resume

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

resume

GitHub

恢复之前的安全狩猎任务，通过读取大脑记忆、链挂起建议和侦察数据，展示已测/未测端点。基于价值而非时间优先排序，提供智能下一步建议及操作选项。

providers/codex/.agents/skills/resume/SKILL.md H-mmer/pentest-agents

Trigger Scenarios

用户输入 /resume 命令需要继续上次的漏洞挖掘会话

Install

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

More Options

Non-standard path

npx skills add https://github.com/H-mmer/pentest-agents/tree/main/providers/codex/.agents/skills/resume -g -y

Use without installing

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

指定 Agent (Claude Code)

npx skills add H-mmer/pentest-agents --skill resume -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": "resume",
    "description": "Resume a previous hunt. Shows hunt history, untested endpoints, memory-informed suggestions. Usage: \/resume target.com"
}

Resume hunt on: $ARGUMENTS

What This Does

Read brain for target: uv run python3 ../../tools/brain.py brief $ARGUMENTS
Read brain exhausted: uv run python3 ../../tools/brain.py exhausted $ARGUMENTS
Read chain-pending advisory: cat .claude/agent-memory-local/chain-pending.md 2>/dev/null — feeder findings from prior session waiting for chain dispatch. SURFACE THESE FIRST — they have proven dollar value if chained, vs untested surface which is speculative.
Generate / refresh chain plan: uv run python3 ../../tools/chain_plan.py $ARGUMENTS — writes evidence/<target>/CHAIN_PLAN.md with 3-5 candidate next-links per pending feeder finding plus the agent to dispatch for each. Read this BEFORE picking the next vuln class — proven feeders trump speculative untested surface.
Read recon data from recon/ directory
Show what's been tested vs what remains
Suggest next techniques based on brain patterns

Output

RESUME: target.com
═══════════════════

Brain Status:
  Confirmed findings: N
  Exhausted techniques: N
  Effective techniques: N

Untested Surface:
  1. /api/v2/users/{id}/export — not tested
  2. /api/v2/users/{id}/share — not tested
  ...

Suggestions:
  - Tech stack [X] matches pattern where IDOR was found before
  - Sibling endpoints of confirmed finding not yet tested

Actions:
  [h] /hunt target.com — resume hunting
  [s] /surface target.com — re-rank attack surface
  [r] /recon target.com — re-run recon (surface may have changed)
  [m] /monitor check — check for target changes since last session

Top-Tier Resume Logic

Resume by value, not chronology.

Priority order:

chain-pending confirmed feeders with clear next link
validated partials needing one proof artifact
changed assets from /monitor
untested P1 crown-jewel endpoints
high-confidence class hypotheses from prior wins
stale recon refresh

Show what not to redo. If an area is exhausted, include the exact blocker and matrix coverage. A resumed hunt should start with a single best command, not a menu of every possible command.