axel:session-save

A command that saves the current work session’s context and decisions in a project memory file. The file helps record what was done and what remains.

In plain words
What is it for?
Use it at the end of a session to record context, changed files, decisions, and unfinished tasks in .claude/MEMORIES.md.
Why use it?
It reduces the need to reconstruct previous work when returning to a project later.

Command

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-session-save
Clone the repo
git clone --depth 1 https://github.com/apiksdev/axel-core
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 711 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 $0.00014 $0.00711
Opus 5 $0.00007 $0.00356
Sonnet 5 $0.00003 $0.00142
Haiku 4.5 $0.00001 $0.00071

Measured 2d ago against content hash 8c58099531c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

axel:session-save 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.

commands/axel-session-save.md · 101 lines

What it actually says

AXEL Command: /axel:session-save

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

  <enforcement>
    <![CDATA[
    - Read the `src`, `ref`, or `target` attribute from the document XML to locate referenced files
    - ${CLAUDE_PLUGIN_ROOT} resolves to plugin installation directory
    - .claude/MEMORIES.md contains type="session" memory entries
    - mode="context" for loading reference files
    - mode="data" for reading existing memories
    - mode="template" for applying output format
    - Append new entries, do not overwrite existing content
    - Notation: {{{xml}}} = ```xml code fence, {{{/xml}}} = ``` close fence
    ]]>
  </enforcement>

  <objective>
    Save current session context and decisions to .claude/MEMORIES.md
    for future reference. Creates structured memory entries with
    timestamp, context, files, and remaining tasks.
  </objective>

  <documents load="always" mode="context">
    <read src="${CLAUDE_PLUGIN_ROOT}/references/AXEL-Core.md"/>
    <read src="${CLAUDE_PLUGIN_ROOT}/skills/skill-axel-core/templates/memory/refs/AXEL-Memory-Session-Tpl.md"/>
    <understanding>
      !! MANDATORY: READ → UNDERSTAND → APPLY !!
      Syntax provides AXEL formatting rules.
      Template provides memory entry structure.
    </understanding>
  </documents>

  <execution flow="linear">
    <![CDATA[
    LINEAR COMMAND (session memory save):

    Step 1 - Read Current State:
    - Read .claude/MEMORIES.md (mode="data") for existing entries
    - Analyze current session conversation

    Step 2 - Analyze Session:
    - Identify completed work and decisions made
    - List related files that were modified or discussed
    - Note remaining tasks to complete

    Step 3 - Create Memory Entry:
    Format as memory XML entry:

    ## {YYYY-MM-DD HH:mm:ss} - {5-10 word summary}

    {{{xml}}}
    <memory type="session" priority="normal" tags="{relevant,tags}">
        <timestamp format="YYYY-MM-DD HH:mm" />
        <subject>{5-10 word summary}</subject>

        <context>
          - {completed work item 1}
          - {completed work item 2}
          - {decision made}
        </context>

        <files>
          - {modified file 1}
          - {discussed file 2}
        </files>

        <remaining>
          - {task left to do}
        </remaining>
    </memory>
    {{{/xml}}}

    ---

    Step 4 - Append to File:
    - Append new entry to .claude/MEMORIES.md
    - Each session entry separated by --- divider
    - IMPORTANT: Append to file, do not overwrite existing entries

    Step 5 - Confirm:
    - Display "Session memory saved to .claude/MEMORIES.md" to user
    ]]>
  </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. 2d ago First seen · 101 lines · 14 tokens per session scan A 8c58099531c3

Subscribe to this mod's changes

axel:session-save is a command published in the GitHub repository apiksdev/axel-core (7 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 14 tokens to every session and 711 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.