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 instructions/ekscrypto/sm3/claude-mdgit clone --depth 1 https://github.com/ekscrypto/sm3What 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 | $0.03860 | $0.03860 |
| Opus 5 | $0.01930 | $0.01930 |
| Sonnet 5 | $0.00772 | $0.00772 |
| Haiku 4.5 | $0.00386 | $0.00386 |
Grade A, and why
sm3 CLAUDE.md 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 2d 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 — 436 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SM3 Swift Implementation Project
Project Description
This project implements the ShangMi 3 (SM3) cryptographic hash algorithm as a Swift Package. The implementation must:
- Use Swift 6.2
- Be entirely implemented in Swift (no C or Objective-C)
- No third-party libraries
- Produce 256-bit hash values
- Be compatible with official SM3 specifications
SM3 Algorithm Overview
SM3 is a cryptographic hash function published by the Chinese National Cryptography Administration on 2010-12-17 as GM/T 0004-2012: SM3 cryptographic hash algorithm. It is also standardized in:
- GB/T 32905-2016 (Chinese standard)
- ISO/IEC 10118-3:2018 (International standard)
- IETF Draft: draft-sca-cfrg-sm3
Key Characteristics
- Output Size: 256 bits (32 bytes)
- Block Size: 512 bits (64 bytes)
- Input Limit: Messages up to 2^64 bits
- Construction: Merkle-Damgård with Davies-Meyer compression function
- Security Level: Similar to SHA-256
Technical Specification
Constants
Initial Hash Value (IV)
0x7380166f, 0x4914b2b9, 0x172442d7, 0xda8a0600,
0xa96f30bc, 0x163138aa, 0xe38dee4d, 0xb0fb0e4e
Step Constants (T_j)
- For j = 0 to 15:
0x79cc4519 - For j = 16 to 63:
0x7a879d8a
Boolean Functions
FF_j (Message Schedule Function)
- For j = 0 to 15:
FF_j(X,Y,Z) = X ⊕ Y ⊕ Z - For j = 16 to 63:
FF_j(X,Y,Z) = (X ∧ Y) ∨ (X ∧ Z) ∨ (Y ∧ Z)
GG_j (Compression Function)
- For j = 0 to 15:
GG_j(X,Y,Z) = X ⊕ Y ⊕ Z - For j = 16 to 63:
GG_j(X,Y,Z) = (X ∧ Y) ∨ (¬X ∧ Z)
Permutation Functions
P₀(X)
P₀(X) = X ⊕ (X <<< 9) ⊕ (X <<< 17)
Where <<< denotes circular left shift (rotate left).
P₁(X)
P₁(X) = X ⊕ (X <<< 15) ⊕ (X <<< 23)
Algorithm Steps
1. Message Padding
Given a message M of length l bits:
- Append a single "1" bit to the message
- Append k "0" bits where k is the smallest non-negative solution to:
l + 1 + k ≡ 448 (mod 512) - Append the 64-bit big-endian representation of l
- Result: padded message with length ≡ 0 (mod 512)
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.
- 2d ago First seen · 436 lines · 3,860 tokens per session scan A 7f8c30a899fe
sm3 CLAUDE.md is an instructions file published in the GitHub repository ekscrypto/sm3 (10 stars, last pushed 9mo ago), licensed MIT. It adds 3,860 tokens to every session, about $0.0193 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 2026-08-31.
Other instructions, from other repositories
AppClaw CLAUDE.md
Instructions for appclawhq/AppClaw, covering claude.md, what is appclaw?, build & run commands, architecture and entry point & cli modes (src/index.ts).
MobiAI-Core CLAUDE.md
Instructions for ArisGuimera/MobiAI-Core, covering mobiai — mobile development ai ecosystem, bootstrap and principles.
freetube CLAUDE.md
Instructions for leshkodev/freetube, covering claude.md, 1. what this project is, 2. non-negotiable constraints, 3. tech stack (locked) and 4. project structure.
ConsultMe CLAUDE.md
Instructions for Tarek-Bohdima/ConsultMe, covering claude.md, project context, common commands, module graph and conventions enforced by tooling.
Plonk AGENTS.md
Instructions for ostapondo/Plonk, covering agent rules, layout, adding a module, build & verify and code style.
kotlin-app-template AGENTS.md
Instructions for ashtanko/kotlin-app-template, covering repository agent guide, start here, repository rules, working method and task-specific guidance.