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.
git 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/review)<a href="https://agentmods.dev/commands/fockus/skill-memory-bank/review"><img src="https://agentmods.dev/badge/commands/fockus/skill-memory-bank/review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/fockus/skill-memory-bank/review"><img src="https://agentmods.dev/badge/commands/fockus/skill-memory-bank/review.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00040 | $0.01018 |
| Opus 5.5 | $0.00016 | $0.00407 |
| Sonnet 5.5 | $0.00008 | $0.00204 |
| Haiku 4.5 | $0.00004 | $0.00102 |
Grade A, and why
review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 14d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review — uncommitted code
1. Gather context
Run:
git diff --staged --name-only
git diff --name-only
git diff
git diff --staged
If ./.memory-bank/roadmap.md or ./.memory-bank/checklist.md exists, read it. That is the current work plan — compare the implementation against it.
If ./.memory-bank/codebase/ARCHITECTURE.md and ./.memory-bank/codebase/CONCERNS.md exist, read them too — ARCHITECTURE.md grounds the architectural analysis in Section 3, CONCERNS.md tells you which known-fragile areas deserve extra scrutiny when touched.
Read every changed file in full, not just the diff — you need full context for architectural analysis.
2. Principles + architecture — deterministic check first
Run the rules checker on the changed files (deterministic SRP / Clean Architecture / TDD-delta):
bash "${MB_SKILLS_ROOT:-$HOME/.claude/skills/memory-bank}/scripts/mb-rules-check.sh" --files <comma-separated list from step 1> --base HEAD --out json
Every CRITICAL violation becomes a Critical item in the Report (step 8), every WARNING a Serious item.
Thresholds and their meaning are defined once in rules/RULES.md.
Apply the remaining judgment-only checks inline:
- KISS — overcomplicated solutions, needless abstractions
- YAGNI — code written "for the future" with no present call site
These are intentionally not deterministic; the enforcer cannot replace a careful human look at "is this code simpler than it needs to be?"
3. Implementation correctness
- Does the code do what the diff/commit claims?
- Is there dead or unreachable code?
- Are there unfinished
TODO,FIXME,HACK, stubs, or placeholders? - Error handling: are all exceptional paths covered?
- Edge cases: empty values,
nil/None, empty collections, boundary numbers - Race conditions in async code
4. Plan alignment
If ./.memory-bank/roadmap.md or ./.memory-bank/checklist.md is found:
- Which plan items are implemented in these changes?
- Which plan items are NOT implemented even though they should be?
- Is there any code that was not part of the plan (scope creep)?
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.
- 14d ago Changed · +25 tokens per session 8da31d30e389
- 23d ago Changed · -8 lines 66a667e66f2f
- 1mo ago First seen · 132 lines · 15 tokens per session scan A a273565d61f9
review is a command published in the GitHub repository fockus/skill-memory-bank (29 stars, last pushed 3d ago), licensed MIT. It adds 40 tokens to every session and 1,018 once invoked, about $0.0002 per session on Opus 5.5. 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
sota-audit
Audit this codebase against the library — agree and pin the scope, route from the surfaces rather than from whatever happened to get loaded, map the trust boundaries, run the scanners, walk every applicable rules file's Audit checklist item by item, ask the questions that need a decision, then fix what you agree to.…
sota-deep-audit
The heavy audit — a hostile review of a whole repository by someone who will inherit it: the threat model reconstructed from the code and a control-presence matrix built against it, then code, history, decisions, results and forward plan, fanned out across independent agents, load-bearing claims re-measured this…
unity-review
Full Unity-aware code review — checks serialization safety, performance, architecture, and Unity-specific pitfalls.
review
Run code review on recent changes.
api-review
Review API design for REST conventions and best practices.
db-review
Review database schema, queries, and migrations.