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/mrvladd-d/memobank/reviewgit 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/commands/mrvladd-d/memobank/review)<a href="https://agentmods.dev/commands/mrvladd-d/memobank/review"><img src="https://agentmods.dev/badge/commands/mrvladd-d/memobank/review.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 | $0.00028 | $0.02031 |
| Opus 5 | $0.00014 | $0.01015 |
| Sonnet 5 | $0.00006 | $0.00406 |
| Haiku 4.5 | $0.00003 | $0.00203 |
Grade A, and why
review 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/review — Multi-expert Memory Bank review
Это не per-task adversarial semantic verification. Для вопроса "решение по существу правильное?" используй /red-verify TASK-<ID>.
0) Артефакты
Создай:
.tasks/TASK-MB-REVIEW/.tasks/TASK-MB-REVIEW/REQUEST.md(что ревьюим, какой режим, какие blocking concerns)
Каждый reviewer пишет отчёт в:
.tasks/TASK-MB-REVIEW/TASK-MB-REVIEW-<STAGE_ID>-final-report-docs-01.md
1) Запусти reviewers (fresh context)
Canonical STAGE_ID table:
| STAGE_ID | Reviewer |
|---|---|
S-01 |
Architect (C4 + boundaries + ADR) |
S-02 |
Scope/RTM (REQ→EP→FT) |
S-03 |
Plan/tasks (JSON records/index/waves/gates) |
S-04 |
Security |
S-05 |
MBB compliance |
S-06 |
Code quality (optional, if code exists) |
Constitution checks are blocking:
- If
.memory-bank/constitution.mdexists, reviewers must flag contradictions between the Constitution and Memory Bank docs, task records, workflow routing, implementation plans, or proposed execution. - A Constitution violation is a blocking finding and must result in
REJECTuntil fixed or explicitly resolved through/constitution. - Do not treat missing domain-specific principles as a violation unless another normative source requires them.
Analysis Quality checks are conditional:
- If
.memory-bank/analysis/product-brief.mdexists, include a lightweight pass inS-02orS-05. - Do not fail a project merely because Analysis artifacts are absent; Analysis before PRD is optional.
- If a product brief exists, check that PRD / requirements / epics / features are traceable to it or explicitly document deltas.
- Check that the brief is not blocked / no-go / not ready with unresolved blocking questions unless
/prdrecorded an explicit user override. - If brainstorming artifacts exist without a product brief, report a warning unless an existing PRD was intentionally used as the upstream source.
- Confirm there is no route from Analysis or Product Brief directly to
/prd-to-taskswithout/write-prd,/spec-init,/prd,/spec-design, and/spec-improve;/clarify-featureis optional and only for explicit feature blockers. - Confirm shared T2/T3 design concerns are not duplicated across feature-local specs when
/spec-designshould have produced a common authoritative backbone.
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 · 101 lines · 28 tokens per session scan A 6008aaec3589
review is a command published in the GitHub repository mrvladd-d/memobank (55 stars, last pushed 3mo ago), licensed MIT. It adds 28 tokens to every session and 2,031 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 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.
session-end
I'll summarize this coding session and update the memory system with our accomplishments.
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.