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/nicelight/devrails-26/mb-gardengit clone --depth 1 https://github.com/nicelight/DevRails-26Wrote 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/nicelight/devrails-26/mb-garden)<a href="https://agentmods.dev/commands/nicelight/devrails-26/mb-garden"><img src="https://agentmods.dev/badge/commands/nicelight/devrails-26/mb-garden.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 5.1 | $0.00000 | $0.01402 |
| Opus 5 | $0.00000 | $0.00701 |
| Sonnet 5 | $0.00000 | $0.00280 |
| Haiku 4.5 | $0.00000 | $0.00140 |
Grade A, and why
mb-garden 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 6d 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/mb-garden — Memory Bank maintenance
1) Read-only scan и classification
- Сначала проведи read-only scan. До классификации findings ничего не меняй.
- Пункты scan ниже являются coverage criteria, а не обязательным порядком. Выбери порядок, инструменты и глубину проверки по фактическому состоянию Memory Bank, но покрой каждую применимую surface до классификации её finding.
- Пробеги
.memory-bank/index.mdи роутеры в подпапках. - Прочитай
.memory-bank/spec-index.mdи проверь, что active specs используютType | Path | Status | Scope | Change route, один active canonical path на concern и direct feature/task links безused_by/file-owner metadata. - Если есть
.memory-bank/constitution.md, проверь ссылки и упоминания Constitution в MBB, spec-backbone, spec-index, workflows, AGENTS.md и generated plans. - Найди stale или contradictory Constitution references: старые пути, alias-команды, legacy task/risk routing, или правила, противоречащие текущей Constitution.
- Найди
Known gaps / TBD / TODO, но не закрывай их и не превращай в задачи от имени garden. - Для linked
.memory-bank/behavior-specs/*.behavior.jsonпроверь feature links и tasksource_artifacts. Stale examples классифицируй как notes в findings, если обычный AC/spec/verification source не сломан. - Сверь
.memory-bank/skills/index.mdс реально установленными.agents/skills/*/SKILL.mdи.claude/skills/*/SKILL.md. Реестр должен использовать canonical runtime command names без второй alias/package surface. - Если есть
.memory-bank/scripts/mb-lint.mjs, initial lint можно использовать как read-only источник findings. Он не заменяет final lint после edits. - Раздели findings на две группы:
- automatic: только stale/broken links и несогласованные index/router entries, для которых существует один однозначный target и не требуется менять смысл;
- blockers: archive/delete/merge, выбор между competing canonical material, TODO/gap-to-task conversion и любые material canonical, task, lifecycle, product, design, contract, security или governance decisions.
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.
- 6d ago First seen · 110 lines · 0 tokens per session scan A 3216a1f9de71
mb-garden is a command published in the GitHub repository nicelight/DevRails-26 (22 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,402 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 2026-08-30.
Other commands, from other repositories
minutes-ideas
Surface recent voice memos and ideas captured from any device. Use when the user asks "what ideas did I have?", "what were my recent memos?", "what did I record while walking?", or wants to recall a captured thought.
learn
Force claude-smart to extract learnings from this session now.
memory-store
Store an insight, decision, or pattern to memory.
cc-memory
Configure persistent memory that survives across sessions using a layered approach: split rule files for always-loaded context, auto-memory for organic learning, and optional MCP-backed long-term memory for large codebases.
analyze-context
USE WHEN you want to analyze project context before starting work on a task. Calls context + recall, then synthesizes goals, decisions, gotchas, and relevant memories into a pre-task brief.
music-suno-prompt
Grounded Suno prompt synthesis from local knowledge corpus + persona canon + label canon. No vibes-prompting.