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/aitytech/agentkits-memory/memorynpx skills add aitytech/agentkits-memory --skill memorygit clone --depth 1 https://github.com/aitytech/agentkits-memoryWhat 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 | $0.00035 | $0.00547 |
| Opus 5 | $0.00017 | $0.00273 |
| Sonnet 5 | $0.00007 | $0.00109 |
| Haiku 4.5 | $0.00003 | $0.00055 |
Grade A, and why
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.
This is a copy
91% identical to memory-workflow — 14 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AgentKits Memory Skill
When to Activate
Use this skill when:
- User asks about past work, previous sessions, or what was done before
- User references a decision, pattern, or error you don't have context for
- You need project history, conventions, or architectural decisions
- User asks "what did we do about X?" or "how did we handle Y?"
- You're missing context that should exist from earlier sessions
- Starting work on a feature that may have prior decisions recorded
Prerequisites
Before searching, check if memories exist:
memory_status()
If the database is empty, skip recall and inform the user.
3-Layer Search Workflow
Layer 1: Search Index (lightweight, ~50 tokens/result)
memory_search(query="your search term")
- Returns IDs, titles, categories, dates, and relevance scores
- Filter by category:
decision,pattern,error,context,observation - Filter by date:
dateStart="2025-01-01",dateEnd="2025-12-31" - Sort:
orderBy="relevance"(default),"date_asc","date_desc"
Layer 2: Timeline Context (understand what happened around a result)
memory_timeline(anchor="MEMORY_ID")
- Shows what happened before/after a specific memory
- Helps understand the sequence of events
- Use when you need temporal context
Layer 3: Full Details (only for filtered IDs)
memory_details(ids=["ID1", "ID2"])
- Returns complete content for selected memories
- Limit to 3-5 IDs at a time to conserve tokens
- NEVER fetch details without filtering through Layer 1 first
Quick Topic Recall
For a fast overview of everything known about a topic:
memory_recall(topic="authentication")
This returns a grouped summary. Follow up with memory_details for specifics.
Token Efficiency Rules
- ALWAYS start with
memory_search(Layer 1), never jump tomemory_details - Review search results and select only relevant IDs before fetching details
- Use filters (category, date range) to narrow results
- Limit
memory_detailsto 3-5 IDs per call - This workflow saves ~87% tokens vs fetching everything at once
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 · 68 lines · 35 tokens per session scan A 75d990ecb35b
memory is a skill published in the GitHub repository aitytech/agentkits-memory (64 stars, last pushed 6mo ago), licensed MIT. It adds 35 tokens to every session and 547 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 91% identical to memory-workflow, differing in 14 lines, and is treated as a copy.
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…