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 skills/apiksdev/axel-core/skill-axel-corenpx skills add apiksdev/axel-core --skill skill-axel-coregit 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 | $0.00029 | $0.02103 |
| Opus 5 | $0.00015 | $0.01052 |
| Sonnet 5 | $0.00006 | $0.00421 |
| Haiku 4.5 | $0.00003 | $0.00210 |
Grade A, and why
skill-axel-core 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.
How it starts
The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AXEL Skill: Core
<document type="skill">
<enforcement>
<![CDATA[
DOCUMENT LOADING ORDER:
- AXEL-Bootstrap.md MUST be loaded FIRST before processing this skill
- Bootstrap provides core AXEL rules and understanding guidelines
- All other documents depend on Bootstrap being in context
PATH RESOLUTION:
- Read the `src`, `ref`, or `target` attribute from the document XML to locate referenced files
- ${CLAUDE_PLUGIN_ROOT} resolves to plugin installation directory
DOCUMENT REFERENCES:
- CLAUDE.md is automatically loaded by Claude Code - DO NOT add to <documents> block
- Use Read tool to access CLAUDE.md content during execution
TRIGGER-BASED DISPATCH:
- Command sends explicit trigger parameter
- Skill matches trigger against workflows registry
- Matching workflow is loaded and executed
DOCUMENT CREATION VALIDATION:
- Creator workflows (create:*) MUST load and apply AXEL-Checklist.md step-by-step
- Location: ${CLAUDE_PLUGIN_ROOT}/references/AXEL-Checklist.md
DOCUMENT RESOLUTION:
- When trigger doesn't match workflows, resolve reference documents
- Analyze prompt keywords against documents:references "ask" attributes
- Load relevant reference documents on-demand
- Use loaded references to answer user request
]]>
</enforcement>
<objective>
Trigger-based workflow dispatcher for AXEL core operations.
Matches incoming trigger to workflow registry and executes.
When no workflow matches, resolves and loads reference documentation
to answer user requests about AXEL concepts and patterns.
</objective>
<documents name="bootstrap" load="always" mode="context">
<read src="${CLAUDE_PLUGIN_ROOT}/AXEL-Bootstrap.md"/>
<understanding>
!! MANDATORY: READ → UNDERSTAND → APPLY !!
Bootstrap provides AXEL core, enforcement rules, and understanding guidelines.
</understanding>
</documents>
<documents name="references" load="on-demand" mode="context">
<read src="${CLAUDE_PLUGIN_ROOT}/skills/skill-axel-core/references/AXEL-Standards.md" ask="standard, pattern, element"/>
<read src="${CLAUDE_PLUGIN_ROOT}/skills/skill-axel-core/references/AXEL-Conventions.md" ask="convention, style, format"/>
<read src="${CLAUDE_PLUGIN_ROOT}/skills/skill-axel-core/references/AXEL-Agent.md" ask="agent, autonomous, executor"/>
<read src="${CLAUDE_PLUGIN_ROOT}/skills/skill-axel-core/references/AXEL-Workflow.md" ask="workflow, process, step"/>
<read src="${CLAUDE_PLUGIN_ROOT}/skills/skill-axel-core/references/AXEL-Skill.md" ask="skill, expertise, capability"/>
<read src="${CLAUDE_PLUGIN_ROOT}/skills/skill-axel-core/references/AXEL-Command.md" ask="command, slash, invoke"/>
<read src="${CLAUDE_PLUGIN_ROOT}/skills/skill-axel-core/references/AXEL-Memory.md" ask="memory, context, persistence"/>
<read src="${CLAUDE_PLUGIN_ROOT}/skills/skill-axel-core/references/AXEL-Claude.md" ask="claude, configuration, project"/>
<read src="${CLAUDE_PLUGIN_ROOT}/skills/skill-axel-core/references/AXEL-Research.md" ask="research, investigation, analysis"/>
<understanding>
!! LOAD ON-DEMAND: Trigger Mismatch Fallback !!
