pace-memory

pace-memory is a skill for Claude Code from jagbanana/PACE. It costs 240 tokens per session (4,907 once invoked), scanned A, original, MIT.

A local Markdown-based memory system for keeping user facts, decisions, preferences, people, and project context across AI sessions.

In plain words
What is it for?
It is for setting up a persistent project memory vault and storing context that can be reused over time.
Why use it?
It addresses the problem of an AI assistant forgetting useful context when a new session begins.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: reads .claude/ paths; mentions .claude-plugin; mentions CLAUDE.md.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the pace-memory plugin — 1 skill, 1 command, 1 MCP server shipped together

Good fit It is for setting up a persistent project memory vault and storing context that can be reused over time.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add jagbanana/PACE
Claude Code
/plugin install pace-memory

Made for: Claude Code.

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

Wrote 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.

agentmods badge for pace-memory

README.md
[![agentmods](https://agentmods.dev/badge/skills/jagbanana/pace/pace-memory/github.svg)](https://agentmods.dev/skills/jagbanana/pace/pace-memory)
Your own site
<a href="https://agentmods.dev/skills/jagbanana/pace/pace-memory"><img src="https://agentmods.dev/badge/skills/jagbanana/pace/pace-memory/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.

agentmods 80×15 button for pace-memory

Your own site · 80×15
<a href="https://agentmods.dev/skills/jagbanana/pace/pace-memory"><img src="https://agentmods.dev/badge/skills/jagbanana/pace/pace-memory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 240 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,907 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00240 $0.04907
Opus 5.5 $0.00096 $0.01963
Sonnet 5.5 $0.00048 $0.00981
Haiku 4.5 $0.00024 $0.00491

Measured 2mo ago against content hash c177e3f69abb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pace-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 2mo 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.

plugin/skills/pace-memory/SKILL.md · 439 lines

How it starts

The opening of the file, as written. The whole thing — 439 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PACE — Persistent AI Context Engine

PACE is a local Markdown memory system that gives you persistence across sessions. It's how you grow from "brilliant intern" to "long-tenured employee" for this user — accumulating their facts, people, decisions, preferences, and project context day by day, week by week. Full design in the user's PACE PRD.md if they have it.

First-vault bootstrap (when MCP isn't loaded yet)

If the user asks to set up, initialize, install, or onboard PACE in this folder — and the pace_* MCP tools aren't available (no pace_status, pace_init, etc. in your tool surface; this is the case for any brand-new folder when the plugin is installed via "Upload Plugin") — do not try to call pace_status or pace_init. They'll fail. Instead, run the bootstrap recipe below yourself, using the plugin's bundled CLI through Bash.

(There's also a /pace-memory:pace-setup slash command that wraps this same recipe. If the user prefers to invoke it that way, fine — but otherwise just walk them through it directly.)

Step 1 — Greet and collect identity

Open with this script (adapt lightly):

Hi — I'm Claude. Before I scaffold this folder as a PACE vault, three quick questions:

  1. What should I call you?
  2. What name and emoji should I use for myself in this vault? Pick a nickname plus emoji, or say "you pick" and I'll choose one that fits the work, or "just Claude is fine" to skip the personality.
  3. What's the rough nature of the work we'll be doing here?

Wait for the user's answers before doing anything else.

  • If they defer on the emoji ("you pick"), choose one that fits the work: 🧠 memory/research, 📊 analytics, 🚀 launches, 🎨 design, 📝 writing. Tell them which one you chose so they can object.
  • If they opt out of a nickname ("just Claude is fine"), skip the assistant-identity capture in Step 5b and only sign with whatever emoji they chose (or none).

Step 2 — Find the plugin install path

${CLAUDE_PLUGIN_ROOT} is not automatically set in your Bash environment — it's only substituted in .mcp.json files at MCP launch time. Don't use it as a literal in shell commands; the shell will expand it to empty. Instead, find the plugin install yourself:

Read the full file on GitHub · 439 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

  1. 2mo ago First seen · 439 lines · 240 tokens per session scan A c177e3f69abb

Subscribe to this mod's changes

pace-memory is a skill published in the GitHub repository jagbanana/PACE (19 stars, last pushed 3mo ago), licensed MIT. It adds 240 tokens to every session and 4,907 once invoked, about $0.0010 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.

Related

pace-memory compared with skills from other repositories

pace-memory next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
pace-memoryjagbanana/PACESkill193mo agoMITA240Claude Code
knowledge-ingestopenclaw/openclawSkill394kyesterdayMITA80Claude Code, Codex
mem0-oss-to-platformmem0ai/mem0Skill68k2d agoApache-2.0A217Claude Code, Codex
forgetasgeirtj/system_prompts_leaksSkill71k2d agoCC0-1.0A74Claude Code, Codex
Cortexdanielmiessler/LifeOSSkill20kyesterdayMITA184Claude Code
memoryopensquilla/opensquillaSkill7.1k6d agoApache-2.0A44Claude Code, Codex
ha-data-storesshiwenwen/hope-agentSkill1.9kyesterdayMITA115Claude Code, Codex