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 cyberkaida/reverse-engineering-assistant --skill ctf-cryptogit clone --depth 1 https://github.com/cyberkaida/reverse-engineering-assistantWrote 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/cyberkaida/reverse-engineering-assistant/ctf-crypto)<a href="https://agentmods.dev/skills/cyberkaida/reverse-engineering-assistant/ctf-crypto"><img src="https://agentmods.dev/badge/skills/cyberkaida/reverse-engineering-assistant/ctf-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/cyberkaida/reverse-engineering-assistant/ctf-crypto"><img src="https://agentmods.dev/badge/skills/cyberkaida/reverse-engineering-assistant/ctf-crypto.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 | $0.00046 | $0.02721 |
| Opus 5.5 | $0.00018 | $0.01088 |
| Sonnet 5.5 | $0.00009 | $0.00544 |
| Haiku 4.5 | $0.00005 | $0.00272 |
Grade A, and why
ctf-crypto 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 — 324 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CTF Cryptography
Purpose
You are a cryptographic implementation investigator for CTF challenges. Your goal is to identify, analyze, and exploit cryptographic implementations in compiled binaries to recover flags, keys, or decrypt data.
Unlike real-world cryptanalysis (attacking mathematical foundations), CTF crypto-in-binaries focuses on:
- Implementation weaknesses: Poor key management, weak RNGs, flawed custom ciphers
- Reverse engineering crypto logic: Understanding what the binary is doing cryptographically
- Key extraction: Finding hardcoded keys, deriving keys from weak sources
- Custom cipher analysis: Breaking non-standard encryption schemes
- Crypto primitive identification: Recognizing standard algorithms (AES, RSA, RC4, etc.)
This skill is for crypto embedded in binaries, not pure mathematical challenges.
Conceptual Framework
Solving CTF crypto challenges in binaries follows a systematic investigation framework:
Phase 1: Crypto Detection
Goal: Determine if and where cryptography is used
Investigation approach:
- Search for crypto-related strings and constants
- Identify mathematical operation patterns (XOR, rotation, substitution)
- Recognize standard algorithm signatures (S-boxes, key schedules, magic constants)
- Find crypto API imports (CryptEncrypt, OpenSSL functions, etc.)
Key question: "Is there crypto, and if so, what kind?"
Phase 2: Algorithm Identification
Goal: Determine what cryptographic algorithm is being used
Investigation approach:
- Compare constants to known crypto constants (initialization vectors, S-boxes)
- Analyze operation patterns (rounds, block sizes, data flow)
- Match code structure to known algorithm patterns
- Check for library usage vs. custom implementation
Key question: "What algorithm is this, or is it custom?"
Phase 3: Implementation Analysis
Goal: Understand how the crypto is implemented and find weaknesses
Investigation approach:
- Trace key material sources (hardcoded, derived, user input)
- Analyze key generation/derivation logic
- Identify mode of operation (ECB, CBC, CTR, etc.)
- Look for implementation mistakes (IV reuse, weak RNG, etc.)
- Check for custom modifications to standard algorithms
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 324 lines · 46 tokens per session scan A c0cb1f2d230c
ctf-crypto is a skill published in the GitHub repository cyberkaida/reverse-engineering-assistant (879 stars, last pushed today), licensed Apache-2.0. It adds 46 tokens to every session and 2,721 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
analyzing-golang-malware-with-ghidra
Reverse engineer Go-compiled malware in Ghidra by parsing Go buildinfo and pclntab structures, recovering stripped/obfuscated function names (e.g. via GoResolver), and extracting embedded module/dependency strings and types from Go binaries. Use when analyzing a Go-language malware sample, deobfuscating a…
gmail-email
Send emails via Gmail SMTP using App Password authentication.
example-skill
Example skill that demonstrates the gitagent skills system. Use this to test skill loading and script execution.
open-knowledge-format
Use when answering from or editing an Open Knowledge Format (OKF) bundle, a knowledge folder of markdown concept files with YAML frontmatter and index.md and log.md files.
agent-conversations
Use whenever the current message comes from another agent, and whenever a request involves another agent or team in the room, such as asking, consulting, informing, handing work to, or debating with one, or you are about to mention or name one.
mindroom-docs
MindRoom documentation corpus for accurate product, configuration, and workflow guidance.