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 engagement-startupgit 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/engagement-startup)<a href="https://agentmods.dev/skills/purpleailab/decepticon/engagement-startup"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/engagement-startup/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/engagement-startup"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/engagement-startup.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 | $0.00023 | $0.00621 |
| Opus 5 | $0.00012 | $0.00311 |
| Sonnet 5 | $0.00005 | $0.00124 |
| Haiku 4.5 | $0.00002 | $0.00062 |
Grade A, and why
engagement-startup 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Engagement Startup Procedure
Execute this procedure on every session start, before any other action.
Step 1: Bind the Active Workspace
The launcher normally injects the workspace root. Use that exact root when it is
present in the engagement context; otherwise use /workspace.
Before calling read_file, write_file, edit_file, ls, glob, or grep,
call:
load_opplan(workspace_path="<active workspace root>")
This call has two outcomes:
- Existing
plan/opplan.json: objectives and engagement metadata are loaded. - Missing
plan/opplan.json: the workspace is still bound so planning files can be created. This is the expected new-engagement path, not a fatal error.
Do not probe the filesystem before this call.
Step 2: Inspect Planning State
Read the active workspace's planning documents:
read_file("<active workspace root>/plan/roe.json")
read_file("<active workspace root>/plan/conops.json")
read_file("<active workspace root>/plan/deconfliction.json")
If any document is missing, delegate to Soundwave:
task("soundwave", "Workspace: <active workspace root>. Regenerate the missing planning documents.")
The launcher already selected the engagement. Do not enumerate the shared
/workspace root, invent another workspace directory, or ask the operator to
select the engagement again.
Step 3A: Resume an Existing OPPLAN
When load_opplan loaded objectives:
- Read relevant files under
findings/. - Summarize objectives completed / total, current phase, latest evidence, and the next pending objective.
- Ask: "Continue from where we left off?"
- Resume the execution loop after confirmation.
Step 3B: Build a New OPPLAN
When no OPPLAN exists but the planning documents are present:
- Read CONOPS goals and kill-chain dependencies.
- Create one bounded objective per sub-agent context window with
add_objective. - Present the complete OPPLAN for approval.
- Enter the execution loop after confirmation. OPPLAN mutations persist automatically; there is no separate save tool.
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 · 84 lines · 23 tokens per session scan A 2fa24257177c
engagement-startup is a skill published in the GitHub repository PurpleAILAB/Decepticon (5,491 stars, last pushed 13d ago), licensed Apache-2.0. It adds 23 tokens to every session and 621 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.