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 AEndrix03/Graft --skill memoryzegit clone --depth 1 https://github.com/AEndrix03/GraftWrote 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/aendrix03/graft/memoryze)<a href="https://agentmods.dev/skills/aendrix03/graft/memoryze"><img src="https://agentmods.dev/badge/skills/aendrix03/graft/memoryze/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/aendrix03/graft/memoryze"><img src="https://agentmods.dev/badge/skills/aendrix03/graft/memoryze.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Memory Poisoning · line 4 Skill injects content designed to persist in agent memory or context across interactions. Persistent injection can alter agent behavior long after the initial interaction.Fix: Do not allow untrusted input to persist in agent memory or context. Validate all content before storing and implement memory isolation between sessions.
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 | $0.00122 | $0.01596 |
| Opus 5.5 | $0.00049 | $0.00638 |
| Sonnet 5.5 | $0.00024 | $0.00319 |
| Haiku 4.5 | $0.00012 | $0.00160 |
Grade A, and why
memoryze 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 13d 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
memoryze — Distill and persist conversation knowledge
You are about to commit something the user solved/decided to long-term memory. This skill is the shape of that act: pick the right granularity, write titles that future-you will actually find, and avoid garbage-in.
Argument shape
The user invokes you with a free-form prompt that may include:
| Hint | Example | What it means |
|---|---|---|
| count / granularity | "3 nodi", "atomic", "one big node", "split per business rule" | How many nodes to produce. Default: heuristic (see below). |
| focus | "the WHY, not the diff", "include the workaround", "skip syntax" | What aspect of the solution to emphasize in body. |
| scope | "this conversation", "from the bug fix onwards", "only the SQL part" | Which slice of context to distill. |
| target profile | "in the work profile", "in test" | Switch via GRAFT_PROFILE for the inserts. |
| enrichment | "expand with the official docs link", "add the error message" | Inject extra data the agent should look up before saving. |
Examples:
/memoryze the spring boot @Valid cascade fix, 1 node, focus on WHY/memoryze split this debugging session into atomic nodes per hypothesis tested/memoryze le ultime 10 messaggi su Angular signal reactivity, 3 nodi
If hints are absent, ask at most one clarifying question, then proceed with the default heuristic.
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.
- 13d ago Changed · +3 lines 097392e7152b
- 1mo ago First seen · 132 lines · 122 tokens per session scan A 3c6665fbb368
memoryze is a skill published in the GitHub repository AEndrix03/Graft (34 stars, last pushed 10d ago), licensed Apache-2.0. It adds 122 tokens to every session and 1,596 once invoked, about $0.0005 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
mnemon
Persistent memory CLI for LLM agents. Store facts, recall past knowledge, link related memories, manage lifecycle.
mnemon
Persistent graph-based memory. Recall context before responding, remember insights after. Each group has private memory; global memory is read-only.
mnemon
Persistent memory CLI for LLM agents. Store facts, recall past knowledge, link related memories, manage lifecycle.
mnemon
Persistent memory CLI for LLM agents. Store facts, recall past knowledge, link related memories, manage lifecycle.
mnemon
Persistent memory CLI for Hermes Agent. Store facts, recall past knowledge, link related memories, manage lifecycle.
mnemon
Persistent memory for MiniMax Code. Recall durable context, store important facts and decisions, and link related memories with the mnemon CLI.