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 agentmods add skills/purpleailab/decepticon/opsecnpx skills add PurpleAILAB/Decepticon --skill opsecgit 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/opsec)<a href="https://agentmods.dev/skills/purpleailab/decepticon/opsec"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/opsec.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 5.1 | $0.00030 | $0.02498 |
| Opus 5 | $0.00015 | $0.01249 |
| Sonnet 5 | $0.00006 | $0.00500 |
| Haiku 4.5 | $0.00003 | $0.00250 |
Grade A, and why
opsec 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 6d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
# curl with delay between requests How it starts
The opening of the file, as written. The whole thing — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Operational Security (OPSEC) Knowledge Base
OPSEC ensures the red team engagement remains covert, controlled, and within authorized scope. Poor OPSEC burns the engagement — detected scans alert the blue team, taint findings, and waste client resources. This skill applies across all recon phases.
1. Core OPSEC Principles
The OPSEC Mindset
- Every packet is a signal — assume the target has IDS/IPS, SIEM, and SOC analysts
- Minimize footprint — collect only what you need, no more
- Blend with normal traffic — timing, volume, and patterns should look legitimate
- Know your tools' signatures — every scanner has a fingerprint
- Document everything — if you can't prove it was authorized, it wasn't
Engagement Scope Awareness
Before ANY active operation:
- Written Rules of Engagement (ROE) on file
- Target IP ranges and domains explicitly listed
- Out-of-scope assets clearly identified
- Testing window defined (dates, times)
- Emergency contact for the client (for accidental impact)
- Get-out-of-jail letter accessible
2. Network OPSEC
Scan Rate Limiting
| Target Type | Recommended Rate | Timing Flag |
|---|---|---|
| Production web server | 5-10 req/sec | nmap -T2 |
| Internal network | 50-100 req/sec | nmap -T3 |
| Development/staging | 100+ req/sec | nmap -T4 |
| High-security target | 1-2 req/sec | nmap -T1 |
| WAF-protected | 1-5 req/sec | Custom delays |
Traffic Shaping
# nmap with specific rate limiting
nmap -sS --max-rate 10 --max-retries 1 -p 80,443 <target>
# ffuf with rate limiting
ffuf -u https://<target>/FUZZ -w wordlist.txt -rate 5
# nuclei with rate limiting
nuclei -u https://<target> -rl 5 -c 2
# curl with delay between requests
for url in $(cat urls.txt); do
curl -s -o /dev/null -w "%{http_code} $url\n" "$url"
sleep 2
done
Timing Considerations
- Business hours (9am-5pm target timezone): Higher baseline traffic → scanning blends in
- Weekends/holidays: Lower baseline → scans stand out more
- Maintenance windows: If known, ideal for aggressive scanning
- Burst vs sustained: Short bursts with long pauses are less detectable than sustained scanning
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.
- 6d ago First seen · 240 lines · 30 tokens per session scan A a3f316155e62
opsec is a skill published in the GitHub repository PurpleAILAB/Decepticon (5,450 stars, last pushed 6d ago), licensed Apache-2.0. It adds 30 tokens to every session and 2,498 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
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.
idea-generation
Stock screening and idea generation: quantitative screens, thematic analysis, shortlist.
add-model
Add a new language model to the Giselle codebase. Use when the user wants to add, register, or integrate a new LLM model (OpenAI, Anthropic, Google) into the system.
python-lib-analyzer
Analyze any Python library structure, explore modules, classes, and functions with signatures and documentation.
fx-notes
Fixture skill fx-notes.