When to Load:
- ONLY when resolved trigger doesn't match workflows:operations registry
- User request doesn't map to any workflow trigger
- User asking about AXEL concepts, patterns, or documentation
How to Load:
- Analyze prompt keywords from user request
- Match keywords against "ask" attributes of each reference document
- Load all matching reference documents into context
- Use loaded references to provide comprehensive answer
Examples:
- "what is an agent?" → load AXEL-Agent.md (ask: agent, autonomous, executor)
- "how to write workflow?" → load AXEL-Workflow.md (ask: workflow, process, step)
- "what are the standards?" → load AXEL-Standards.md (ask: standard, pattern, element)
Available References:
- Standards & Conventions (structural rules)
- All AXEL document types (Agent, Workflow, Skill, Command, Memory, Claude, Research)
</understanding>
</documents>
<role>
Workflow dispatcher that routes trigger-based requests
to appropriate AXEL core operation workflows.
</role>
<capabilities>
- Receive trigger parameter from command
- Match trigger against workflows registry
- Load and execute matching workflow
- Pass parameters to workflow
- Resolve reference documents when workflow not matched
- Answer user requests using loaded reference documentation
</capabilities>
<workflows name="operations" load="on-trigger">
<!-- creators -->
<read src="${CLAUDE_PLUGIN_ROOT}/skills/skill-axel-core/workflows/creators/AXEL-Agent-Creator-Workflow.md" trigger="create:agent"/>
<read src="${CLAUDE_PLUGIN_ROOT}/skills/skill-axel-core/workflows/creators/AXEL-Workflow-Creator-Workflow.md" trigger="create:workflow"/>
<read src="${CLAUDE_PLUGIN_ROOT}/skills/skill-axel-core/workflows/creators/AXEL-Skill-Creator-Workflow.md" trigger="create:skill"/>
<read src="${CLAUDE_PLUGIN_ROOT}/skills/skill-axel-core/workflows/creators/AXEL-Command-Creator-Workflow.md" trigger="create:command"/>
<read src="${CLAUDE_PLUGIN_ROOT}/skills/skill-axel-core/workflows/creators/AXEL-Bootstrap-Creator-Workflow.md" trigger="create:bootstrap"/>
<!-- research -->
<read src="${CLAUDE_PLUGIN_ROOT}/skills/skill-axel-core/workflows/research/AXEL-Research-Workflow.md" trigger="research"/>
<!-- utilities -->
<read src="${CLAUDE_PLUGIN_ROOT}/skills/skill-axel-core/workflows/utilities/AXEL-Fix-Workflow.md" trigger="fix"/>
<read src="${CLAUDE_PLUGIN_ROOT}/skills/skill-axel-core/workflows/utilities/AXEL-Compact-Workflow.md" trigger="compact"/>
<read src="${CLAUDE_PLUGIN_ROOT}/skills/skill-axel-core/workflows/utilities/AXEL-Bypass-Workflow.md" trigger="bypass"/>
<read src="${CLAUDE_PLUGIN_ROOT}/skills/skill-axel-core/workflows/utilities/AXEL-Install-Workflow.md" trigger="install"/>
<understanding>
!! MANDATORY: READ → UNDERSTAND → APPLY !!
Trigger-based workflow registry. Match resolved trigger to execute workflow.
