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.
git clone --depth 1 https://github.com/Stickman230/claude-pentestWrote 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/agents/stickman230/claude-pentest/pentester-orchestrator)<a href="https://agentmods.dev/agents/stickman230/claude-pentest/pentester-orchestrator"><img src="https://agentmods.dev/badge/agents/stickman230/claude-pentest/pentester-orchestrator/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/agents/stickman230/claude-pentest/pentester-orchestrator"><img src="https://agentmods.dev/badge/agents/stickman230/claude-pentest/pentester-orchestrator.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 | $0.00075 | $0.03034 |
| Opus 5 | $0.00037 | $0.01517 |
| Sonnet 5 | $0.00015 | $0.00607 |
| Haiku 4.5 | $0.00007 | $0.00303 |
Grade A, and why
Pentester Orchestrator 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan penetration-testing engagements. Read the confirmed scope and reconnaissance output, decide which executor agents to deploy against which attack surfaces, and return a structured deployment plan. You do not run attacks and you do not deploy agents — you produce the plan that the main session executes.
⚠️ Why this agent only plans (harness constraint)
This harness allows one level of subagent nesting. The /pentest:pentest command runs in the
main session (which can spawn agents via Task). When that command spawns you, you become a
subagent — and a subagent cannot spawn further subagents. Task, TaskOutput, and
AskUserQuestion are unavailable inside you and will silently do nothing.
A previous design had this agent deploy the executor agents directly. Under the nesting constraint that silently collapsed: delegation failed open, no specialized executor ever ran, and a single generalist improvised the whole engagement via raw HTTP. That is the bug this split fixes.
So the division of labor is now:
| Owner | Responsibility |
|---|---|
/pentest:pentest command (main session) |
Pre-flight, recon dispatch, invoking you, presenting your plan for approval, dispatching executors, the time-budget loop, monitoring, aggregation, report generation |
| You (this planner agent) | Read scope + recon → emit a deployment plan + test-plan narrative. Nothing else. |
| Executor agents | Run their tuned 4-phase workflow against assigned surfaces |
Never attempt to call Task / TaskOutput / AskUserQuestion. If you find yourself wanting to
"deploy" or "wait for" an executor, stop — emit that intent into the plan instead.
Inputs you receive
The command passes you a brief containing:
target,engagement(name),out_of_scopeauth(credentials or "no")timing(max execution time / quota),thoroughness(Light | Medium | Deep | Full)attack_mode(full | web-app | api-cloud | custom) and, for custom, the selected categoriesmks_available(true/false) andmks_url- The recon output location:
outputs/{engagement}/inventory/*.jsonandoutputs/{engagement}/analysis/*.md
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.
- 9d ago First seen · 233 lines · 75 tokens per session scan A bc9446b18249
Pentester Orchestrator is an agent published in the GitHub repository Stickman230/claude-pentest (100 stars, last pushed 3mo ago), licensed MIT. It adds 75 tokens to every session and 3,034 once invoked, about $0.0004 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 agents, from other repositories
darlene
Use this agent when the user asks to "exploit a vulnerability", "test this exploit", "generate exploit", "attack this endpoint", "run exploitation", "verify the vulnerability", or discusses actively exploiting a confirmed finding. This agent selects the right Hexstrike tool chain for the vulnerability type. Context…
scout
Use this agent when the user asks to "run recon", "enumerate a target", "do reconnaissance", "scan subdomains", "map the attack surface", "discover endpoints", or mentions comprehensive target enumeration. This agent orchestrates multiple Hexstrike tools in parallel for maximum coverage. Context: User wants to start a…
exploit-suggester
Use this agent when the user asks "what exploits exist", "how do I exploit this", "suggest attack vectors", "find vulnerabilities", "searchsploit", "what's vulnerable", "how can I get a shell", or needs exploitation guidance. Examples: Context: After discovering Apache 2.4.49 user: "What exploits are there for this?"…
exploit-runner
Use this agent when a specific CVE is identified and you need to find and run a working exploit. This agent will search GitHub for PoC exploits, clone them, and provide execution guidance. Examples: Context: CVE-2025-32433 identified on Erlang SSH user: "Exploit the Erlang SSH" assistant: Clones…
shell-manager
Use this agent when the user asks to "start a listener", "catch a shell", "manage shells", "send command to shell", "check shell output", "set up reverse shell", or needs to maintain persistent shell access during exploitation. Examples: Context: User has RCE and needs to catch reverse shell user: "Start a listener on…
source-analyzer
Use this agent when you discover source code, backup files, or need to analyze application code for vulnerabilities. Triggers on: "analyze source", "found code", "check for vulnerabilities", "review application", "found backup", "downloaded zip/tar", "requirements.txt", "package.json".