A private local Markdown notebook that an AI assistant can use as long-term memory across tasks. It stores notes, facts, ideas, meeting records, and other personal context in files.

Use it to save things you want the assistant to remember, search past notes, retrieve earlier context, and manage a personal knowledge store.

It prevents useful context from being lost between separate AI conversations. You can find, update, organize, connect, and recover information instead of repeating it.

yaps-memory — Skill by richawo

Install

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.

agentmods

npx agentmods add skills/richawo/yaps-codex-plugin/yaps-memory

Any agent

npx skills add richawo/yaps-codex-plugin --skill yaps-memory

Clone the repo

git clone --depth 1 https://github.com/richawo/yaps-codex-plugin

Made for: Claude Code, Codex.

Or install yaps-memory, the plugin that ships this one along with the rest of its 1 skill, 1 MCP server.

Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,216 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00081	$0.03216
Opus 5	$0.00041	$0.01608
Sonnet 5	$0.00016	$0.00643
Haiku 4.5	$0.00008	$0.00322

Measured 2d ago against content hash 4916348e136f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

yaps-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.

plugins/yaps-memory/skills/yaps-memory/SKILL.md · 229 lines

How it starts

The opening of the file, as written. The whole thing — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Yaps Memory

Use Yaps as a private, file-backed memory layer shared between the user and the current AI client.

Choose the available transport

Test capabilities instead of guessing the host from its product name or user agent:

Prefer Yaps MCP tools such as vault_search and vault_note_get when they are available. MCP enforces Yaps Agent Access and supplies the most structured interface.
If MCP is unavailable, try the skills-only CLI fallback with vault status. On macOS or Linux, locate yaps-plugin-launcher.sh at <skill-dir>/scripts/yaps-plugin-launcher.sh; for a full local plugin checkout, fall back to <plugin-root>/scripts/yaps-plugin-launcher.sh. This launcher can use Codex Desktop's bundled runtime on a clean computer where node is not installed globally. On Windows, locate the adjacent yaps-plugin-launcher.cmd instead; for a full local plugin checkout, fall back to <plugin-root>/scripts/yaps-plugin-launcher.cmd.
Run the fallback on macOS or Linux as:
```
sh <launcher> --action vault.status --stage reachability -- yaps --pretty vault status
```
In Windows PowerShell, run:
```
& "<launcher.cmd>" --action vault.status --stage reachability -- yaps --pretty vault status
```
The runner honors an explicit override, checks PATH, then finds the CLI packaged inside the installed Yaps app, and validates it with a bounded, read-only status command. Never ask the user to install a CLI, edit PATH, copy a token, or configure MCP.
If either transport succeeds, continue with it for the task. Do not stop merely because MCP is absent; public uploaded plugins may intentionally be skills-only.
If the CLI validates but MCP is unavailable, say that the CLI is working and the private-vault connector is unavailable; continue through the CLI fallback when the task permits it. Never call that state “CLI missing.” If neither transport can reach Yaps, repeat the runner's specific recovery guidance. If the current task cannot reach the local engine, direct the user to a local-capable session on the computer where Yaps is installed: in Claude, that is Claude Code or the Claude desktop app; if the task is ChatGPT web, browser-only, or cloud-hosted, offer ChatGPT desktop and a new local-capable Work or Codex task. Do not claim Yaps is uninstalled merely because it was not found in the known locations. When its recovery code is cli_missing, offer Yaps desktop as the direct install-or-open step; do not describe it as a separate CLI download.

Read the full file on GitHub · 229 lines

Changes

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 · 229 lines · 81 tokens per session scan A 4916348e136f

Subscribe to this mod's changes

yaps-memory is a skill published in the GitHub repository richawo/yaps-codex-plugin (2 stars, last pushed 4d ago), licensed MIT. It adds 81 tokens to every session and 3,216 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 2026-08-31.

Memory and context ai-agents codex local-first notes plugin

note-taker

Capture decisions and facts as durable notes; use when the user makes a decision worth remembering.

jnMetaCode/local-agent-toolkit · 22 tokens

notes

Create detailed study notes from YouTube videos, local media, or local transcripts. Use only when the user explicitly asks to make notes/a конспект through notes, names the notes skill, or runs /notes. Do not use for ordinary summaries, YouTube links, or конспект requests that do not explicitly mention notes.

speech115/notes-skill · 68 tokens

hr-onboarding

A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".

nexu-io/open-design · 62 tokens

html-ppt-taste-brutalist

16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).

nexu-io/open-design · 78 tokens

taiyi-ui-design

TaiyiForge 第 4 阶段 — UI/UX 契约，产出 UI-DESIGN.md。四端通用。.

Dong90/oh-my-taiyiforge · 35 tokens

google-meet

Google Meet via gws: create spaces, fetch join links, list recordings.

Open-Curiosity/gini-agent · 20 tokens