Borrowing it
Nothing to install: this file belongs to Huskyauto/VisionClaw-Agent-Public-Release. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Huskyauto/VisionClaw-Agent-Public-Release/main/AGENTS.mdgit clone --depth 1 https://github.com/Huskyauto/VisionClaw-Agent-Public-ReleaseWrote 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/huskyauto/visionclaw-agent-public-release/agents-md)<a href="https://agentmods.dev/instructions/huskyauto/visionclaw-agent-public-release/agents-md"><img src="https://agentmods.dev/badge/instructions/huskyauto/visionclaw-agent-public-release/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 5.1 | $0.02657 | $0.02657 |
| Opus 5 | $0.01328 | $0.01328 |
| Sonnet 5 | $0.00531 | $0.00531 |
| Haiku 4.5 | $0.00266 | $0.00266 |
Grade A, and why
VisionClaw-Agent-Public-Release AGENTS.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 7d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Working in the VisionClaw Codebase
Companion to
replit.md. This file is the standard "agent instructions" surface that Claude Code, Cursor, OpenAI Codex CLI, and Gemini CLI all read on entry. Replit Agent readsreplit.md. Both files should stay in sync.
Identity
You are a coding agent working on VisionClaw — a multi-tenant agentic AI platform (Express/TypeScript backend, React/Vite frontend, Drizzle/Postgres, Stripe + