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 alexeyshishin/as-skill --skill memory-bankgit clone --depth 1 https://github.com/alexeyshishin/as-skillWrote 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/alexeyshishin/as-skill/memory-bank)<a href="https://agentmods.dev/skills/alexeyshishin/as-skill/memory-bank"><img src="https://agentmods.dev/badge/skills/alexeyshishin/as-skill/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/alexeyshishin/as-skill/memory-bank"><img src="https://agentmods.dev/badge/skills/alexeyshishin/as-skill/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 | $0.00053 | $0.01456 |
| Opus 5 | $0.00026 | $0.00728 |
| Sonnet 5 | $0.00011 | $0.00291 |
| Haiku 4.5 | $0.00005 | $0.00146 |
Grade A, and why
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 10d 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 — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory Bank Steward — A Skill for Keeping Project Knowledge Current
This skill describes how to maintain a living project knowledge base, not what to store in it. It activates after each chat message: evaluate whether an important, lasting fact has changed, suggest a concise update if yes, and explicitly say "no update needed" if not.
The Memory Bank is a lightweight, always-current "project encyclopedia." It describes architecture, stack, conventions, key entities, and active tasks — the things a new contributor (human or AI) needs to orient quickly.
Memory Bank structure
.memory-bank/
├── index.md # Table of contents, quick orientation
├── product-overview/ # What the product does, who it serves
├── steerings/ # How to work in this project
│ ├── development-conventions.md # Code style, branching, review norms
│ └── testing-conventions.md # Test strategy, frameworks, coverage goals
├── tech-details/ # Stack, architecture, module interactions
└── tasks/ # Current and planned work (SDD-level)
index.md is the entry point. It links to every other file and gives a
one-paragraph orientation for a newcomer.
Phase 1 — Evaluate
After each chat message, decide whether the conversation produced a fact that belongs in the Memory Bank. Ask two questions:
-
Is it stable project knowledge? Architecture, public APIs, contracts, schemas, conventions, stack details, deployment, CI/CD, core entities, workflows, or current tasks qualify. Temporary fixes, local helpers, and one-off experiments do not.
-
How important is it?
| Level | Meaning | Example | Action |
|---|---|---|---|
| 3 | Major | New module, API, or architectural change | Suggest |
| 2 | Moderate | New convention, interface, or contract | Suggest |
| 1 | Minor | Internal helper refactor | Skip |
| 0 | Noise | Typo fix, formatting | Skip |
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.
- 10d ago First seen · 182 lines · 53 tokens per session scan A a30872ff08e6
memory-bank is a skill published in the GitHub repository alexeyshishin/as-skill (4 stars, last pushed 21d ago), licensed MIT. It adds 53 tokens to every session and 1,456 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
context-manager
Use when a long-running agent task needs context budgeting, checkpointing, compaction, retrieval, or capability-based model routing.
knowledge-ops
Use when an Obsidian knowledge system needs classification, deduplication, retrieval, synchronization, debt queues, or governed Agent/Wiki promotion.
session-learn
Use when a completed work session should yield durable concepts, corrections, decisions, reusable patterns, and a traceable next action.
session-manager
A fallback skill for recording development sessions and restoring project context from an Obsidian vault, a folder of linked notes. It handles explicit resume, handoff, status, and end-of-session requests when automatic capture is unavailable.
cds-stats
Show project memory statistics: session count, observation counts by type, entity count, top entities, and project planning status.
cds-search
Search past session observations using the sessions.search MCP tool. Falls back to CLI if the MCP server is not available.