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 cryptogit 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/crypto)<a href="https://agentmods.dev/skills/purpleailab/decepticon/crypto"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/crypto/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/crypto"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/crypto.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high YARA Match · line 101 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
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 | $0.00030 | $0.01463 |
| Opus 5 | $0.00015 | $0.00732 |
| Sonnet 5 | $0.00006 | $0.00293 |
| Haiku 4.5 | $0.00003 | $0.00146 |
Grade A, and why
crypto-decode scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
r = subprocess.run(cmd, timeout=timeout, capture_output=True, text=True) Copies of this mod
1 near-identical copy found in the catalogue:
- crypto-decode — 98% identical, 4 lines differ
How it starts
The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Crypto / Decode Playbook
When you have unknown ciphertext (CTF flag, leaked DB field, captured token, encoded payload), the right tool depends on the cipher class.
1. Identify FIRST
Unknown text → automated cracker
# Ciphey — original (Python, slowed maintenance)
ciphey -t "$CIPHERTEXT"
# Ares — Rust rewrite (faster, current)
ares -t "$CIPHERTEXT"
A*-search across 16+ decoders (base64, base85, hex, Caesar, ROT-N, Atbash, Vigenere, XOR-known-plaintext, URL encoding, binary, morse, brainfuck, esolang, leetspeak, etc.) + BERT plaintext detector to know when to stop.
Hash → identify type
hashid -m '$2a$12$....' # bcrypt 12 rounds
hashid -m '5f4dcc3b5aa765d61d8327deb882cf99' # MD5
hash-identifier
Specific format checks
# JWT
echo $TOKEN | cut -d. -f1-2 | tr '_-' '/+' | base64 -d 2>/dev/null
# Hex → bytes
echo "$HEX" | xxd -r -p
# Base64 → bytes (handle URL-safe)
echo "$B64" | tr '_-' '/+' | base64 -d 2>/dev/null
# Multi-encoded (unwind layers)
echo "$BLOB" | base64 -d | base64 -d | xxd -r -p
2. Classical cipher quick-checks
| Cipher | Signature |
|---|---|
| Base64 | [A-Za-z0-9+/=]+, len multiple of 4 |
| Base32 | [A-Z2-7=]+ |
| Hex | [0-9a-fA-F]+, even length |
| Caesar/ROT | only A-Z + spaces, freq-attack ready |
| Vigenere | A-Z, multiple-of-key-length repeating bigrams |
| Substitution | A-Z, IC ≈ 0.066 (English) |
| Vernam/OTP | random-looking bytes, no statistical signal |
| XOR fixed-key | bytes w/ printable XOR'd against pattern (file headers leak) |
| Hill | small block size, matrix-based |
3. CyberChef recipe library
CyberChef (gchq.github.io/CyberChef) is the GUI workhorse but recipes can be exported as JSON and chained programmatically:
# Common chains
"From Base64 / Magic / To Hex"
"From Hex / XOR (Brute) / Magic"
"AES Decrypt(KEY) / From Hex / Strings"
CLI version: cyberchef-cli (community port).
4. Hash cracking quick-ref
| Mode | Hash type |
|---|---|
| 0 | MD5 |
| 100 | SHA-1 |
| 1400 | SHA-256 |
| 1700 | SHA-512 |
| 1000 | NTLM |
| 13100 | Kerberos TGS-REP (etype 23) |
| 19700 | Kerberos TGS-REP (etype 18) |
| 18200 | Kerberos AS-REP |
| 16500 | JWT (HS256) |
| 3200 | bcrypt |
| 7400 | sha256crypt $5$ |
| 1800 | sha512crypt $6$ |
| 22000 | WPA-EAPOL+PMKID |
| 7100 | macOS v10.8+ (PBKDF2-SHA512) |
| 8200 | 1Password Cloud Keychain |
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 · 162 lines · 30 tokens per session scan A 4e755e1170f4
crypto-decode is a skill published in the GitHub repository PurpleAILAB/Decepticon (5,491 stars, last pushed 13d ago), licensed Apache-2.0. It adds 30 tokens to every session and 1,463 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). 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.