axel:memories

A command for loading AXEL memory files, which are project notes stored under .claude and can include learned or archived information.

In plain words
What is it for?
It is for loading session memories, learned notes, or all available memory, depending on the command arguments.
Why use it?
It helps an AXEL session recover relevant knowledge from earlier work.

Command

Part of the axel-core plugin — 1 skill, 16 commands, 1 agent shipped together

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 commands/apiksdev/axel-core/axel-memories
Clone the repo
git clone --depth 1 https://github.com/apiksdev/axel-core

Or install axel-core, the plugin that ships this one along with the rest of its 1 skill, 16 commands, 1 agent.

Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 836 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 $0.00012 $0.00836
Opus 5 $0.00006 $0.00418
Sonnet 5 $0.00002 $0.00167
Haiku 4.5 $0.00001 $0.00084

Measured 3d ago against content hash 4f69b85ad4d4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

axel:memories 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 3d 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.

commands/axel-memories.md · 113 lines

What it actually says

AXEL Command: /axel:memories

<document type="command" entry="cmd:main">

  <enforcement>
    - Read the `src`, `ref`, or `target` attribute from the document XML to locate referenced files
    - ${CLAUDE_PLUGIN_ROOT} resolves to plugin installation directory
    - Memory files: .claude/MEMORIES.md, .claude/LEARNED.md
    - Archived to: .claude/memories/archived/
  </enforcement>

  <objective>
    Memory management - load memory files.
  </objective>

  <documents name="core" load="always" mode="context">
    <read src="${CLAUDE_PLUGIN_ROOT}/AXEL-Bootstrap.md"/>
    <understanding>
      !! MANDATORY: READ → UNDERSTAND → APPLY !!
      Bootstrap provides core AXEL rules.
    </understanding>
  </documents>

  <variables>
    <var name="action" from="args.0"/>
    <var name="type" from="args.1"/>
    <var name="plugin_root" value="${CLAUDE_PLUGIN_ROOT}"/>
  </variables>

  <command id="cmd:main">
    <goto when="action == ''" to="help"/>
    <goto when="action == 'session'" to="load-session"/>
    <goto when="action == 'learned'" to="load-learned"/>
    <goto when="action == 'all'" to="load-all"/>
    <goto to="help"/>
  </command>

  <execution flow="staged">

    <!-- help: Usage -->
    <stage id="help">
      <print>
        ## /axel:memories

        **Usage:**
          /axel:memories session    - Load session memories
          /axel:memories learned    - Load learned lessons
          /axel:memories all        - Load all
      </print>
      <stop kind="end"/>
    </stage>

    <!-- load-session: Load session memories -->
    <stage id="load-session">
      <read src=".claude/MEMORIES.md" output="content" mode="raw"/>
      <goto when="content == error" to="no-file"/>
      <tasks output="list">
        Parse MEMORIES.md, list memories:
        - [priority] subject
      </tasks>
      <print>${list}</print>
      <stop kind="end"/>
    </stage>

    <!-- load-learned: Load learned lessons -->
    <stage id="load-learned">
      <read src=".claude/LEARNED.md" output="content" mode="raw"/>
      <goto when="content == error" to="no-file"/>
      <tasks output="list">
        Parse LEARNED.md, list lessons:
        - [priority] subject
      </tasks>
      <print>${list}</print>
      <stop kind="end"/>
    </stage>

    <!-- load-all: Load all memories -->
    <stage id="load-all">
      <read src=".claude/MEMORIES.md" output="mem" mode="raw"/>
      <read src=".claude/LEARNED.md" output="learn" mode="raw"/>
      <tasks output="list">
        Parse both files, list all:
        **Session:** ...
        **Learned:** ...
      </tasks>
      <print>${list}</print>
      <stop kind="end"/>
    </stage>

    <!-- no-file: File not found -->
    <stage id="no-file">
      <print>Memory file not found. Run `/axel:axel-install` first.</print>
      <stop kind="end"/>
    </stage>

  </execution>

  <understanding/>

</document>
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. 3d ago First seen · 113 lines · 12 tokens per session scan A 4f69b85ad4d4

Subscribe to this mod's changes

axel:memories is a command published in the GitHub repository apiksdev/axel-core (7 stars, last pushed 7mo ago), licensed Apache-2.0. It adds 12 tokens to every session and 836 once invoked, about $0.0001 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.