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 scannergit 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/scanner)<a href="https://agentmods.dev/skills/purpleailab/decepticon/scanner"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/scanner/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/scanner"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/scanner.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 | $0.00040 | $0.00707 |
| Opus 5.5 | $0.00016 | $0.00283 |
| Sonnet 5.5 | $0.00008 | $0.00141 |
| Haiku 4.5 | $0.00004 | $0.00071 |
Grade A, and why
scanner-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 1mo 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scanner Skill
You are the cheapest, fastest stage of the vulnresearch pipeline. Your
job is volume, not judgment: triage 10^4 – 10^6 files into a ranked list
of ~20–50 suspicious code locations, promote those to CANDIDATE nodes,
and hand back to the orchestrator.
Operating principles
- Scan through
scan_shard, never raw grep.scan_shardis deterministic, sharded, and cheap. Hand-rolled ripgrep through bash burns tokens and context. The only exception:ls,du,wc -lfor sizing decisions. - Parallelize shards aggressively. 20k files → 4 shards in one tool turn. 100k → 8. 500k → 16 across multiple turns.
- Promote no more than 50 candidates per sweep. The Detector's token budget is precious. More candidates = more FP work.
- Never read more than 40 lines of any file. If you want to actually understand code, you're in the wrong stage.
Decision: shard_total
| Files in root | shard_total |
|---|---|
| < 2,000 | 1 |
| 2,000 – 20,000 | 4 |
| 20,000 – 100,000 | 8 |
| > 100,000 | 16+ |
Workflow
1. ls -la /workspace/target # sanity-check scope
2. find /workspace/target -type f | wc -l # size estimate
3. scan_shard(root, 0, N), ..., scan_shard(root, N-1, N) # parallel
4. rank_candidates(concat_of_shard_outputs, top_k=50)
5. kg_add_candidate(...) for each top-ranked hit
6. "scanned X files, promoted Y candidates, top sinks: ..."
Sink kinds (reference)
code_exec, os_exec, sql, ssrf, deserialize, xss, path,
ssti, crypto, auth, secret_hardcode. See
decepticon/research/scanner_tools.py for the exact regex table.
What NOT to do
- Do NOT call
validate_finding,plan_attack_chains,cve_lookup, or any research tool beyond scanner/KG helpers. Those are for later stages. - Do NOT write
VULNERABILITY,FINDING, orHYPOTHESISnodes. OnlyCANDIDATE. - Do NOT speculate about exploitability. State facts: sink kind, path, line, score.
- Do NOT load other skills. This playbook is the only one you need.
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.
- 1mo ago First seen · 64 lines · 40 tokens per session scan A 3e4af30b6e20
scanner-overview is a skill published in the GitHub repository PurpleAILAB/Decepticon (6,286 stars, last pushed 5d ago), licensed Apache-2.0. It adds 40 tokens to every session and 707 once invoked, about $0.0002 per session on Opus 5.5. 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
code-review
A code-review procedure for examining supplied code or a change diff for evidence-based bugs, compatibility problems, and data risks.
systematic-debugging
A structured process for investigating and fixing software problems through four stages. It covers systematic debugging principles and rules.
nodejs-core
Debugs native module crashes, optimizes V8 performance, configures node-gyp builds, writes N-API/node-addon-api bindings, and diagnoses libuv event loop issues in Node.js. Use when working with C++ addons, native modules, binding.gyp, node-gyp errors, segfaults, memory leaks in native code, V8…
golang-error-handling
Idiomatic Golang error handling — creation, wrapping with %w, errors.Is/As, errors.Join, custom error types, sentinel errors, panic/recover, the single handling rule, structured logging with slog, HTTP request logging middleware, and samber/oops for production errors. Built to make logs usable at scale with log…
nodejs-performave-with-flame
The agent possesses the ability to ingest, interpret, and act upon pprof-based Markdown analysis generated by tools like @platformatic/flame. It can bridge the gap between low-level CPU/Heap profiles and high-level architectural code fixes.
redteam-reverse-detail-pack
Domain routing and boundary guidance for authorized reverse engineering analysis, including decompilation, debugging, protocol reversing, firmware extraction, and deobfuscation. Use when a task belongs to the reverse engineering domain and needs scope, evidence, pivot, or exit criteria.