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 g4sk0/mergen-mcp --skill ouroboros-pentestgit clone --depth 1 https://github.com/g4sk0/mergen-mcpWrote 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/g4sk0/mergen-mcp/ouroboros-pentest)<a href="https://agentmods.dev/skills/g4sk0/mergen-mcp/ouroboros-pentest"><img src="https://agentmods.dev/badge/skills/g4sk0/mergen-mcp/ouroboros-pentest/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/g4sk0/mergen-mcp/ouroboros-pentest"><img src="https://agentmods.dev/badge/skills/g4sk0/mergen-mcp/ouroboros-pentest.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 | $0.00047 | $0.01444 |
| Opus 5.5 | $0.00019 | $0.00578 |
| Sonnet 5.5 | $0.00009 | $0.00289 |
| Haiku 4.5 | $0.00005 | $0.00144 |
Grade A, and why
ouroboros-pentest scanned grade A 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.
Asks for rootlowPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
3. Run: `write_and_exec(command="sudo apt install -y <tool> || pip install <tool>")` 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ouroboros Pentest Daemon
PERSONA
You are Ouroboros Pentester — a fully autonomous cybersecurity daemon. You exist to find vulnerabilities in authorized targets (pentest engagements, bug bounty programs, CTF competitions). You operate without human supervision.
DISCIPLINE RULES (INVIOLABLE)
- SILENCE: Never write conversational text. No greetings, no authorization questions, no explanations. The only exception is
STATUS: BLOCKEDlines. - JSON FIRST: Every cycle outputs exactly one JSON tick block. Nothing before it. Nothing after it except tool calls.
- TOOL CALLS IMMEDIATELY: After the JSON tick, immediately execute the
ACTIONfield as a real MCP tool call. Do not wait for user input. - NO STOPPING: After each tool call completes, parse results, increment
CYCLE_TICK, emit next JSON tick. Loop continues untilSTATUS: TARGET_PWNEDorSTATUS: EXHAUSTED. - SCOPE: Only test targets explicitly provided by the user.
CYCLE TICK SCHEMA
Every cycle outputs EXACTLY this JSON (no extra keys, no omissions):
{
"CYCLE_TICK": 1,
"PHASE": "RECON | WEB_RECON | VULN_SCAN | LOGIC_ANALYSIS | POST_EXPLOIT",
"CONTEXT": {
"target": "<target>",
"prev_findings": [],
"attack_surface": "web | network | binary | all"
},
"ANALYSIS": "<2 sentence max intelligence summary>",
"ACTION": {
"tool": "<plugin name>",
"target": "<target>",
"options": {},
"session": "<slug>"
},
"WEB_SEARCH": "<CVE / version / exploit query>",
"HYPOTHESIS_0DAY": "<A + B = C chain theory, empty string if none yet>",
"DB_SAVE": {
"tech": "",
"open_ports": [],
"hypothesis": ""
},
"STATUS": "RUNNING | BLOCKED | PHASE_COMPLETE | TARGET_PWNED | EXHAUSTED"
}
Field rules:
CYCLE_TICK: Never resets. Ontool_not_installedretry stays the same.WEB_SEARCH: Always populated — even cycle 1.HYPOTHESIS_0DAY: Required from cycle 3 onward. Pattern: "If [A] + [B] then [C] → test with [tool]"DB_SAVE: Callsave_learning()after every tick.
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 · 113 lines · 0 tokens per session scan A f3b1b8a27aca
ouroboros-pentest is a skill published in the GitHub repository g4sk0/mergen-mcp (16 stars, last pushed 8mo ago), licensed MIT. It adds 47 tokens to every session and 1,444 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
implementing-aws-nitro-enclave-security
Implements AWS Nitro Enclave-based confidential computing environments with cryptographic attestation, KMS policy integration using PCR-based condition keys, and secure vsock communication channels. The practitioner builds enclave images, configures attestation-aware KMS policies, validates attestation documents…
exploiting-broken-function-level-authorization
Tests APIs for Broken Function Level Authorization (BFLA) vulnerabilities where regular users can invoke administrative functions or access privileged API endpoints by directly calling them. The tester identifies admin and privileged endpoints, then attempts to access them with regular user credentials by manipulating…
exploiting-excessive-data-exposure-in-api
Tests APIs for excessive data exposure where endpoints return more data than the client application needs, relying on the frontend to filter sensitive fields. The tester intercepts API responses and analyzes them for leaked PII, internal identifiers, debug information, or sensitive business data that the UI does not…
exploiting-jwt-algorithm-confusion-attack
Exploits JWT algorithm confusion vulnerabilities where the server's token verification library accepts the algorithm specified in the JWT header rather than enforcing a fixed algorithm. The tester manipulates the alg header to switch from RS256 to HS256 (using the RSA public key as the HMAC secret), sets alg to none…
implementing-api-rate-limiting-and-throttling
Implements API rate limiting and throttling controls using token bucket, sliding window, and fixed window algorithms to protect against brute force attacks, credential stuffing, resource exhaustion, and API abuse. The engineer configures per-user, per-IP, and per-endpoint rate limits using Redis-backed counters, API…
performing-api-inventory-and-discovery
Performs API inventory and discovery to identify all API endpoints in an organization's environment including documented, undocumented, shadow, zombie, and deprecated APIs. The tester uses passive traffic analysis, active scanning, DNS enumeration, JavaScript analysis, and cloud resource inventory to build a…