Install
$ agentstack add skill-mrvladd-d-memobank-mb-init ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
mb-init — Initialize Memory Bank skeleton
- What it does: creates the base folders, core docs, and project-native command proxies.
- Use it when: you want the skeleton only, without immediately choosing PRD or brownfield mapping.
- Input: repository root.
- Output:
.memory-bank/,.tasks/,.protocols/,AGENTS.md, and generated command stubs.
Goal
Create a consistent baseline so agents can work with repo-local context instead of ad-hoc prompts.
Steps
1) Create directories
Create (if missing):
.memory-bank/with subfolders (see./references/shared-structure-template.md).tasks/.protocols/
2) Create core Memory Bank files
From templates, create:
AGENTS.mdCLAUDE.md→ symlink/copy toAGENTS.md.memory-bank/index.md.memory-bank/constitution.md.memory-bank/mbb/index.md.memory-bank/spec-index.md.memory-bank/glossary.md.memory-bank/invariants.md.memory-bank/product.md.memory-bank/requirements.md.memory-bank/schemas/task.schema.json.memory-bank/tasks/index.json.memory-bank/testing/index.md.memory-bank/skills/index.md
Fresh PRD-less bootstrap must not create .memory-bank/features/FT-001-*.md, .memory-bank/tasks/TASK-001.task.json, or any other fake roadmap artifact. .memory-bank/tasks/index.json starts as { "version": 1, "tasks": [] }; /write-prd creates a clarified PRD, /spec-init prepares only the lightweight SDD route map, /prd creates real features, mandatory /spec-design creates a minimal or full backbone gate, /spec-improve FT- completes or marks unnecessary feature design, and /prd-to-tasks FT- creates real TASK-*.task.json records after that. /clarify-feature FT- is optional for explicitly pending/blocked features.
Also create optional folders that support the richer normative layer without making it mandatory:
.memory-bank/contracts/.memory-bank/states/.memory-bank/runbooks/
3) Create command stubs
So links from AGENTS.md are not broken, create minimal docs under .memory-bank/commands/. Use ./references/shared-commands-*.md:
mb.mdanalysis.mdbrainstorm.mdbrief.mdconstitution.mdwrite-prd.mdspec-init.mdprd.mdspec-design.mdspec-improve.mdspec-auto.mdclarify-feature.mdprd-to-tasks.mdexecute.mdverify.mdred-verify.mdautopilot.mdautonomous.mdmap-codebase.mddiscuss.mdadd-tests.mdreview.mdfind-skills.md
4) Create native skills (proxy commands)
Create thin proxy skills for each command so they work natively across runtimes:
.claude/skills//SKILL.md→ Claude Code + OpenCode.agents/skills//SKILL.md→ Codex CLI + OpenCode
Each proxy contains: Read and follow the instructions in .memory-bank/commands/.md. This registers commands natively: /mb in Claude Code, $mb in Codex, /mb in OpenCode.
The init-mb.js script creates both sets automatically.
Agents must read .memory-bank/constitution.md early during priming. It records project governing principles and does not replace .memory-bank/invariants.md, .memory-bank/contracts/*, or .memory-bank/spec-index.md; use /constitution only to create or amend those principles.
5) Enforce MBB rules immediately
- Every
.memory-bank/**/*.mdmust have frontmatter (description,status).
Optional fast path
If Node.js is available, you may run the helper script (safe: doesn’t overwrite existing files):
# Option A: copy ./scripts/shared-init-mb.js into your repo then run:
node scripts/init-mb.js
If you don’t want a script, just create the files manually using the templates.
Definition of done
AGENTS.mdexists and points to.memory-bank/index.md.CLAUDE.mdexists and mirrorsAGENTS.md..memory-bank/has the seeded docs..memory-bank/constitution.mdexists as the governing-principles doc and/constitutionis available in.memory-bank/commands/..memory-bank/tasks/index.jsonand.memory-bank/schemas/task.schema.jsonexist; task state is JSON-backed..memory-bank/tasks/index.jsonhas an emptytasksarray in a PRD-less skeleton.- Skeleton bootstrap creates no fake feature docs; task planning starts later with
/write-prd,/spec-init,/prd, mandatory/spec-design,/spec-improve FT-, then/prd-to-tasks FT-. - No
.memory-bank/tasks/TASK-001.task.jsonis created by bootstrap. - Future task records must contain mandatory
tier: T0|T1|T2|T3; routing is only throughtask.tier, not the removedrisk/risk.levelmodel. .memory-bank/commands/has stub command docs..tasks/and.protocols/exist.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: mrvladd-d
- Source: mrvladd-d/memobank
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.