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/fockus/skill-memory-bank/groomgit clone --depth 1 https://github.com/fockus/skill-memory-bankWrote 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/fockus/skill-memory-bank/groom)<a href="https://agentmods.dev/commands/fockus/skill-memory-bank/groom"><img src="https://agentmods.dev/badge/commands/fockus/skill-memory-bank/groom.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 | $0.00030 | $0.01083 |
| Opus 5 | $0.00015 | $0.00541 |
| Sonnet 5 | $0.00006 | $0.00217 |
| Haiku 4.5 | $0.00003 | $0.00108 |
Grade A, and why
groom 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/mb groom
Groom a task with the agent before (or during, or after) implementation. Unlike /mb discuss, the goal is NOT to produce a spec — it is to cover the white spots: the agent approaches the requirements critically, challenges the user on whether the thing should be done at all and how exactly, proposes its own solutions, gives advice, and asks follow-up questions.
Usable at any stage: a raw idea, a task that already has a spec, a decision worth revisiting, or any open question. The resulting context and decisions then feed spec planning (/mb sdd) or change already-accepted decisions.
Difference from /mb discuss
/mb discuss |
/mb groom |
|
|---|---|---|
| Goal | EARS-validated requirements → context/<topic>.md, status: ready for /mb sdd//mb plan |
Cover white spots, challenge the task, record decisions |
| Output | Requirements document | Dialogue summary + decisions routed into agreements/backlog |
| EARS enforcement | Yes | No |
| Fixed phases | 5 phases + size triage + transcript contracts | Free-form, driven by white spots |
Alias note: /mb ask_me is an alias for /mb discuss, not for groom.
Workflow
Pre-flight
- Resolve
MB_PATH = .memory-bank/. Refuse if missing (suggest/mb init). GROOM_FILE = $MB_PATH/context/<topic>-groom.md(same folder as/mb discussoutput).- Read existing artifacts first — groom against reality, not from scratch:
context/<topic>.md,specs/<topic>/, matchingplans/*.md,agreements.md,backlog.mdentries mentioning the topic (best-effort, skip missing).
Research (before the first question)
Same evidence discipline as /mb discuss Phase 0, lighter: codebase recon (code graph / mb-semantic-search.py / grep, cite file:line), prior decisions (/mb recall <topic>, agreements.md, notes/). Recommendations must cite evidence; a recommendation without a citation is a guess — say so.
Grooming dialogue
Reuse the grilling rules from commands/discuss.md (recommend-first, one question per turn, concrete scenarios, surface contradictions with code, decision ledger), plus the grooming-specific stance:
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 · 63 lines · 30 tokens per session scan A a4c2cac5e71d
groom is a command published in the GitHub repository fockus/skill-memory-bank (25 stars, last pushed 1mo ago), licensed MIT. It adds 30 tokens to every session and 1,083 once invoked, about $0.0002 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
vitaecontext-github
Audit or improve GitHub profile and repository SEO.
vitaecontext-vitaegraph
Create, validate, index, or use a private VitaeGraph.
setup
Fetch Kobiton credentials from the authenticated MCP server and write them to /.kobiton/.credentials.
bug-check
Run automated tests and build checks first, then agent code review. For each bug found, propose or document a regression test.
review-video
Make a " Reviews" video — a fast, faceless VO montage of REAL, verified competitor reviews that names the recurring complaints and positions YOUR business as the alternative, then hands off to your own customer testimonials.
clean
Remove the git worktrees review checked PR code out into. Each one is a full checkout on disk; nothing else is touched.