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/d4rkninja/infynon-cli/claude-mdgit clone --depth 1 https://github.com/d4rkNinja/infynon-cliWrote 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/d4rkninja/infynon-cli/claude-md)<a href="https://agentmods.dev/instructions/d4rkninja/infynon-cli/claude-md"><img src="https://agentmods.dev/badge/instructions/d4rkninja/infynon-cli/claude-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 | $0.00700 | $0.00700 |
| Opus 5 | $0.00350 | $0.00350 |
| Sonnet 5 | $0.00140 | $0.00140 |
| Haiku 4.5 | $0.00070 | $0.00070 |
Grade A, and why
infynon-cli 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 5d 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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
src/contains the Rust CLI and product modules:cli/for argument routing,api/for Weave flows,trace/for repo memory,engine/for package scanning,tui/for terminal UI, andweb/for the embedded web server.front-layer/is the Vite + React frontend that is built and embedded into the Rust binary at compile time.docs/holds command and feature guides.scripts/contains install/build helpers.npm/andgo/provide wrapper distribution targets.- Build-time embedding is controlled by
build.rs; treat it as part of the app runtime path, not as optional tooling.
Build, Test, and Development Commands
cargo buildbuilds the Rust CLI and triggers frontend embedding when needed.cargo install --path . --forceinstalls the local build onto the machine for real CLI testing.cargo testruns Rust tests.npm run buildfromfront-layer/builds the web UI bundle explicitly.npm run lintandnpm run typecheckfromfront-layer/validate frontend code.infynon --host 127.0.0.1 --port 4173runs the bundled web server locally.
Coding Style & Naming Conventions
- Use Rust idioms:
snake_casefor functions/modules,PascalCasefor types, and small focused modules. - Keep frontend components in
PascalCasefiles when they are app-level components; shared UI primitives follow the existingfront-layer/src/components/ui/naming. - For frontend feature work, prefer composing dedicated subcomponents instead of keeping large pages in a single file.
- Use the existing shadcn UI primitives from
front-layer/src/components/ui/wherever possible instead of introducing ad-hoc replacements. - Do not add hardcoded colors in frontend code. Use theme tokens and semantic utility classes such as
bg-card,text-muted-foreground,border-border,bg-primary, and related token-based variants. - Prefer ASCII source files. Match existing formatting; use
cargo fmtonly on files you intend to change. - Avoid path-dependent runtime behavior. New web/runtime features should work from any current working directory.
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.
- 5d ago First seen · 39 lines · 700 tokens per session scan A c6b2e497aa54
infynon-cli CLAUDE.md is an instructions file published in the GitHub repository d4rkNinja/infynon-cli (8 stars, last pushed 3mo ago), licensed MIT. It adds 700 tokens to every session, about $0.0035 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
intelligent-terminal rust-wta.instructions.md
File-scoped conventions for the WTA Rust crate.
moai-adk CLAUDE.md
Claude Code instructions for modu-ai/moai-adk, covering moai execution directive, 0. standing contract (imported), 1. core identity, hard rules (mandatory) and 2. request processing pipeline.
lid AGENTS.md
Instructions for jszmajda/lid, covering agents.md, repository purpose, structure, plugin architecture (claude code) and other agentic coding tools.
cc-use-exp rust.instructions.md
Instructions for doccker/cc-use-exp: Rust 相关任务遵守以下约定（聚焦后端 Web，Axum + Tokio 路线）：.
agentdoctor AGENTS.md
Instructions for youssefsz/agentdoctor, covering agent instructions, project overview, operating principles, stack and commands.
conforme rust-conventions.instructions.md
Instructions for maxgfr/conforme, a project described as: Sync your AI coding config from Claude Code, Cursor, or any tool — rules, skills, agents, MCP servers.