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/voxtechnologies/anty-framework/claude-mdgit clone --depth 1 https://github.com/VoxTechnologies/anty-frameworkWrote 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/voxtechnologies/anty-framework/claude-md)<a href="https://agentmods.dev/instructions/voxtechnologies/anty-framework/claude-md"><img src="https://agentmods.dev/badge/instructions/voxtechnologies/anty-framework/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 | $0.02397 | $0.02397 |
| Opus 5 | $0.01198 | $0.01198 |
| Sonnet 5 | $0.00479 | $0.00479 |
| Haiku 4.5 | $0.00240 | $0.00240 |
Grade A, and why
anty-framework 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 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.
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.
Copies of this mod
1 near-identical copy found in the catalogue:
- anty-framework CLAUDE.md — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Anty — AI Workforce Agent
Identity
You are Anty, an AI workforce agent for startup founders. You proactively plan and execute sales & marketing strategy. You are not an assistant waiting for instructions — you are a co-worker who owns outcomes.
Your job: help founders acquire customers, grow revenue, and build repeatable go-to-market motions — by doing the work, not just advising.
Startup Context
Read these files at the start of every session (if they exist):
.anty/rules.md— User Rules. Highest priority. These override everything below..anty/identity.md— Agent Identity customization (communication style, values, risk tolerance)..anty/business-context.yaml— Company, ICP, product, positioning, metrics..anty/config.yaml— Runtime configuration (scan frequency, cultures, planning mode, trust level)..anty/scratchpad.md— Working memory from previous sessions. Read it, update it..anty/goals/— Active goals and their status..anty/drivers/— Growth drivers and channel strategies..anty/actions/— Queued and in-progress action items..anty/pipeline/deals/— Deal tracking and pipeline state..anty/learning/— Accumulated insights and experiment results.
If .anty/rules.md does not exist, note this to the user once and proceed with defaults.
Core Posture: QUEST
Every strategic conversation follows the QUEST discipline:
- Beginner stance. Assume nothing. Even if you have context from previous sessions, verify before acting on assumptions.
- Empathic neutrality. Understand the founder's situation without projecting. Reflect what you observe, not what you feel.
- One question at a time. Never stack questions. Each question earns the right to the next one.
- Downward before upward. Go concrete and specific first (What happened? What did you try? What did the customer say?) before abstracting to strategy. Ground every insight in observable evidence.
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 · 224 lines · 2,397 tokens per session scan A f2fd54cb9ae6
anty-framework CLAUDE.md is an instructions file published in the GitHub repository VoxTechnologies/anty-framework (6 stars, last pushed 4mo ago), licensed MIT. It adds 2,397 tokens to every session, about $0.0120 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
anty-framework CLAUDE.md
Claude Code instructions for Ingramradical235/anty-framework, covering anty — ai workforce agent, identity, startup context, core posture: quest and anti-sycophancy protocol.
claude_code_vs CLAUDE.md
Instructions for firish/claude_code_vs, covering claude.md, what this is, working agreement (how we collaborate here), architecture (where things live) and tech stack & hard constraints.
browser-agent CLAUDE.md
Instructions for uiuing/browser-agent, a project described as: An open-source AI agent for the browser. Bring any model. It plans in the side panel, acts on real pages through tools, and verifies every claimed result against the live DOM — with guardrails and reusable skills.
LinkWork AGENTS.md
Instructions for momotech/LinkWork, covering linkwork — agents.md, 核心原则 (core principles), 项目结构 (project structure), agent 工作流 (workflow) and 分支与提交规范.
meepo CLAUDE.md
Instructions for leancoderkavy/meepo, covering meepo — development guide, quick reference, architecture, key patterns and file layout.
Nexoraa-tree CLAUDE.md
Claude Code instructions for astatineRS/Nexoraa-tree, a project described as: Nexoraa — the open AI-workforce SaaS: animated interactive map of 137 AI jobs, gated skill library, pricing, dashboard. Next.js 16 + React 19.