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/kota1026/quantum-shield/agents-mdgit clone --depth 1 https://github.com/kota1026/quantum-shieldWrote 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/instructions/kota1026/quantum-shield/agents-md)<a href="https://agentmods.dev/instructions/kota1026/quantum-shield/agents-md"><img src="https://agentmods.dev/badge/instructions/kota1026/quantum-shield/agents-md.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 | $0.01591 | $0.01591 |
| Opus 5 | $0.00796 | $0.00796 |
| Sonnet 5 | $0.00318 | $0.00318 |
| Haiku 4.5 | $0.00159 | $0.00159 |
Grade F, and why
quantum-shield AGENTS.md scanned grade F with 4 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 3d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- "sudo *" Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
- "curl * | sh" Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- "rm -rf" Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- "curl * | sh" How it starts
The opening of the file, as written. The whole thing — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md - Quantum Shield Project
Standard: OpenAI Agentic AI Foundation Version: 1.0 Last Updated: 2026-01-11
Project Overview
Quantum Shield is a quantum-resistant L3 blockchain protocol with multi-signature verification.
Core Components
| Component | Path | Language | Description |
|---|---|---|---|
| L1 Contracts | contracts/ |
Solidity | Ethereum mainnet contracts |
| L3 Aegis | l3-aegis/ |
Rust | Custom L3 chain (4-node BFT) |
| Backend API | services/api/ |
Rust | REST API server |
| Event Bridge | services/event-bridge/ |
Rust | L1↔L3 message relay |
| React SDK | packages/sdk/react/ |
TypeScript | React hooks for DApp |
| WASM Crypto | packages/sdk/wasm/ |
Rust→WASM | Client-side cryptography |
| Web Apps | apps/ |
TypeScript/React | Frontend applications |
Allowed Actions
File Operations
read:
- "**/*" # All files readable
write:
- "contracts/src/**/*.sol"
- "contracts/test/**/*.sol"
- "contracts/script/**/*.sol"
- "l3-aegis/**/*.rs"
- "services/**/*.rs"
- "packages/**/*.ts"
- "packages/**/*.tsx"
- "apps/**/*.ts"
- "apps/**/*.tsx"
- "docs_new/**/*.md"
- "*.md"
- "*.json"
- "*.toml"
- "*.yaml"
delete:
- "contracts/test/**/*" # Test files only
- "docs_new/01_phase/**/*.md" # Phase docs
no_write:
- "_archive/**/*" # Archive is read-only reference
- "docs_new/00_core/CORE_PRINCIPLES.md" # Constitution is immutable
- ".git/**/*"
- "node_modules/**/*"
- "target/**/*"
Command Execution
allowed_commands:
# Build
- "forge build"
- "forge clean"
- "cargo build"
- "cargo build --release"
- "npm run build"
- "npm install"
# Test
- "forge test"
- "forge test --match-*"
- "forge test --fuzz-runs *"
- "cargo test"
- "npm test"
- "npm run test:*"
# Analysis
- "slither *"
- "mythril analyze *"
- "cargo clippy"
- "npm run lint"
# Development
- "anvil"
- "forge script *"
- "cargo run *"
# Git (read-only + safe operations)
- "git status"
- "git diff"
- "git log"
- "git branch"
- "git add"
- "git commit"
- "git push origin claude/*" # Only claude/ branches
prohibited_commands:
- "git push origin main"
- "git push origin master"
- "git push --force"
- "rm -rf"
- "sudo *"
- "curl * | sh"
- "wget * | sh"
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.
- 3d ago First seen · 211 lines · 1,591 tokens per session scan F 14ff18aa119e
quantum-shield AGENTS.md is an instructions file published in the GitHub repository kota1026/quantum-shield (0 stars, last pushed 5d ago), licensed MIT. It adds 1,591 tokens to every session, about $0.0080 per session on Opus 5. A static security scan graded it F with 4 findings (asks for root, downloads and executes remote code, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
WAIaaS CLAUDE.md
Instructions for waiaas/WAIaaS, covering waiaas project rules, language, communication, schema & type system and database.
ponscli CLAUDE.md
Claude Code instructions for mesutgulecen/ponscli, covering ponscli, the rule that matters most, layout, verifying a change and things that will bite.
ponscli AGENTS.md
AGENTS.md instructions for mesutgulecen/ponscli, a project described as: Unofficial command-line interface for the Pons launchpad on Robinhood Chain.
lineth-monorepo AGENTS.md
AGENTS.md instructions for LFDT-Lineth/lineth-monorepo, covering agents.md, documentation precedence, agent entry points, local agent workflows and discoverability index.
behavioral-prediction-mcp CLAUDE.md
Instructions for ChainAware/behavioral-prediction-mcp, covering chainaware behavioral prediction mcp, project overview, mcp tools (14 total), batch pipeline and repository structure.
suwappubot CLAUDE.md
Claude Code instructions for 0xSoftBoi/suwappubot, covering claude.md, workflow, response length, git conventions and git operations.