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/superclaude-org/superclaude_framework/reflectgit clone --depth 1 https://github.com/SuperClaude-Org/SuperClaude_FrameworkWhat 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 | $0.00011 | $0.00732 |
| Opus 5 | $0.00005 | $0.00366 |
| Sonnet 5 | $0.00002 | $0.00146 |
| Haiku 4.5 | $0.00001 | $0.00073 |
Grade A, and why
reflect 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 3d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- reflect — 94% identical, 10 lines differ
How it starts
The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/sc:reflect - Task Reflection and Validation
Triggers
- Task completion requiring validation and quality assessment
- Session progress analysis and reflection on work accomplished
- Cross-session learning and insight capture for project improvement
- Quality gates requiring comprehensive task adherence verification
Usage
/sc:reflect [--type task|session|completion] [--analyze] [--validate]
Behavioral Flow
- Analyze: Examine current task state and session progress using Serena reflection tools
- Validate: Assess task adherence, completion quality, and requirement fulfillment
- Reflect: Apply deep analysis of collected information and session insights
- Document: Update session metadata and capture learning insights
- Optimize: Provide recommendations for process improvement and quality enhancement
Key behaviors:
- Serena MCP integration for comprehensive reflection analysis and task validation
- Bridge between TodoWrite patterns and advanced Serena analysis capabilities
- Session lifecycle integration with cross-session persistence and learning capture
- Performance-critical operations with <200ms core reflection and validation
MCP Integration
- Serena MCP: Mandatory integration for reflection analysis, task validation, and session metadata
- Reflection Tools: think_about_task_adherence, think_about_collected_information, think_about_whether_you_are_done
- Memory Operations: Cross-session persistence with read_memory, write_memory, list_memories
- Performance Critical: <200ms for core reflection operations, <1s for checkpoint creation
Tool Coordination
- TodoRead/TodoWrite: Bridge between traditional task management and advanced reflection analysis
- think_about_task_adherence: Validates current approach against project goals and session objectives
- think_about_collected_information: Analyzes session work and information gathering completeness
- think_about_whether_you_are_done: Evaluates task completion criteria and remaining work identification
- Memory Tools: Session metadata updates and cross-session learning capture
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.
- 3d ago First seen · 89 lines · 11 tokens per session scan A e57db47a5934
reflect is a command published in the GitHub repository SuperClaude-Org/SuperClaude_Framework (23,856 stars, last pushed 12d ago), licensed MIT. It adds 11 tokens to every session and 732 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 2026-08-30.
Other commands, from other repositories
estimate
Provide development estimates for tasks, features, or projects with intelligent analysis.
task
Execute complex tasks with intelligent workflow management and delegation.
spawn
Meta-system task orchestration with intelligent breakdown and delegation.
index
Generate comprehensive project documentation and knowledge base with intelligent organization.
reflect
Task reflection and validation using Serena MCP analysis capabilities.
select-tool
Intelligent MCP tool selection based on complexity scoring and operation analysis.