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 kill-chain-analysisgit 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/kill-chain-analysis)<a href="https://agentmods.dev/skills/purpleailab/decepticon/kill-chain-analysis"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/kill-chain-analysis/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/kill-chain-analysis"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/kill-chain-analysis.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 | $0.00027 | $0.01396 |
| Opus 5 | $0.00014 | $0.00698 |
| Sonnet 5 | $0.00005 | $0.00279 |
| Haiku 4.5 | $0.00003 | $0.00140 |
Grade A, and why
kill-chain-analysis 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 7d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- kill-chain-analysis — 91% identical, 3 lines differ
How it starts
The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kill Chain Analysis & Attack Path Decision-Making
Decision Framework
When selecting the next action, evaluate in order:
- What does the OPPLAN say? — Prioritized objectives drive decisions
- What do findings tell us? — Previous phase results constrain options
- What's the risk/reward? — Lower noise approaches first
- What's the OPSEC impact? — Consult
opsecskill before noisy actions
Findings Analysis
After Recon Phase — Selecting Attack Vectors
Read recon/ outputs and categorize:
| Finding Type | Indicates | Next Action |
|---|---|---|
| Web apps with known CVEs | Web exploitation path | exploit → web techniques |
| AD services (88/389/636) | AD attack surface | exploit → AD techniques (after initial access) |
| Exposed credentials (OSINT) | Credential-based access | exploit → credential stuffing/spray |
| Cloud misconfigs (S3/blob) | Cloud attack path | exploit → cloud-specific techniques |
| VPN/remote access services | Network perimeter entry | exploit → VPN/RDP exploitation |
| Employee emails + breach data | Social engineering path | exploit → phishing (if in scope) |
Attack Vector Prioritization
Rank available vectors by:
Score = (Success Probability × Impact) / Detection Risk
1. Valid credentials from OSINT → High prob, High impact, Low noise
2. Known web CVE (public exploit) → High prob, Med impact, Med noise
3. AD misconfiguration (no patch) → Med prob, High impact, Med noise
4. Password spray against O365 → Med prob, High impact, High noise
5. Zero-day or custom exploit → Low prob, High impact, Low noise
Always prefer: credentials > misconfigurations > known CVEs > brute force
After Exploitation — Deciding Post-Exploit Strategy
Once a foothold is established, analyze:
| Context | Decision |
|---|---|
| Low-privilege user on workstation | Prioritize: privesc → cred dump → lateral to server |
| Service account on server | Prioritize: cred dump (may have cached admin creds) → lateral |
| Domain user credentials | Prioritize: AD enumeration → Kerberoasting → DCSync path |
| Local admin on single host | Prioritize: cred dump → check for cached domain creds → lateral |
| Already domain admin | Prioritize: objective completion → evidence collection → reporting |
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.
- 7d ago First seen · 134 lines · 27 tokens per session scan A 10499312a25e
kill-chain-analysis is a skill published in the GitHub repository PurpleAILAB/Decepticon (5,482 stars, last pushed 11d ago), licensed Apache-2.0. It adds 27 tokens to every session and 1,396 once invoked, about $0.0001 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
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.
secretary
Workspace and research management — dispatch analyses, monitor running agents, manage workspaces and threads.
python-lib-analyzer
Analyze any Python library structure, explore modules, classes, and functions with signatures and documentation.
analyzing-windows-prefetch-with-python
Use when parse Windows Prefetch files using the windowsprefetch Python library to reconstruct application execution history, detect renamed or masquerading binaries, and identify suspicious program execution patterns. Use when working with analyzing windows prefetch with python.