</understanding>
</workflows>
<execution flow="linear"><![CDATA[
WORKFLOW DISPATCH:
Step 1 - Receive Parameters:
- trigger: ${param.trigger} (optional)
- prompt: ${param.prompt} (optional)
- Additional: topic, doc_type, target_path
Step 2 - Resolve Trigger:
- IF trigger provided → use directly
- IF trigger empty → detect from prompt:
Keyword Priority (first match):
1. "create" + "agent" → create:agent
2. "create" + "workflow" → create:workflow
3. "create" + "skill" → create:skill
4. "create" + "command" → create:command
5. "create" + "bootstrap" → create:bootstrap
6. "research" | "investigate" → research
7. "validate" | "fix" → fix
8. "compact" | "archive" → compact
9. "bypass" | "permissions"→ bypass
10. "install" | "init" → install
Step 3 - Match Workflow:
- Check if resolved trigger matches workflows:operations registry
- IF trigger matched → GO TO Step 4 (Execute workflow)
- IF trigger NOT matched → GO TO Step 3.1 (Resolve Documents)
Step 3.1 - Resolve Documents (fallback when no workflow match):
- Analyze prompt keywords
- Match keywords to documents:references "ask" attributes
- Load relevant reference documents from on-demand registry
→ Example: "agent" keyword → load AXEL-Agent.md
→ Example: "workflow" keyword → load AXEL-Workflow.md
→ Example: "standard" keyword → load AXEL-Standards.md
- Use loaded references to answer user request
- SKIP Step 4
Step 4 - Execute Workflow:
- IF trigger starts with "create:":
→ Load ${CLAUDE_PLUGIN_ROOT}/references/AXEL-Checklist.md
→ Execute matched workflow with parameters
→ Validate created document step-by-step against checklist (all phases)
- ELSE:
→ Execute matched workflow with parameters
]]></execution>
<understanding/>
</document>
What ships with it
43 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/AXEL-Agent.md 17 KB
- references/AXEL-Claude.md 16 KB
- references/AXEL-Command.md 15 KB
- references/AXEL-Conventions.md 5.9 KB
- references/AXEL-Memory.md 6.3 KB
- references/AXEL-Research.md 9.4 KB
- references/AXEL-Skill.md 16 KB
- references/AXEL-Standards.md 26 KB
- references/AXEL-Workflow.md 15 KB
- scripts/axel_bypass.py 6.3 KB runs code
- scripts/axel_compact.py 10 KB runs code
- scripts/axel_install.py 8.5 KB runs code
- templates/agents/AXEL-Agent-Template-Bootstrap.md 1.4 KB
- templates/agents/refs/AXEL-Agent-Linear-Tpl.md 2.1 KB
- templates/agents/refs/AXEL-Agent-Staged-Tpl.md 8.3 KB
- templates/claude/AXEL-Bootstrap-Tpl.md 1.6 KB
- templates/claude/AXEL-Claude-Tpl.md 2.6 KB
- templates/commands/AXEL-Command-Template-Bootstrap.md 1.4 KB
- templates/commands/refs/AXEL-Command-Linear-Tpl.md 1.3 KB
- templates/commands/refs/AXEL-Command-Staged-Tpl.md 8.7 KB
- templates/memory/AXEL-Memory-Template-Bootstrap.md 1.3 KB
- templates/memory/refs/AXEL-Memory-Learned-Tpl.md 1.5 KB
- templates/memory/refs/AXEL-Memory-Session-Tpl.md 1.4 KB
- templates/research/AXEL-Research-Template-Bootstrap.md 1.9 KB
- templates/research/refs/AXEL-Research-Architecture-Tpl.md 3.6 KB
- templates/research/refs/AXEL-Research-Best-Practices-Tpl.md 3.7 KB
- templates/research/refs/AXEL-Research-Tech-Stack-Tpl.md 3.0 KB
- templates/skill/AXEL-Skill-Template-Bootstrap.md 1.2 KB
- templates/skill/refs/AXEL-Skill-Linear-Tpl.md 4.5 KB
- templates/skill/refs/AXEL-Skill-Staged-Tpl.md 7.6 KB
- templates/workflows/AXEL-Workflow-Template-Bootstrap.md 1.2 KB
- templates/workflows/refs/AXEL-Workflow-Linear-Tpl.md 1.3 KB
- templates/workflows/refs/AXEL-Workflow-Staged-Tpl.md 7.5 KB
- workflows/creators/AXEL-Agent-Creator-Workflow.md 6.3 KB
- workflows/creators/AXEL-Bootstrap-Creator-Workflow.md 11 KB
- workflows/creators/AXEL-Command-Creator-Workflow.md 7.2 KB
- workflows/creators/AXEL-Skill-Creator-Workflow.md 9.2 KB
- workflows/creators/AXEL-Workflow-Creator-Workflow.md 8.8 KB
- workflows/research/AXEL-Research-Workflow.md 8.4 KB
- workflows/utilities/AXEL-Bypass-Workflow.md 4.6 KB
- workflows/utilities/AXEL-Compact-Workflow.md 3.2 KB
- workflows/utilities/AXEL-Fix-Workflow.md 4.2 KB
- workflows/utilities/AXEL-Install-Workflow.md 3.6 KB
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 · 190 lines · 29 tokens per session scan A 52b2746d3d1c
skill-axel-core is a skill published in the GitHub repository apiksdev/axel-core (7 stars, last pushed 7mo ago), licensed Apache-2.0. It adds 29 tokens to every session and 2,103 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…