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 Utundry/sloplesscode --skill remembergit clone --depth 1 https://github.com/Utundry/sloplesscodeWrote 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/utundry/sloplesscode/remember)<a href="https://agentmods.dev/skills/utundry/sloplesscode/remember"><img src="https://agentmods.dev/badge/skills/utundry/sloplesscode/remember/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/utundry/sloplesscode/remember"><img src="https://agentmods.dev/badge/skills/utundry/sloplesscode/remember.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 | $0.00060 | $0.00611 |
| Opus 5.5 | $0.00024 | $0.00244 |
| Sonnet 5.5 | $0.00012 | $0.00122 |
| Haiku 4.5 | $0.00006 | $0.00061 |
Grade A, and why
remember 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 1mo 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.
What it actually says
Remember — Save to Super Memory
Save the provided information to the local semantic memory store.
Arguments
$ARGUMENTS
Instructions
-
Parse the arguments to extract:
- content: The main text to remember (required — everything before any flags)
- agent: Agent/user ID (flag
--agent <id>, default:"default") - type: Memory type (flag
--type <type>, default:"fact")fact— factual informationpreference— user preferences and habitsexperience— things that happenedtask— tasks and todoscontext— project/session context
- importance: Float 0.0–1.0 (flag
--importance <n>, default:0.7) - tags: Optional comma-separated tags (flag
--tags <t1,t2>)
-
If no flags are provided, treat the entire argument as content and use smart defaults:
- Detect memory type from content: preferences →
preference, tasks/todos →task, etc. - Set importance based on urgency words ("important", "critical", "always") → 0.9+
- Detect memory type from content: preferences →
-
Call
mcp__super-memory__memory_storewith the parsed values. -
Confirm success with the returned memory ID and a short summary.
Examples
/remember User prefers Python over JavaScript
/remember --agent project1 --type preference --importance 0.9 Always use async/await, never callbacks
/remember --type task --importance 0.8 Review PR #42 before Friday
/remember --type context --tags docker,infra The production DB runs on port 5433 not 5432
Output format
After saving, respond with:
Saved to memory: "<first 60 chars of content>"
ID: <uuid>
Type: <type> | Importance: <score>
If the memory server is unreachable, say so clearly and suggest running:
docker compose up qdrant -d and uvicorn app.main:app in D:\work\mnemoforge
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.
- 1mo ago First seen · 58 lines · 60 tokens per session scan A 2d4336066070
remember is a skill published in the GitHub repository Utundry/sloplesscode (1 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 60 tokens to every session and 611 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
dreamd
Works with: Claude Code, Cursor, and Cline have adapter docs in this repo. Any MCP client can call the two tools below.
knowledge-base
Skill "knowledge-base" from Pinvou/pinvou-agent, covering ima knowledge base, operations, routing rules, examples and file upload guard.
notes
Skill "notes" from Pinvou/pinvou-agent, covering ima notes, operations, write rules, examples and response handling.
plur-create-engrams
Create or improve PLUR engrams from conversations, documents, decisions, observations, and explicit preferences. Use for memory extraction, engram authoring, or reviewing proposed memories, including global, scoped, pinned, retrieved, and provisional knowledge. Ordinary use of existing memories does not require this…
plur-memory
Persistent learning for AI agents. Open engram format. Your agent learns from corrections, remembers across sessions, and transfers knowledge across domains.
plur-session-end
Extract durable learnings at the end of a session. Saves corrections, preferences, and codebase patterns as engrams — nothing ephemeral, nothing sensitive.