memory-refresh

A command-line helper for rebuilding summaries in a file-based memory system. It updates global and project summaries, recent session notes, and their dates and next steps.

In plain words
What is it for?
Use it after several new sessions, decisions, or lessons, or when the agent's startup context needs updating globally, for one project, or for both.
Why use it?
It prevents the short summaries loaded at startup from falling behind the underlying memory records after substantial changes.

Skill for Claude CodeCodex

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/pyros-projects/limitless/memory-refresh
Any agent
npx skills add pyros-projects/limitless --skill memory-refresh
Clone the repo
git clone --depth 1 https://github.com/pyros-projects/limitless

Made for: Claude Code, Codex.

Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 347 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.

ModelPer sessionOnce invoked
Fable 5 $0.00043 $0.00347
Opus 5 $0.00022 $0.00173
Sonnet 5 $0.00009 $0.00069
Haiku 4.5 $0.00004 $0.00035

Measured 2d ago against content hash 76692a57f94f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

memory-refresh 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/codies-memory/skills/memory-refresh/SKILL.md · 48 lines

What it actually says

Memory Refresh

Use this skill when the derived warm-memory artifacts may be stale.

Typical triggers:

  • the user says "refresh memory", "rebuild warm summaries", or "update the boot summaries"
  • several new sessions, decisions, threads, or lessons were added
  • boot feels behind the current vault state

Command

From the plugin repo or a standalone install:

codies-memory refresh --agent <name>

To target only one layer:

codies-memory refresh --agent <name> --scope global
codies-memory refresh --agent <name> --scope project

What It Rebuilds

  • boot/global-summary.md
  • projects/<slug>/boot/project-summary.md
  • projects/<slug>/boot/recent-episodes.md

Format notes:

  • summaries include generation dates
  • project summary lines include record dates where available
  • recent episodes include the session date, title, a short excerpt, and next_step
  • recent episode excerpts are intentionally capped at 400 chars and only the latest 5 sessions are kept

Usage Notes

  • Prefer --scope both or the default after meaningful project work.
  • Use --scope global when only identity or cross-project lessons changed.
  • Use --scope project when only one project's sessions, decisions, or threads changed.
  • If no project vault resolves, --scope project should fail clearly rather than guessing.
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. 2d ago First seen · 48 lines · 43 tokens per session scan A 76692a57f94f

Subscribe to this mod's changes

memory-refresh is a skill published in the GitHub repository pyros-projects/limitless (9 stars, last pushed 20d ago), licensed MIT. It adds 43 tokens to every session and 347 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.

Related

Other skills, from other repositories

using-superpowers

Bootstrap skill — teaches the agent how to find and invoke skills. Use when starting any new task or session.

ArchieIndian/openclaw-superpowers · 26 tokens

omh-jit-learn

This is a Hermes-native jit-learn workflow skill.

rlaope/oh-my-hermes · 78 tokens

story-long-analyze

长篇网文拆文。深度拆解爆款长篇小说的黄金三章、人设架构、爽点设计、节奏控制。 单一深度拆解管道:跑完黄金三章(Stage 1)后产出快速预览报告并询问是否继续全量拆解, 确认后从 Stage 2 续跑逐章摘要、聚合分析、设定关系、汇总报告,全程产物落盘 拆文库/{书名}/。 触发方式:/story-long-analyze、/长篇拆文、「帮我拆这本书」「拆这本书」「分析黄金三章」 「深度拆解」「完整拆解」「系统拆解」或提供小说文本文件路径——全部进入同一管道。.

uu201/character-arc · 175 tokens

beamer-academic

Generate high-quality academic Beamer slides from a thesis/paper (PDF, Word, or LaTeX source). Compatible with Claude Code and Codex. Supports thesis defense, proposal presentations, and conference talks. Built-in layout library with 13 professional page types, 5 color schemes, and interactive editing loop. Use when…

Faust-Donf/beamer-academic · 148 tokens

教程类H5-小红书小工具

用 AI 生图 + SPA 课程架构 + 离线 H5 zip = 在小红书"创作者中心 → 小工具"发布的多课程 H5 互动产品。讲清楚 4 层栈 / 5 步流程 / 7 节课程都适用。触发词:「做教程类 H5」「小红书小工具」「H5 课程」「离线 H5 课程」「多节课 H5」。.

huangrichao2020/pretty-skills · 110 tokens

sansheng-distill

Distill any book/text into a self-contained HTML page with 5-layer structure (overview / per-chapter / book-soul / action-checklist / credibility-grading). Zero external dependencies, embedded mermaid mind-map, thinking-process traceable. Use when user says "拆书", "读书蒸馏", "AI 拆书", "把一本书蒸透", "把 [book] 拆成 5 层", or any…

huangrichao2020/pretty-skills · 108 tokens