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.
npx agentmods add commands/apiksdev/axel-core/axel-learned-savegit clone --depth 1 https://github.com/apiksdev/axel-coreWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00015 | $0.00607 |
| Opus 5 | $0.00008 | $0.00303 |
| Sonnet 5 | $0.00003 | $0.00121 |
| Haiku 4.5 | $0.00002 | $0.00061 |
Grade A, and why
axel:learned-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.
What it actually says
AXEL Command: /axel:learned-save
<document type="command" entry="cmd:main">
<enforcement>
<![CDATA[
- Read the `src`, `ref`, or `target` attribute from the document XML to locate referenced files
- ${CLAUDE_PLUGIN_ROOT} resolves to plugin installation directory
- .claude/LEARNED.md contains type="learned" memory entries
- mode="append" for adding new entries without overwriting
- Notation: {{{xml}}} = ```xml code fence, {{{/xml}}} = ``` close fence
]]>
</enforcement>
<objective>
Save learned lesson to LEARNED.md file.
Single-purpose command with linear execution.
</objective>
<documents name="core" load="always" mode="context">
<read src="${CLAUDE_PLUGIN_ROOT}/references/AXEL-Core.md"/>
<understanding>
!! MANDATORY: READ → UNDERSTAND → APPLY !!
Syntax reference provides AXEL DSL rules for memory entry format.
</understanding>
</documents>
<execution flow="linear">
<![CDATA[
Step 1 - Problem Analysis:
- Identify the problem that was solved
- Analyze the root cause of the problem
- Document the solution steps taken
- Extract the key lesson learned
Step 2 - Create Memory Entry:
- Create a new learned memory entry
- Append to .claude/LEARNED.md file
Format:
## {YYYY-MM-DD HH:mm:ss} - {problem title 5-10 words}
{{{xml}}}
<memory type="learned" priority="high" tags="{relevant,tags}">
<timestamp format="YYYY-MM-DD HH:mm" />
<subject>{problem title 5-10 words}</subject>
<context>
- {problem description}
- {root cause}
</context>
<files>
- {related file 1}
- {related file 2}
</files>
<solution>
- {solution step 1}
- {solution step 2}
</solution>
<lesson>
- {key takeaway}
</lesson>
</memory>
{{{/xml}}}
---
Step 3 - Complete:
- Each learned entry separated by --- divider
- IMPORTANT: Append to file, do not overwrite existing entries
- Signal to user: "Learned lesson saved to .claude/LEARNED.md"
]]>
</execution>
<understanding/>
</document>
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.
- 2d ago First seen · 93 lines · 15 tokens per session scan A 43b59b612b1f
axel:learned-save is a command published in the GitHub repository apiksdev/axel-core (7 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 15 tokens to every session and 607 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.
Other commands, from other repositories
mock
A complete simulated interview (4-6 questions in sequence) with holistic feedback on the full arc — not just individual answers.
review
View your learning progress — quiz scores, weak areas, and what to study next.
start-1-7
Start Lesson 1.7 - Project Memory.
edit-textbook-chapter
Edit a textbook-style chapter, following evidence-based writing instructions.
explain
Explain code, concepts, or system behavior with adjustable depth levels.
harness-onboarding
Generate a human-readable onboarding document from HARNESS.md, AGENTS.md, and REFLECTIONLOG.md — a friendly guide for new team members.