remember

Agent Skills › H-mmer/pentest-agents › remember

remember

GitHub

将安全测试中的发现或模式持久化存储至大脑记忆，支持自动填充上下文、用户确认及结构化记录。用于跨目标学习、状态追踪和避免重复工作，提升后续Agent的recall能力。

.claude/skills/remember/SKILL.md H-mmer/pentest-agents

Trigger Scenarios

用户输入/remember命令需要记录漏洞发现或测试结果时

Install

npx skills add H-mmer/pentest-agents --skill remember -g -y

More Options

Non-standard path

npx skills add https://github.com/H-mmer/pentest-agents/tree/main/.claude/skills/remember -g -y

Use without installing

npx skills use H-mmer/pentest-agents@remember

指定 Agent (Claude Code)

npx skills add H-mmer/pentest-agents --skill remember -a claude-code -g -y

安装 repo 全部 skill

npx skills add H-mmer/pentest-agents --all -g -y

预览 repo 内 skill

npx skills add H-mmer/pentest-agents --list

SKILL.md

Frontmatter

{
    "name": "remember",
    "description": "Log a finding or pattern to persistent brain memory. Auto-fills from session context. Usage: \/remember",
    "disable-model-invocation": false
}

Save current finding/pattern to brain memory.

Flow

Read current session context — what target, endpoint, vuln class
Ask user to confirm or edit:
- Target: (auto-detected)
- Endpoint: (from session)
- Vuln class: (from session)
- Result: confirmed / rejected / partial
- Severity: critical / high / medium / low
- Bounty: $___
- Notes: ___
Write to brain:
- If confirmed: uv run python3 $CLAUDE_PROJECT_DIR/tools/brain.py record <target> confirmed "<description>" "<details>"
- If rejected: uv run python3 $CLAUDE_PROJECT_DIR/tools/brain.py record <target> exhausted "<what failed>" "<why>"
Sync to global brain: uv run python3 $CLAUDE_PROJECT_DIR/tools/global_brain.py learn technique "<pattern>"
Track response if submitted: uv run python3 $CLAUDE_PROJECT_DIR/tools/response_tracker.py log <id> <status>

Why This Matters

/resume shows which endpoints you've tested and which remain
Cross-target learning: patterns from target A inform hunting on target B
Global brain accumulates technique knowledge across all engagements

Top-Tier Recall Standard

Before writing memory, make it useful to a future agent that has no conversation context.

Use this shape:

target:
surface:
vuln_class:
primitive:
accounts_or_roles:
evidence_path:
request_summary:
response_marker:
impact:
status:
next_action:

If the item is rejected, preserve the blocker with the same care as a finding. High-quality negative memory prevents duplicate work and false confidence.