claude-code-bmad-skills, covering claude.md, the one rule that defines this project, architecture: marketplace → plugin → skills, conventions that are easy to get wrong and commands.
bmad-plugin AGENTS.md
AGENTS.md instructions for PabloLION/bmad-plugin, covering bmad plugin project conventions, runtime, available scripts, upstream sync and core bmad-method release.
CodexPotter AGENTS.md
AGENTS.md instructions for breezewish/CodexPotter, covering repository guidelines, workflow principles, engineering rules, core principles: simplicity & readability and better maintainability.
sugar AGENTS.md
AGENTS.md instructions for roboticforce/sugar, covering sugar - agents.md, git branching rules (strict), always create branches from develop, after work is complete and then create pr targeting develop.
next-payload-ai-fluent-starter AGENTS.md
AGENTS.md instructions for joshuamartyn/next-payload-ai-fluent-starter, covering task-driven development with github + archon, 🔒 critical rule, 📦 task management rules (github), 📚 research workflow (archon) and research checklist (before coding).
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).