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 skills add thapr0digy/skills --skill pentest-cleanupgit clone --depth 1 https://github.com/thapr0digy/skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/thapr0digy/skills/pentest-cleanup)<a href="https://agentmods.dev/skills/thapr0digy/skills/pentest-cleanup"><img src="https://agentmods.dev/badge/skills/thapr0digy/skills/pentest-cleanup/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/thapr0digy/skills/pentest-cleanup"><img src="https://agentmods.dev/badge/skills/thapr0digy/skills/pentest-cleanup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00038 | $0.02735 |
| Opus 5.5 | $0.00015 | $0.01094 |
| Sonnet 5.5 | $0.00008 | $0.00547 |
| Haiku 4.5 | $0.00004 | $0.00274 |
Grade B, and why
pentest-cleanup scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reaches for credential filesmediumPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
| SSH authorized_keys entry | `sed -i '/<key fingerprint>/d' ~/.ssh/authorized_keys` | `cat ~/.ssh/authorized_keys` | Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/pentest-cleanup — Engagement Cleanup
Generate a cleanup checklist for engagement end. Parse activity log to identify every artifact deployed on target systems — tools uploaded, persistence mechanisms, accounts created, tunnels, web shells. Produce checklist with removal + verification commands. You do NOT execute any removal commands.
Step 1: Resolve Active Engagement
Use the Bash tool to read the active engagement pointer and extract required fields:
# --- Engagement Resolver ---
ENGAGEMENT_JSON=$(cat ~/.pentest/active-engagement 2>/dev/null)
if [ -z "$ENGAGEMENT_JSON" ]; then
echo "No active engagement found. Run /pentest-init or /pentest-switch." >&2
exit 1
fi
if [ ! -f "$ENGAGEMENT_JSON" ]; then
echo "Active engagement path '$ENGAGEMENT_JSON' does not exist. Run /pentest-switch." >&2
exit 1
fi
ENGAGEMENT_ID=$(jq -r '.engagement_id' "$ENGAGEMENT_JSON")
OUTPUT_DIR=$(jq -r '.output_dir' "$ENGAGEMENT_JSON")
TESTER=$(whoami)
TESTER_MATCH=$(jq -r --arg h "$TESTER" '.testers[] | select(.handle == $h) | .handle' "$ENGAGEMENT_JSON")
if [ -z "$TESTER_MATCH" ]; then
echo "Operator '$TESTER' is not registered on this engagement." >&2
exit 1
fi
# --- End Engagement Resolver ---
After this block, $ENGAGEMENT_ID, $OUTPUT_DIR, and $TESTER are guaranteed to be set and valid.
Step 2: Parse Activity Log for Artifacts
Use the Bash tool to extract all completed exploit and post-exploit entries from the activity log:
jq -r 'select(.action == "post_exploit" or .action == "exploit") | select(.status == "completed") | [.ts, .tester, .action, .target, .tool, .command] | @csv' "${OUTPUT_DIR}/activity.log"
Also read the loot directory index if present — some tool deployments are only traceable from loot entries (e.g., an LSASS dump implies procdump was uploaded):
ls -1 "${OUTPUT_DIR}/loot/" 2>/dev/null
For each log entry returned, classify the artifact using the following signal table:
| Activity Log Signal | Artifact Type |
|---|---|
action == "exploit" and tool contains shell or webshell |
Web shell |
action == "post_exploit" and tool contains chisel, ligolo, socat, or ssh |
Tunnel/proxy |
action == "post_exploit" and details or command mentions persistence, cron, schtask, service, or registry |
Persistence |
action == "post_exploit" and details or command mentions upload, transfer, or push |
Tool uploaded |
action == "exploit" and details or command mentions account, user, or addcomputer |
Account created |
action == "post_exploit" and details or command mentions firewall, iptables, or netsh |
Firewall change |
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.
- 2mo ago First seen · 259 lines · 38 tokens per session scan B d43008f020b8
pentest-cleanup is a skill published in the GitHub repository thapr0digy/skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 38 tokens to every session and 2,735 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 1 finding (reaches for credential files). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
pentest-cleanup compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| pentest-cleanupthapr0digy/skills | Skill | 2 | 2mo ago | MIT | B | 38 | Claude Code |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | today | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | today | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 314k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |