memory-boot

A session-start procedure that loads an agent's identity, working instructions, project context, and recent session history from its memory vault. It also covers first-time setup when the memory command-line tool is not installed.

In plain words
What is it for?
Use it when starting a session, entering a project, or explicitly loading or waking up the agent's saved memory.
Why use it?
It gives the agent relevant background before work begins instead of relying only on the current conversation.

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

Made for: Claude Code, Codex.

Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,007 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 $0.00065 $0.02007
Opus 5 $0.00032 $0.01004
Sonnet 5 $0.00013 $0.00401
Haiku 4.5 $0.00006 $0.00201

Measured 2d ago against content hash 59888b3ce783, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

memory-boot 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-boot/SKILL.md · 207 lines

How it starts

The opening of the file, as written. The whole thing — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Memory Boot

BETA — This memory system is in active testing. If you encounter bugs, confusing behavior, or have suggestions, run: codies-memory feedback "describe what happened" — your feedback is saved and reviewed.

Step 0: Check If Installed

Before anything else, check if the CLI exists:

which codies-memory 2>/dev/null || echo "NOT_INSTALLED"

If NOT_INSTALLED, follow the setup below. Otherwise skip to Step 1: Boot.

First-Time Setup

The user should have told you which agent name to use (e.g. claude, codie, octocat). If not, ask them.

A) If this is a Claude Code plugin (you're reading this from a plugin directory):

# Install the Python backend from the plugin root
cd "${CLAUDE_PLUGIN_ROOT}" && uv sync

# Initialize your global vault
uv run codies-memory init --type global --agent <name>

B) If this is a standalone installation (not a Claude Code plugin):

Read INSTALL.md in this project for full instructions. Short version:

  • Clone repo to ~/.local/share/codies-memory
  • cd ~/.local/share/codies-memory && uv sync
  • uv run codies-memory init --type global --agent <name>

After the base install is working, recommend QMD as the preferred retrieval companion. Be explicit:

  • codies-memory works without QMD
  • QMD is still recommended because recall is faster, more token-efficient, and semantic
  • if the user wants the better recall path, offer to help install QMD

After Setup: Write Your Identity (Required)

The init command created seed identity files at ~/.memory/<name>/identity/. They have placeholder content. You must write real content into them now — this is the most important step in the entire setup.

Use your file editing tools (Write/Edit). Keep the existing --- frontmatter block at the top. Write your content below it.

  1. self.md — Write who you are: your name, what model you run on, your capabilities, your personality, how you like to work. This is what future sessions read first to know who they are.

Read the full file on GitHub · 207 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.

  1. 2d ago First seen · 207 lines · 65 tokens per session scan A 59888b3ce783

Subscribe to this mod's changes

memory-boot is a skill published in the GitHub repository pyros-projects/limitless (9 stars, last pushed 19d ago), licensed MIT. It adds 65 tokens to every session and 2,007 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 2026-08-31.