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 skills add mrvladd-d/memobank --skill mb-analysisgit clone --depth 1 https://github.com/mrvladd-d/memobankWrote 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/skills/mrvladd-d/memobank/mb-analysis)<a href="https://agentmods.dev/skills/mrvladd-d/memobank/mb-analysis"><img src="https://agentmods.dev/badge/skills/mrvladd-d/memobank/mb-analysis.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 | $0.00024 | $0.00633 |
| Opus 5 | $0.00012 | $0.00316 |
| Sonnet 5 | $0.00005 | $0.00127 |
| Haiku 4.5 | $0.00002 | $0.00063 |
Grade A, and why
mb-analysis 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 7d 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 — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mb-analysis - Optional Analysis before PRD
- What it does: adds a lightweight Analysis phase before
/prdwhen the idea is vague, unstable, or needs explicit product framing. - Use
/analysiswhen: you need a router that inspects current Memory Bank state and recommends the next command. - Use
/brainstormwhen: the idea is raw and needs facilitated ideation. The AI acts as a coach; the user's product intent and choices remain the source of truth. - Use
/briefwhen: the concept is clear enough to produce a concise Product Brief, or after a brainstorming report exists. - Output: optional artifacts under
.memory-bank/analysis/.
Analysis is optional. Raw PRD text or an existing external PRD should pass /constitution first when project principles are not ratified/partial, then be normalized and checked through /write-prd, producing .memory-bank/prd.md with type: prd, clarification_status: complete, and constitution_checked: true; then /spec-init prepares the lightweight SDD route map before /prd decomposes it. After /prd, /spec-design is mandatory but adaptive: simple T0/T1 scope may record a minimal backbone, while shared/T2/T3 scope records the needed domain/model/contracts/state/security/runtime design. Brownfield projects should map the current codebase first with /map-codebase before planning deltas.
/brief creates the Product Brief as the input contract for /constitution and /write-prd. It is not a PRD, backlog, research report, or marketing document.
The normal planning path is:
/analysis -> /brief -> /constitution -> /write-prd -> /spec-init -> /prd -> /spec-design -> /spec-improve FT-<NNN> -> /prd-to-tasks FT-<NNN>
Use /brainstorm before /brief when the idea is raw. /constitution should read the Product Brief when present and run the governing-principles interview; if the user explicitly skips it, downstream PRD work may continue with framework-default/skipped principles.
Analysis never creates task records. /spec-design also does not create task records or feature-local implementation design; it only updates backbone SDD specs and spec-index, while /spec-improve FT-<NNN> remains the feature-level gate. /clarify-feature FT-<NNN> is optional and only for a specific feature that is explicitly pending/blocked or has decomposition-affecting unresolved markers.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago First seen · 37 lines · 24 tokens per session scan A 5cf81879758a
mb-analysis is a skill published in the GitHub repository mrvladd-d/memobank (55 stars, last pushed 3mo ago), licensed MIT. It adds 24 tokens to every session and 633 once invoked, about $0.0001 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…