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 dfirgit 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/dfir)<a href="https://agentmods.dev/skills/purpleailab/decepticon/dfir"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/dfir/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/dfir"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/dfir.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 | $0.00068 | $0.00889 |
| Opus 5 | $0.00034 | $0.00445 |
| Sonnet 5 | $0.00014 | $0.00178 |
| Haiku 4.5 | $0.00007 | $0.00089 |
Grade A, and why
dfir-overview 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Forensicator / DFIR Skill Catalog
Decepticon emits attacks AND detection rules. This catalog feeds the detection rules back through real forensic artifacts to confirm they fire — closing the Offensive Vaccine loop on the operations side.
Playbooks
Inline technique reference — not separately loadable skills. The entries below are summarized here for direct use; there is no separate
SKILL.mdto open for each. Do NOT call the skill loader on them — apply the technique with your tools using this summary and the Workflow in this file.
| Technique | Use for |
|---|---|
| volatility-windows | Volatility 3 Windows plugins: pslist, malfind, cmdline, netscan, dlllist, handles |
| volatility-linux | Volatility 3 Linux: linux.pslist, linux.bash, linux.malfind |
| plaso-timeline | psort + log2timeline; super-timeline construction; Sigma matchers on the timeline |
| sigma-cli-validation | sigma-cli convert + match against captured event logs |
| yara-scan | yara-x scan against memory dumps and disk images |
| event-log-mining | Windows Event Log (.evtx) extraction + key event ID reference |
| etw-trace | ETW provider triage; .etl file extraction |
| edr-validation | Replay an attack against a target with Velociraptor / OSQuery active; capture artifacts |
Loop closure workflow
- Run an offensive technique (e.g.,
dcsyncfrom the ad-operator agent). - Detector agent emits Sigma rule describing the expected detection
pattern (event 4662 with right
ControlAccessRights, etc.). - Defender pushes the Sigma to the customer SIEM via
sigma_to_splunk_savedsearch/sigma_to_sentinel_analyticrule/sigma_to_elastic_detection_rule. - Forensicator validates by:
- Collecting the event log from the DC at attack time.
- Running
sigma-cli convert --target sqliteand matching against the log file. - If the match count is 0 → detection rule has a bug. Iterate with Detector.
- If match count is N → detection works. Record the validation evidence in the engagement knowledge graph.
- Patcher proposes the fix; Forensicator validates the patch doesn't break the detection (verify the rule still fires on attempted exploitation of the patched build).
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 · 76 lines · 68 tokens per session scan A c66c8b0a5459
dfir-overview is a skill published in the GitHub repository PurpleAILAB/Decepticon (5,491 stars, last pushed 13d ago), licensed Apache-2.0. It adds 68 tokens to every session and 889 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 2026-09-03.
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.