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/blackms/aistack/memorynpx skills add blackms/aistack --skill memorygit clone --depth 1 https://github.com/blackms/aistackWhat 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 | $0.00087 | $0.00570 |
| Opus 5 | $0.00044 | $0.00285 |
| Sonnet 5 | $0.00017 | $0.00114 |
| Haiku 4.5 | $0.00009 | $0.00057 |
Grade A, and why
aistack-memory 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
aistack: Shared agent memory
aistack gives agents a persistent, searchable memory store (SQLite-backed, optionally vector-indexed). This is how specialized agents hand off context without stuffing everything into one prompt, and how knowledge survives across sessions.
When to use
- You established a fact, decision, or artifact that a later agent or session will need.
- The user asks to "remember this", "recall what we decided", or "what's the context on X".
- You are about to re-derive something that was likely already computed earlier — search memory first.
MCP tools (bundled aistack server)
| Tool | Purpose |
|---|---|
memory_store |
Persist a piece of knowledge (content + optional tags/metadata) |
memory_search |
Semantic / keyword search over stored memory |
memory_get |
Fetch a specific memory by id |
memory_list |
List recent memories |
memory_delete |
Remove a memory |
List the exact tool schemas with npx @blackms/aistack mcp tools.
Workflow
Before starting heavy work — recall
Call memory_search with the key terms of the task. If a relevant decision or artifact exists, reuse it instead of redoing the work.
After establishing something durable — store
Call memory_store for:
- Architectural decisions and their rationale ("decided to use X because Y").
- Stable facts about the codebase (entry points, conventions, gotchas).
- Hand-off artifacts between agents (an API contract, a test plan, a research summary).
Write the content so a future agent with no context can act on it: be explicit, include file paths, avoid pronouns referring to the current conversation.
Do NOT store
- Secrets, tokens, credentials.
- Large blobs better kept in files.
- Transient scratch state that will not matter next session.
Tips
- Tag memories consistently (e.g. by component or issue id) so
memory_searchis precise. - When orchestrating (see the
aistack-orchestrateskill), have each agent store its output and the next agent recall it — that is the core handoff mechanism.
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 · 52 lines · 87 tokens per session scan A 7e70f34adb5e
aistack-memory is a skill published in the GitHub repository blackms/aistack (53 stars, last pushed 2mo ago), licensed MIT. It adds 87 tokens to every session and 570 once invoked, about $0.0004 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.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…