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 agentmods add skills/transilienceai/communitytools/cryptographynpx skills add transilienceai/communitytools --skill cryptographygit clone --depth 1 https://github.com/transilienceai/communitytoolsWrote 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/transilienceai/communitytools/cryptography)<a href="https://agentmods.dev/skills/transilienceai/communitytools/cryptography"><img src="https://agentmods.dev/badge/skills/transilienceai/communitytools/cryptography.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00027 | $0.00417 |
| Opus 5 | $0.00014 | $0.00209 |
| Sonnet 5 | $0.00005 | $0.00083 |
| Haiku 4.5 | $0.00003 | $0.00042 |
Grade A, and why
cryptography 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 4d 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.
What it actually says
Cryptography
Scope
Practical cryptanalysis for CTF and pentest engagements: identifying when a cryptographic primitive's structure (custom hash, partial leaks, related primes, bad RNG, weak modes) admits a faster-than-brute-force solver, then implementing that solver in pure Python where possible. Covers RSA-style algebraic factoring, lattice/AGCD recovery, GF(2) linear collapse of "complicated-looking" custom ciphers, smooth-order DLP, differential fault attacks, and Shamir-style secret-sharing recovery over non-prime moduli. Always read source first to detect linearity/algebraic structure before reaching for SageMath or symbolic solvers.
When to use
- A challenge or target ships custom crypto (custom hash, custom block cipher, hand-rolled key derivation) and you need to look for affine / GF(2)-linear collapse.
- RSA-style primitives with structured primes (
p = a·r + b,phi(n)perfect square, multi-prime hint files, common factors). - A service exposes a chosen-ciphertext / chosen-input oracle and you suspect padding-oracle, smooth-order DLP, or Bleichenbacher-style recovery.
- AES with fault injection (correct + faulty ciphertext for the same key — Piret-Quisquater DFA).
- Shamir secret sharing or threshold schemes with non-prime moduli (2-adic recovery via Lagrange interpolation with valuation tracking).
References
- reference/lattice-attacks.md — AGCD lattice, discriminant-square factoring, smooth-order DLP, Piret-Quisquater DFA.
- reference/linear-secret-recovery.md — GF(2) affine collapse of custom hashes/ciphers via column-by-column linear recovery.
What ships with it
25 files 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.
- reference/cryptography-principles.md 4.9 KB
- reference/INDEX.md 3.7 KB
- reference/lattice-attacks.md 7.2 KB
- reference/linear-secret-recovery.md 3.3 KB
- reference/scenarios/classical/repeating-key-xor.md 2.4 KB
- reference/scenarios/lattice/agcd-attack.md 2.7 KB
- reference/scenarios/lattice/boneh-durfee-low-d.md 2.7 KB
- reference/scenarios/lattice/coppersmith-known-bits.md 3.1 KB
- reference/scenarios/lattice/lll-basis-reduction.md 3.2 KB
- reference/scenarios/padding-oracle/cbc-padding-oracle.md 3.6 KB
- reference/scenarios/padding-oracle/ecb-prefix-oracle.md 3.7 KB
- reference/scenarios/padding-oracle/pkcs1-v1.5-bleichenbacher.md 3.3 KB
- reference/scenarios/rsa-quirks/common-modulus.md 2.4 KB
- reference/scenarios/rsa-quirks/fermat-close-primes.md 2.4 KB
- reference/scenarios/rsa-quirks/low-public-exponent.md 3.0 KB
- reference/scenarios/rsa-quirks/small-prime-factorization.md 3.5 KB
- reference/scenarios/rsa-quirks/wiener-attack.md 2.7 KB
- reference/scenarios/secret-sharing/shamir-non-prime-modulus.md 5.0 KB
- reference/scenarios/signature-forgery/ecdsa-nonce-reuse.md 3.1 KB
- reference/scenarios/signature-forgery/gcd-transcript-operand-recovery.md 9.8 KB
- reference/scenarios/signature-forgery/jwt-alg-confusion.md 4.5 KB
- reference/scenarios/signature-forgery/rsa-pkcs1-v1.5-bleichenbacher.md 3.5 KB
- reference/scenarios/weak-rng/dual-ec-backdoor.md 3.3 KB
- reference/scenarios/weak-rng/lcg-state-recovery.md 3.5 KB
- reference/scenarios/weak-rng/mt19937-state-recovery.md 3.6 KB
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.
- 4d ago First seen · 24 lines · 27 tokens per session scan A f27acbccc67d
cryptography is a skill published in the GitHub repository transilienceai/communitytools (507 stars, last pushed 1mo ago), licensed MIT. It adds 27 tokens to every session and 417 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
pentester-playwright
Phases 1b/3/4 authorized browser automation — SPA recon, multi-role auth, route/API catalog, PoC screenshots, Evidence landing (scoped proxy). Skill-gate read for web phases. Use when Phase 1b/3/4 web work, JS-rendered SPA, real browser needed, HAR/network capture, or Playwright PoC evidence.
osint-recon
Phase 1 conditional OSINT depth — four-dimension model (server→site→domain→people; people is conditional). Skill-gate companion to pentester-enum-services / pentester-recon. Use for passive OSINT depth, full recon dimensions, author tracking, not as Phase 0/Schema replacement.
pentester-exploit
Phase 4 exploitation — PoC construction, exploit-db/msf search, safe verification. Required Skill-gate read at Phase 4. Use when starting Phase 4, exploitation, exploit, PoC, exploit-db, msf, Metasploit, or payload delivery.
pentester-recon
Phase 1 intelligence recon methodology — passive+active recon, stack fingerprint, attack-surface map. Required Skill-gate read at Phase 1 (with pentester-enum-services). Use when starting Phase 1, intelligence gathering, recon, reconnaissance, OSINT prep, target profiling, or attack surface mapping.
pentester-toolkit
Provision the pinned pentest toolset via DotSlash for the current scanenv (host-kali or kali-target-${ID}). Adapter, not a tool wrapper.
pentester-waf-bypass
Phase 4 conditional — WAF/filter bypass for authorized CTF/range/pentest when payloads are blocked. Use at Phase 4 if blocked, or when user mentions WAF bypass, filter evasion, SQL/XSS/command-injection bypass, or security filter analysis.