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 skills add mehmetdemirci/comb-ai --skill create-memory-bankgit clone --depth 1 https://github.com/mehmetdemirci/comb-aiWrote 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/skills/mehmetdemirci/comb-ai/create-memory-bank)<a href="https://agentmods.dev/skills/mehmetdemirci/comb-ai/create-memory-bank"><img src="https://agentmods.dev/badge/skills/mehmetdemirci/comb-ai/create-memory-bank/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/skills/mehmetdemirci/comb-ai/create-memory-bank"><img src="https://agentmods.dev/badge/skills/mehmetdemirci/comb-ai/create-memory-bank.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 | $0.00045 | $0.01000 |
| Opus 5.5 | $0.00018 | $0.00400 |
| Sonnet 5.5 | $0.00009 | $0.00200 |
| Haiku 4.5 | $0.00005 | $0.00100 |
Grade A, and why
create-memory-bank 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 1mo 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Memory Bank (Greenfield)
Initialize a COMB (Context-Optimized Memory Bank) for the new $0 project.
For existing projects with code: Use
/adopt-memory-bankinstead — it analyzes the codebase and pre-fills memory bank files with real data.
Process
Step 1 — Gather project information
Ask the user for these details before creating files:
- Project name: $0 (from argument)
- Technical domains: What are the main development areas? (e.g., backend, frontend, infrastructure, mobile)
- Tech stack per domain: What technologies are used? (e.g., backend: .NET 8 + PostgreSQL, frontend: React 18 + TypeScript)
- Current phase: What phase is the project in? (kickoff, active development, maintenance)
- Team size: Solo developer or team?
Step 2 — Create directory structure
memory-bank/
├── INDEX.md
├── core/
│ ├── projectbrief.md
│ ├── productContext.md
│ ├── active-context.md
│ └── sprint-tracker.md
├── tech/
│ └── (one file per domain: backend-stack.md, frontend-stack.md, etc.)
└── arch/
├── patterns-overview.md
└── decisions-summary.md
Step 3 — Create project root files
Create these files in the project root:
memory-bank-protocol.md— Copy from the COMB methodology templateproject-rules.md— Create with project-specific rules and the dynamic zoneCLAUDE.md— Create the Claude Code pointer file
If the user uses Cursor, also create:
4. .cursor/rules/memory-bank.mdc — The thin Cursor wrapper
Step 4 — Fill in INDEX.md
The INDEX.md is the most critical file. Fill in:
- Project overview (name, team, version, status)
- Smart reading strategy decision tree (customized to the project's domains)
- Cache-aware reading order (static files listed before dynamic files)
- File map with line counts (initially estimated)
- Key technologies summary
- Architecture highlights
- Performance metrics placeholders
Step 5 — Create core files
core/projectbrief.md— Ask user for project scope, goals, constraintscore/productContext.md— Ask user for product vision, target users, key featurescore/active-context.md— Initialize with current phase and first taskscore/sprint-tracker.md— Initialize with Sprint 1 if applicable
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.
- 1mo ago First seen · 118 lines · 45 tokens per session scan A 5be0f3f71b9d
create-memory-bank is a skill published in the GitHub repository mehmetdemirci/comb-ai (13 stars, last pushed 8mo ago), licensed MIT. It adds 45 tokens to every session and 1,000 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 skills, from other repositories
cao-learning
Report task outcomes and distill lessons so the team improves across runs — reportoutcome after each unit of work, retrospector handoffs at natural boundaries, and applying injected lessons. Use in workflows that run repeatedly over similar work items. Requires memory.learningenabled; degrade silently when the tools…
cao-memory
Store, recall, and forget durable facts with CAO memory — user preferences, project conventions, decisions, and corrections that should persist across sessions and agents. Use proactively to check memory before asking the user, and to save anything worth remembering. Distinct from any provider-native memory.
remember
Save the decisions, facts, dead ends and architecture this conversation established to Atlas's shared memory, so other agents and future sessions can build on them.
lov-auto-context
Manual or hook-triggered context operator. Evaluates the current session for pollution (long conversations, topic drift, stale noise), AND takes concrete context-shaping actions: writing project memory, updating global or project CLAUDE.md (with diff + confirm), and recommending harness commands like /fork, /compact…
lov-ataru-indexing
A maintenance tool for building, repairing, or checking a local searchable index of Ataru AI conversation history. An index is an organised lookup structure that makes searching stored records faster.
lov-search-chat
A local search tool for recalling relevant parts of earlier AI conversations from an indexed memory store. It returns matching sessions and identifiable excerpts from the original conversations.