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 skills/mrvladd-d/memobank/mb-map-codebasenpx skills add mrvladd-d/memobank --skill mb-map-codebasegit clone --depth 1 https://github.com/mrvladd-d/memobankWhat 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 | $0.00022 | $0.00923 |
| Opus 5 | $0.00011 | $0.00462 |
| Sonnet 5 | $0.00004 | $0.00185 |
| Haiku 4.5 | $0.00002 | $0.00092 |
Grade A, and why
mb-map-codebase 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 2d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mb-map-codebase — Brownfield: Repo → Memory Bank
- What it does: scans an existing repository, merges evidence from scoped workers, and writes as-is Memory Bank docs.
- Use it when: code already exists and you need a reliable baseline before planning changes.
- Input: repository root plus an initialized
.memory-bank/. - Output: product, architecture, testing, runbook, and contract docs that describe the current system without speculative task planning.
Preconditions
- You are in the repo root.
.memory-bank/skeleton exists (if not, runmb-init).
Process
1) Start a protocol + task folder
Create:
.protocols/MAP-CODEBASE/plan.md.protocols/MAP-CODEBASE/progress.md.protocols/MAP-CODEBASE/verification.md(mapping completeness + evidence).protocols/MAP-CODEBASE/handoff.md.protocols/MAP-CODEBASE/decision-log.md(optional)
Create:
.tasks/TASK-MB-MAP/
Plan MUST include MB-SYNC (link .memory-bank/workflows/mb-sync.md).
2) Spawn scanning subagents (parallel)
Use ./agents/shared-repo-scanner.md as the base worker prompt.
Rules:
- Max 5–7 parallel subagents.
- Non-overlapping scopes (to avoid conflicts).
- Smart calling: each worker validates that its globs match real files.
Suggested scopes:
- S-01 tooling/CI
- S-02 backend/services
- S-03 frontend/UI
- S-04 data layer
- S-05 tests/quality
Each subagent writes:
.tasks/TASK-MB-MAP/TASK-MB-MAP-S-0X-final-report-<code|docs>-01.md
3) Fan-in (mandatory)
Before writing final docs:
- read all worker reports
- merge into a single outline
- resolve contradictions (or record them as “needs verification”)
- write a short fan-in note into
.protocols/MAP-CODEBASE/progress.mdwith:- which reports were used
- what conflicted and how resolved
- open questions
4) Synthesize Memory Bank (as-is)
Using the fan-in view, create/update:
- product brief (
.memory-bank/product.md) - architecture overview (
.memory-bank/architecture/) - normative routing docs when supported by evidence (
.memory-bank/spec-index.md,.memory-bank/glossary.md,.memory-bank/invariants.md) - runbooks (
.memory-bank/runbooks/) - contracts (
.memory-bank/contracts/) - states (
.memory-bank/states/) when lifecycle/state rules are evident from code, workflows, or tests - testing strategy (
.memory-bank/testing/index.md) - index (
.memory-bank/index.md)
What ships with it
1 file 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.
- 2d ago First seen · 103 lines · 22 tokens per session scan A 6d5525291f2d
mb-map-codebase is a skill published in the GitHub repository mrvladd-d/memobank (55 stars, last pushed 3mo ago), licensed MIT. It adds 22 tokens to every session and 923 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.