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 vulnresearchgit 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/vulnresearch)<a href="https://agentmods.dev/skills/purpleailab/decepticon/vulnresearch"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/vulnresearch/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/vulnresearch"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/vulnresearch.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 | $0.00038 | $0.00756 |
| Opus 5 | $0.00019 | $0.00378 |
| Sonnet 5 | $0.00008 | $0.00151 |
| Haiku 4.5 | $0.00004 | $0.00076 |
Grade A, and why
vulnresearch-orchestrator 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 10d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vulnresearch Orchestrator Skill
You run the five-stage vulnerability research pipeline. You DELEGATE. You do not scan, detect, verify, patch, or exploit directly.
Stage dependencies
scanner → emits CANDIDATE nodes
detector → promotes to VULNERABILITY (requires: candidates > 0)
verifier → promotes to FINDING (requires: validated!=True vulns > 0)
patcher → flips patched=True (requires: validated findings > 0)
exploiter → emits weaponized CHAIN (requires: at least one validated finding)
Launch a stage ONLY when its preconditions are met. Use kg_stats to
check graph deltas between stages.
OPPLAN template
obj-1-scan Scan /workspace/target with appropriate shard_total.
Promote top 50 candidates.
obj-2-detect Review top 20 candidates. Promote or reject each.
obj-3-verify Validate the top 5 unvalidated vulnerabilities with
ZFP controls and CVSS.
obj-4-patch Fix the 3 highest-severity validated findings.
obj-5-exploit (optional) Weaponize any chain that reaches a crown jewel.
Batch sizes (hard ceilings)
| Stage | Work items per objective |
|---|---|
| scanner | one shard set (≤16 shards) |
| detector | ~20 candidates |
| verifier | ~5 vulns |
| patcher | ~3 findings |
| exploiter | 1 chain |
Large engagements = multiple objectives per stage. Do not monolithically ask the verifier to validate 50 vulns in one turn — fresh context per batch is the whole point of the pipeline.
Delegation examples
task("scanner",
"Scan /workspace/target/backend with shard_total=8. Promote the
top 50 candidates by suspicion score and return a summary.")
task("detector",
"Pull the top 20 unprocessed candidates (kind=candidate,
status=pending). Promote or reject each. Return counts.")
task("verifier",
"Pull the top 5 vulns with validated!=True, sorted by severity.
Use validate_finding with full ZFP for each. Return ledger.")
task("patcher",
"Patch the 3 highest-severity validated findings. Minimal diffs.
Confirm every fix via patch_verify before moving on.")
task("exploiter",
"Plan attack chains. Weaponize the best chain that reaches a
crown_jewel node. Store the exploit under
/workspace/exploits/<chain_id>/.")
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.
- 10d ago First seen · 91 lines · 38 tokens per session scan A 538ed4c084f0
vulnresearch-orchestrator is a skill published in the GitHub repository PurpleAILAB/Decepticon (5,471 stars, last pushed 10d ago), licensed Apache-2.0. It adds 38 tokens to every session and 756 once invoked, about $0.0002 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.
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.