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 kostyk348/sint-ua-v2.1 --skill memory-systemgit clone --depth 1 https://github.com/kostyk348/sint-ua-v2.1Wrote 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/kostyk348/sint-ua-v2.1/memory-system)<a href="https://agentmods.dev/skills/kostyk348/sint-ua-v2.1/memory-system"><img src="https://agentmods.dev/badge/skills/kostyk348/sint-ua-v2.1/memory-system/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/kostyk348/sint-ua-v2.1/memory-system"><img src="https://agentmods.dev/badge/skills/kostyk348/sint-ua-v2.1/memory-system.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 | $0.00047 | $0.01669 |
| Opus 5 | $0.00023 | $0.00834 |
| Sonnet 5 | $0.00009 | $0.00334 |
| Haiku 4.5 | $0.00005 | $0.00167 |
Grade A, and why
memory-system 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 9d 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 — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Structured memory system with semantic typing and hash-chain provenance. Replaces STATE.MD with JSON blocks that agents read/write programmatically.
ARCHITECTURE
.opencode/memory/
├── state.json # Current focus, pending decisions (small, fast)
├── chain.jsonl # Global hash-chain: every block append-only
├── blocks/
│ ├── 0001.fact.json # Semantic-typed memory blocks
│ ├── 0002.logic.json
│ └── ...
└── sessions/
├── 2026-07-13.jsonl # Session logs (append-only)
└── ...
MEMORY BLOCKS
Each block is a JSON file. Filename: {id}.{register}.json
{
"id": "0042",
"register": "FACT",
"prev_hash": "a3f2c...",
"hash": "7b1d9...",
"timestamp": "2026-07-14T12:00:00Z",
"project": "DSA",
"content": "DSA 3D attenuation verified: near=0.25 far=0.0025",
"source": "bench run 2026-07-13",
"confidence": 0.95,
"tags": ["3d", "attenuation", "verified"],
"links": ["0038", "0040"]
}
Registers (semantic types)
| Register | Use for | Example |
|---|---|---|
SENSE |
Raw observations, user input, logs | "recvfrom captured 264/324 pages" |
FACT |
Verified claims with sources | "Cipher = stream cipher [source: taint trap]" |
LOGIC |
Inferences from FACT/SENSE | "xRead key needed for full decrypt" |
OPINION |
Subjective assessments | "Option (a) preferred for RE approach" |
ACTION |
Execution plans, next steps | "RE logiovfs xRead next session" |
Hash-chain
Every block references the previous block's hash:
block_N.prev_hash = block_{N-1}.hash
block_N.hash = sha256(id + register + content + prev_hash)
This creates a tamper-evident chain. If any block is modified, all subsequent hashes break.
HOW TO READ
Current state
Read state.json — it has focus, pending decisions, session count.
Find blocks by project
Search blocks/ for files containing "project": "DSA".
Find blocks by register
Search blocks/ for files named *.fact.json etc.
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.
- 9d ago First seen · 214 lines · 47 tokens per session scan A 4cdf52901297
memory-system is a skill published in the GitHub repository kostyk348/sint-ua-v2.1 (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 47 tokens to every session and 1,669 once invoked, about $0.0002 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
engrama-onboard
Build a personalized Engrama memory graph for any user through a conversational interview. Use this skill whenever someone says "set up Engrama", "create my graph", "onboard", "build my profile", "configure Engrama for me", or asks how to start using Engrama. Also use when the user mentions they have a different role…
handoff
Save a session handoff to Engram for future sessions. Captures decisions, todos, blockers, mental model, and next steps as a structured memory. Use when the user wants to preserve session context before ending work.
read-handoffs
Resume a session by loading recent handoffs from Engram. Use at the start of a session or when the user wants to review what was done previously.
memx
Use when an agent needs to recall, save, inspect, or audit memX memories through the bundled MCP tools.
memory-review
Memory hygiene audit -- finds stale facts, contradictions, low-confidence entries, and consolidation candidates in Pensyve memory. Use periodically to maintain memory quality.
session-memory
End-of-session memory capture -- classifies session signals using a tiered taxonomy and stores confirmed items via Pensyve. Use when ending a work session or when the user wants to capture what was learned.