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/referencesnpx skills add PurpleAILAB/Decepticon --skill referencesgit 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/references)<a href="https://agentmods.dev/skills/purpleailab/decepticon/references"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/references.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 | $0.00054 | $0.01013 |
| Opus 5 | $0.00027 | $0.00507 |
| Sonnet 5 | $0.00011 | $0.00203 |
| Haiku 4.5 | $0.00005 | $0.00101 |
Grade A, and why
references 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 5d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
External References Skill
Decepticon ships with a curated catalogue of high-signal third-party resources. You can either query the metadata directly or fetch the full repo into the sandbox for grep-level access.
Catalogue (13 entries)
| Category | Slug | What's inside |
|---|---|---|
| report-corpus | hackerone-reports | Every public H1 disclosure — calibrate CVSS + reward |
| payload-library | payloads-all-the-things | Canonical payloads for every web vuln class |
| cheat-sheet | book-of-secret-knowledge | Pentester one-liners + recipes |
| reference-agent | pentagi | vxcontrol multi-agent pentest platform |
| reference-agent | pentestgpt | Academic pentest LLM agent |
| reference-agent | shannon | Keygraph autonomous security agent |
| reference-agent | strix | Usestrix autonomous pentest agent |
| reference-agent | hexstrike-ai | 150+ tools exposed via MCP |
| reference-agent | neurosploit | LLM + Metasploit driver |
| tool-index | redteam-tools | Kill-chain-phase tool index |
| cve-poc | trickest-cve | Continuous CVE + PoC corpus |
| cve-poc | penetration-testing-poc | Second-opinion PoC mirror |
| methodology | all-about-bug-bounty | Per-class bug bounty methodology |
When to use each
First engagement iteration
ref_suggest(vuln_class="...", goal="recon")to see which references matter for your current lane. Save the suggestions to the graph.
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.
- 5d ago First seen · 87 lines · 54 tokens per session scan A 125d60eb7281
references is a skill published in the GitHub repository PurpleAILAB/Decepticon (5,445 stars, last pushed 5d ago), licensed Apache-2.0. It adds 54 tokens to every session and 1,013 once invoked, about $0.0003 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 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.