Decepticon is an autonomous red-team agent that coordinates AI agents, security tools, sandboxes, and supporting services for authorized cybersecurity assessments. Security researchers and red teams can run it through its Docker stack, cloud service, command-line interface, or Python SDK, with the catalogue entries representing its available skills.
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 PurpleAILAB/Decepticon --skill icsgit clone --depth 1 https://github.com/PurpleAILAB/DecepticonWrote 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/purpleailab/decepticon/ics)<a href="https://agentmods.dev/skills/purpleailab/decepticon/ics"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/ics/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/purpleailab/decepticon/ics"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/ics.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00081 | $0.01054 |
| Opus 5 | $0.00041 | $0.00527 |
| Sonnet 5 | $0.00016 | $0.00211 |
| Haiku 4.5 | $0.00008 | $0.00105 |
Grade A, and why
ics-overview 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ICS / OT Operator Skill Catalog
Industrial engagements are not application security with longer rules of engagement — they are a different discipline. A miswritten Modbus coil on a real plant kills people. This catalog is read-mostly by default; every write-scope skill carries an explicit safety gate.
Hard rules
- No writes without OPPLAN.safety_critical confirmation. The
middleware refuses writes when the active OPPLAN objective does not
carry
safety_critical_confirmed=true. Bypass requires operator signature in/workspace/safety-attestation.txt. - Read-only protocol discovery first. Identify what's on the wire before any active probing. Many ICS protocols are unauthenticated; a single malformed read can crash an old PLC.
- Out-of-band physical safety. The blue team includes plant ops.
A ConOps with
blue_team.plant_ops_phoneis mandatory for engagements on active production lines.
Playbooks
Inline technique reference — not separately loadable skills. The entries below are summarized here for direct use; there is no separate
SKILL.mdto open for each. Do NOT call the skill loader on them — apply the technique with your tools using this summary and the Workflow in this file.
| Technique | Use for |
|---|---|
| modbus-discovery | Read-only Modbus TCP/RTU enumeration, function code 3/4 polling |
| modbus-write | GATED Write coils / registers; safety gate enforced |
| bacnet-discovery | BACnet/IP Who-Is, object enumeration, device profile |
| s7comm | Siemens S7 / S7Comm Plus enumeration via Snap7 / python-snap7 |
| dnp3 | DNP3 outstation / master discovery; integrity poll |
| opcua | OPC-UA browse, anonymous auth check, certificate analysis |
| hmi-web | HMI web stacks (Wonderware, Iconics, Schneider) — known CVEs |
| engineering-software | TIA Portal / Studio 5000 / Unity Pro project extraction |
Workflow
- Passive observation: tap a SPAN port if available. Identify protocols
on the wire (
tshark -Y modbus || tshark -Y bacnet || ...). - Network-layer discovery: nmap with
-sV --script modbus-discover,bacnet-info,s7-info,dnp3-info(NSE scripts ship in Kali by default; some are slow — set-T2for production networks). - Function-code-3 polling: read holding registers from every Modbus
device discovered. Log register maps to the knowledge graph as
:Servicenodes withprotocol=modbus. - Identify the safety integrity level (SIL) of any device touched. SIL 3+ devices NEVER get write probes without plant-ops sign-off.
- Engineering software attack path: if you can reach the engineering workstation, extract the project archive (.s7p, .acd, .stp). The project file is the crown jewel — it reveals the entire process model.
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 · 89 lines · 81 tokens per session scan A a3c0432e114e
ics-overview is a skill published in the GitHub repository PurpleAILAB/Decepticon (5,497 stars, last pushed 13d ago), licensed Apache-2.0. It adds 81 tokens to every session and 1,054 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 2026-09-03.
Other skills, from other repositories
bun-ffi-native-binding
Build high-performance native modules for JavaScript using Bun's FFI (Foreign Function Interface) with Zig or C. Use when optimizing hot paths, integrating system libraries, or requiring native performance for compute-intensive operations.
blucli
BluOS CLI (blu) for discovery, playback, grouping, and volume control of Bluesound and NAD speakers. Use when the user wants to play music, stream audio, control speakers, adjust volume, group or ungroup Bluesound players, search TuneIn radio, or manage multi-room streaming setups.
pylabrobot
Vendor-agnostic lab automation framework. Use when controlling multiple equipment types (Hamilton, Tecan, Opentrons, plate readers, pumps) or needing unified programming across different vendors. Best for complex workflows, multi-vendor setups, simulation. For Opentrons-only protocols with official API…
interactive-dashboard
Interactive web dashboards: stock trackers, sector heatmaps, portfolio monitors — served via preview URL.
onboarding
First-time user onboarding to set up investment profile, watchlists, portfolio, and preferences.
deepep-to-cam-converter
A code migration skill for replacing DeepEP communication operations with CAM operations when moving mixture-of-experts code from CUDA/NCCL to Ascend NPUs.