菜单
Extracts learnings from execution trajectories at the end of a Mantis loop. Use to parse agent conversations, extract successes, failures, and false assumptions, and append them to learnings.jsonl. Don't use for analyzing source code or writing patches.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Synthesizes raw learnings and codebase analysis into an interlinked Markdown Knowledge Base (KB). Use at the beginning of a loop to build or update architecture.md, entities, and vulnerabilities. Don't use for generating threat models or formulating execution plans.
Calculates the final risk score based on empirical evidence and architectural impact. Use when findings have been fully processed by previous stages and you need to append final risk scores to the finding files. Don't use for discovering new vulnerabilities or writing patches.
Synthesizes trust boundaries, attack surfaces, and attacker profiles into a living threat model. Use as Stage B of the Knowledge Base generation process, reading architecture and entity definitions from the KB. Don't use for analyzing source code or extracting raw learnings from JSONL files.
Analyzes individual security findings to identify and construct complex exploit chains. Use after validation stages to see if multiple low-severity bugs can be combined into a higher impact vulnerability. Don't use for initial codebase auditing or writing patch code.
Consolidates raw security findings to eliminate redundant reports. Use when raw findings have been generated by the researcher and need consolidation before review. Don't use for initial code auditing or patch generation.
Audits production source code files based on the strategy in plan.json. Use when a review plan exists and you need to perform static analysis and deep-dive reviews of targeted files. Don't use for planning, deduplicating, or writing patches.
| name | mantis_reflect |
| description | Extracts learnings from execution trajectories at the end of a Mantis loop. Use to parse agent conversations, extract successes, failures, and false assumptions, and append them to learnings.jsonl. Don't use for analyzing source code or writing patches. |
Execution Trajectory Analyst. Analyzes the sequence of thoughts, tool calls, and observations (the "trajectory" or "conversation") of the other Mantis agents. Extracts valuable insights to prevent future agents from making the same mistakes.
/mantis_reflectlearnings.jsonl.Analyze the execution trajectories of the mantis_researcher, mantis_critic,
and mantis_patch agents from the current round to distill what went right and
what went wrong.
Execute the reflection stage as follows:
Extract Trajectories (Token Optimization):
transcript.jsonl or
conversation.jsonl files natively with read_file, as they can be
massive and blow out your context window.jq/grep to
extract key events: tool error messages, final agent summaries,
instances where an agent "gave up", or messages indicating a trust
boundary assumption was incorrect.Synthesize Insights: Review the extracted events. Look for:
Append to the Inbox (learnings.jsonl): For each distinct insight,
append a structured JSON object to learnings.jsonl in the root workspace
directory.
learnings.jsonl){"type": "trajectory_insight", "action": "add | update | remove", "target_entity": "[e.g., auth_module.py or sandbox_env]", "insight": "The researcher assumed input was unsanitized, but it is actually cleansed by the middleware. Do not attempt XSS on this parameter.", "source_stage": "mantis_researcher"}
Ensure the file is appended to, not overwritten. When complete, notify the user.