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-rungit 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 | $0.00012 | $0.00724 |
| Opus 5 | $0.00006 | $0.00362 |
| Sonnet 5 | $0.00002 | $0.00145 |
| Haiku 4.5 | $0.00001 | $0.00072 |
Grade A, and why
axel:run 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:run
<document type="command" entry="cmd:main">
<enforcement>
<![CDATA[
- Read the `src`, `ref`, or `target` attribute from the document XML to locate referenced files
- ${CLAUDE_PLUGIN_ROOT} resolves to plugin installation directory
SEMANTIC:
- "run" = execute single workflow file
- Fire-and-forget (stateless)
- Workflow-only execution
]]>
</enforcement>
<objective>
Execute a single AXEL workflow file.
Stateless execution for workflow documents.
</objective>
<documents name="core" load="always" mode="context">
<read src="${CLAUDE_PLUGIN_ROOT}/AXEL-Bootstrap.md"/>
<understanding>
!! MANDATORY: READ -> UNDERSTAND -> APPLY !!
Bootstrap provides AXEL syntax and execution rules.
</understanding>
</documents>
<variables>
<var name="args" from="$ARGUMENTS"/>
<var name="plugin_root" value="${CLAUDE_PLUGIN_ROOT}"/>
<var name="file_path" value=""/>
</variables>
<command id="cmd:main">
<goto when="args = 'help'" to="help"/>
<goto when="args = ''" to="help"/>
<goto to="execute"/>
</command>
<execution flow="staged">
<!-- help: Show usage -->
<stage id="help">
<print>
## /axel:run
Execute a single AXEL workflow file.
**Usage:**
/axel:run {workflow.md} - Execute the workflow
**Examples:**
/axel:run .claude/workflows/my-workflow.md
/axel:run .claude/workflows/build-deploy.md
**Note:**
- Workflow-only execution (stateless)
- For todo management, use `/axel:todos` commands
</print>
<stop kind="end"/>
</stage>
<!-- execute: Run the workflow -->
<stage id="execute">
<set var="file_path" value="${args}"/>
<print>## Running workflow: ${file_path}</print>
<invoke name="Task" output="result">
<param name="subagent_type">axel-core:agent-axel-runner:agent-axel-runner</param>
<param name="description">Run: ${file_path}</param>
<param name="prompt"><![CDATA[
PLUGIN_ROOT: ${plugin_root}
axel_file_path: ${file_path}
]]></param>
</invoke>
<goto to="show_result"/>
</stage>
<!-- show_result: Display result -->
<stage id="show_result">
<print>
## Workflow Execution Complete
**Workflow:** ${file_path}
**Status:** ${result.status}
</print>
<stop kind="end"/>
</stage>
</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 · 112 lines · 12 tokens per session scan A cf8eb1c6b276
axel:run is a command published in the GitHub repository apiksdev/axel-core (7 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 12 tokens to every session and 724 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
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.