export-system-prompt
Export Claude Code's current system prompt to console or file
What this skill does
# Export System Prompt
Export Claude Code's complete system prompt (all instructions, tool definitions, CLAUDE.md content, memory imports, and session context) to the console or a markdown file.
## Arguments
- **No arguments**: Output formatted system prompt directly to console (default)
- **`--output`**: Write to auto-generated path in `.claude/temp/`
- **`--output <path>`**: Write to specified path (`.md` extension added if missing)
## Execution Workflow
### Step 1: Parse Arguments
1. Check if `--output` flag is present in `$ARGUMENTS`
2. If `--output` present, check if a path follows it
3. Determine output mode:
- `console` (no flag)
- `file_auto` (flag without path)
- `file_custom` (flag with path)
### Step 2: Get Current Timestamp
Run: `date -u +"%Y-%m-%dT%H:%M:%SZ"` to get UTC timestamp for metadata.
### Step 3: Capture System Prompt
The "system prompt" includes everything Claude sees as instructions at the start of each turn:
- Base Claude Code system instructions
- Tool definitions and descriptions
- CLAUDE.md file contents (project instructions)
- Memory file imports (@-file references)
- Hook-injected content (`<system-reminder>` tags)
- Session-specific context (gitStatus, environment info)
**Important:** Output the COMPLETE system prompt without truncation. This is the entire context Claude operates under.
### Step 4: Format Output
Format as markdown with metadata header:
```markdown
# System Prompt Export
**Exported:** {UTC timestamp}
**Working Directory:** {cwd from environment}
**Model:** {model name from system context}
---
## Complete System Prompt
{Everything from the system context - tools, instructions, CLAUDE.md, memory, hooks, etc.}
---
*Exported by `/claude-ecosystem:export-system-prompt`*
```
### Step 5: Output Based on Mode
**Console Mode (default):**
Output the formatted markdown directly. The user will see the complete system prompt in the conversation.
**File Mode (--output):**
1. Determine output path:
- If path provided: Use it (append `.md` if missing)
- If no path: Generate `.claude/temp/YYYY-MM-DD_HHmmss-system-prompt-export.md`
2. Write formatted output to file using Write tool
3. Report success: `Saved system prompt to: {path}`
## Output Template
```markdown
# System Prompt Export
**Exported:** {timestamp}
**Working Directory:** {cwd}
**Model:** {model}
---
## Complete System Prompt
### Tool Definitions
{List all available tools with their descriptions}
### System Instructions
{Base Claude Code instructions}
### Project Instructions (CLAUDE.md)
{Contents of CLAUDE.md and imported memory files}
### Session Context
{gitStatus, environment info, hook-injected reminders}
---
*Exported by `/claude-ecosystem:export-system-prompt`*
```
## Verification Protocol
Before reporting completion, verify:
- [ ] Arguments parsed correctly (detected output mode)
- [ ] Timestamp captured
- [ ] Complete system prompt included (not truncated)
- [ ] Output formatted as markdown with metadata
- [ ] If file mode: File written successfully and path reported
- [ ] If console mode: Full output displayed
## Notes
- **Large output warning**: System prompts can be 10K+ tokens. For easier handling, consider using `--output` to save to a file.
- **Security awareness**: The exported prompt contains your repository's CLAUDE.md instructions and configuration. Be mindful when sharing.
- **Debugging use case**: This command is useful for understanding exactly what instructions Claude is operating under, especially when troubleshooting unexpected behavior.
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.