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/ngocsangyem/meowkit/memorynpx skills add ngocsangyem/MeowKit --skill memorygit clone --depth 1 https://github.com/ngocsangyem/MeowKitWrote 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/ngocsangyem/meowkit/memory)<a href="https://agentmods.dev/skills/ngocsangyem/meowkit/memory"><img src="https://agentmods.dev/badge/skills/ngocsangyem/meowkit/memory.svg" alt="Measured on agentmods" 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 | $0.00086 | $0.01013 |
| Opus 5 | $0.00043 | $0.00507 |
| Sonnet 5 | $0.00017 | $0.00203 |
| Haiku 4.5 | $0.00009 | $0.00101 |
Grade A, and why
mk: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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory System Toolkit
Reference guides for the memory system: session capture, pattern extraction, and cost tracking.
When to Use
- During Phase 0 (Orient) to load previous session context
- During Phase 6 (Reflect) to capture learnings and patterns
- When the
analystagent tracks costs or extracts patterns
Workflow Integration
Operates in Phase 0 (Orient) and Phase 6 (Reflect). Output supports the analyst agent.
References
| Reference | When to load | Content |
|---|---|---|
| capture-architecture.md | Before any agent-side memory write | The 2-path contract — ##prefix: is user-typed only; agents write via direct Edit |
| session-capture.md | Phase 6 | Capturing session learnings in 3 categories (patterns/decisions/failures) |
| pattern-extraction.md | Phase 6 | Extracting high-frequency patterns for instruction-file promotion |
| cost-tracking.md | Phase 0, 6 | Token usage tracking, cost reporting, budget alerts |
| consolidation.md | Manual | Prune stale entries, merge duplicates, archive cost data (run when memory grows large) |
How session-capture is invoked
session-capture is not a CLI subcommand. At Phase 6 (Reflect) the agent reads references/session-capture.md and follows its 4 steps using Read / Write / Edit directly. There is no mewkit memory session-capture script — content extraction requires LLM analysis that a static CLI cannot produce.
Subcommands
--prune
Prune old standard-severity entries from canonical JSON stores, then regenerate Markdown views.
Stores subject to pruning: fixes.json, review-patterns.json, and
architecture-decisions.json.
What gets pruned:
## headingswith a date(YYYY-MM-DD, severity: standard)older than threshold (default: 90 days)
What ships with it
5 files 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.
- 2d ago First seen · 84 lines · 86 tokens per session scan A d168bb80113b
mk:memory is a skill published in the GitHub repository ngocsangyem/MeowKit (14 stars, last pushed 1mo ago), licensed MIT. It adds 86 tokens to every session and 1,013 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 2026-09-03.
Other skills, from other repositories
cache
Use when the user wants to view, search, add, edit, prune, archive, or clear hyperflow memory entries. CRUD interface for .hyperflow/memory/ — never modifies source code, only memory files. Trigger with /hyperflow:cache, "show memory", "search memory for X", "clear memory", "what does hyperflow remember about Y".
learn-from-fix
Capture Elixir/Ecto/LiveView lessons and Hex API rules. Use after corrections or when asked to document learning, record a lesson, prevent a fixed mistake, or remember package guidance with --library.
assigns-audit
Inspect LiveView socket assigns for memory bloat — missing temporaryassigns, unused assigns, unbounded lists needing streams, memory estimates. Use when LiveView memory grows or you need to add temporaryassigns.
recall
Recall prior work from past sessions — how a bug was fixed, what was decided, where a pattern lives. Use when asked 'have we done this before' or 'how did I fix X' in Elixir/Phoenix work. ccrider MCP when available, else git + solution docs.
compound-docs
Searchable Elixir/Phoenix/Ecto solution documentation system with YAML frontmatter. Builds institutional knowledge from solved problems. Use when consulting past solutions before investigating new issues.
continuous-learning-construction
Automatically extract patterns, best practices, and reusable knowledge from construction automation sessions to improve future performance.