memb-skill

memb-skill is a skill for Codex from hybridlabor-api/bdb-dev-optimized-agent-skills. It costs 36 tokens per session (1,904 once invoked), scanned A, original, Apache-2.0.

A guide to memB, a local-first long-term memory system for storing developer preferences, project structures, and recurring solutions.

In plain words
What is it for?
Use it to query and maintain persistent project knowledge, developer preferences, coding patterns, and safe long-term context.
Why use it?
It helps an agent remember useful context across tasks without storing sensitive credentials or raw environment settings.

Skill for Codex

Written for Codex: reads ~/.codex or $CODEX_HOME. Also seen: reads .claude/ paths; mentions Claude Code; mentions Codex.

Good fit Use it to query and maintain persistent project knowledge, developer preferences, coding patterns, and safe long-term context.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hybridlabor-api/bdb-dev-optimized-agent-skills/memb-skill
Install

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.

Any agent
npx skills add hybridlabor-api/bdb-dev-optimized-agent-skills --skill memb-skill
Clone the repo
git clone --depth 1 https://github.com/hybridlabor-api/bdb-dev-optimized-agent-skills

Made for: Codex.

Wrote 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.

agentmods badge for memb-skill

README.md
[![agentmods](https://agentmods.dev/badge/skills/hybridlabor-api/bdb-dev-optimized-agent-skills/memb-skill.svg)](https://agentmods.dev/skills/hybridlabor-api/bdb-dev-optimized-agent-skills/memb-skill)
Your own site
<a href="https://agentmods.dev/skills/hybridlabor-api/bdb-dev-optimized-agent-skills/memb-skill"><img src="https://agentmods.dev/badge/skills/hybridlabor-api/bdb-dev-optimized-agent-skills/memb-skill.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,904 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00036 $0.01904
Opus 5 $0.00018 $0.00952
Sonnet 5 $0.00007 $0.00381
Haiku 4.5 $0.00004 $0.00190

Measured 4d ago against content hash 9af1cdbb9704, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

memb-skill 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 4d 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.

skills/global_config/memb-skill/SKILL.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

memB: Local Long-Term Memory Skill

This skill allows agents to access and maintain a persistent, offline-first long-term memory bank using the memb-mcp server. It manages user preferences, project structures, and complex developer workarounds.


🔒 Memory Safety & Secret Filtration

[!IMPORTANT] Secret Ingestion Rule: Under no circumstances should raw credentials, passwords, API keys (e.g. GEMINI_API_KEY, POSTGRES_PRISMA_URL), or raw environment configurations be written to memory. Ensure all inputs are scrubbed of high-entropy strings before calling memory tools.


🛠️ Memory Categorization (Dynamic Flower-Like Graph Layout)

memB implements a dynamic, project-agnostic hierarchical layout that structures memories into clusters automatically without hardcoded categories:

  1. "God Mode" / General Knowledge Hub (Center):
    • Mapped using category="godmode" (with project_id=None).
    • Holds universal developer preferences, coding philosophies, global style sheets, and general core commands.
  2. Dynamic Project Leaves (Petals):
    • Mapped using a specific project_id (e.g. project_id="VisualSelect_By_BDB" or project_id="litha-gathering").
    • Isolates facts, custom configurations, and files routing patterns to the specific workspace project, preventing context pollution.
    • System Integration: The agent dynamically resolves the basename of the active workspace directory to scan and bind project memories automatically.

🔌 Using Memory Tools

When working on tasks, query memory at the start of your turn to retrieve relevant developer context, and add critical decisions at the end.

1. Ingestion (add_memory)

Use add_memory to commit a new fact, style preference, or design decision.

  • Args: text (string), user_id (string, default: "bdb_developer"), category (string, default: "godmode"), project_id (string, optional)
  • Usage Guidelines:
    • General Preferences: "Alice prefers to use absolute import paths globally." -> add_memory({ text: "Prefers absolute import paths globally", category: "godmode" })
    • Project Learned Facts: "In project VisualSelect, we must bypass the Firebase Auth login on localhost." -> add_memory({ text: "Bypass Firebase Auth login on localhost", category: "project_node", project_id: "VisualSelect_By_BDB" })

Read the full file on GitHub · 136 lines

Changes

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.

  1. 4d ago First seen · 136 lines · 36 tokens per session scan A 9af1cdbb9704

Subscribe to this mod's changes

memb-skill is a skill published in the GitHub repository hybridlabor-api/bdb-dev-optimized-agent-skills (6 stars, last pushed 3d ago), licensed Apache-2.0. It adds 36 tokens to every session and 1,904 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 2026-09-03.