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/komluk/scaffolding/semantic-memory-storenpx skills add komluk/scaffolding --skill semantic-memory-storegit clone --depth 1 https://github.com/komluk/scaffoldingWrote 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/komluk/scaffolding/semantic-memory-store)<a href="https://agentmods.dev/skills/komluk/scaffolding/semantic-memory-store"><img src="https://agentmods.dev/badge/skills/komluk/scaffolding/semantic-memory-store.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 | $0.00063 | $0.01251 |
| Opus 5 | $0.00032 | $0.00626 |
| Sonnet 5 | $0.00013 | $0.00250 |
| Haiku 4.5 | $0.00006 | $0.00125 |
Grade A, and why
semantic-memory-store 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 5d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Semantic Memory Store
Store knowledge as vector-embedded entries in an optional semantic memory service. When the service is available, entries are automatically embedded and retrievable via cosine similarity search by any agent in future sessions.
This skill is optional. If no semantic memory service is configured, agents should degrade gracefully and rely on the file-based memory described in the agent-memory skill.
When to Use
- Agent discovers a non-obvious insight worth preserving beyond file-based memory
- A debugging session reveals a root cause that would help future agents
- An architectural decision is made that affects multiple components
- A pattern or anti-pattern is confirmed through implementation experience
- Cross-project knowledge that does not belong in a single file
When NOT to Use
- Temporary task context (use conversation memory in
.scaffolding/conversations/) - Information already in CLAUDE.md, docs/, or KNOWLEDGE.md
- Large code snippets (use file-based memory instead)
- Speculative or unverified conclusions
Availability Check
Before attempting to store or search, verify a semantic memory backend is reachable:
- If
mcp__memory__*MCP tools are available, use those (see thesemantic-memory-mcpskill). - If an optional backend service is configured for the project, use its documented interface.
- If neither is available, skip this skill entirely and use file-based memory from the
agent-memoryskill. Do not block on missing infrastructure.
How to Store
When a semantic memory backend is available, store an entry with the following fields. The backend embeds the content and persists it for similarity search.
Parameter Reference
| Parameter | Required | Description |
|---|---|---|
content |
Yes | Text to embed and store (keep concise; long content may be truncated) |
agent_name |
No | Agent that created this memory (e.g. developer, debugger) |
content_type |
No | One of: learning, error, pattern, decision (default: learning) |
tags |
No | List of string tags for filtering |
task_id |
No | Source task ID if applicable |
project_id |
No | Associated project ID |
conversation_id |
No | Associated conversation ID |
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.
- 5d ago First seen · 115 lines · 63 tokens per session scan A abdf644d4c81
semantic-memory-store is a skill published in the GitHub repository komluk/scaffolding (15 stars, last pushed 1mo ago), licensed MIT. It adds 63 tokens to every session and 1,251 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
import
Import a self-contained NeatContext context bundle shared by another person, or reconcile a newer copy of a context already on this machine, leaving the source bundle unchanged. Use only when the user explicitly invokes this skill or asks to import a NeatContext bundle.
save
Save durable decisions, findings, plans, and implementation knowledge from the visible Codex conversation into a new or existing NeatContext context. Use only when the user explicitly invokes this skill or asks to preserve the current conversation as reusable context.
create
Create a fresh NeatContext context from a user-defined behavioral profile and an existing local knowledge folder. Use only when the user explicitly invokes this skill or asks to create a new context rather than save the current conversation.
export
Export a NeatContext context saved from a conversation into a self-contained bundle folder that can be shared or moved to another machine. Use only when the user explicitly invokes this skill or asks to export a NeatContext context.
use
Connect or switch Codex to a local NeatContext Context by name or list number. Use only when the user explicitly invokes this skill, names a context to connect, or agrees to a routing suggestion.
delete
Preview and permanently delete a NeatContext context while preserving any externally linked knowledge folder. Use only when the user explicitly invokes this skill or clearly asks to delete a context.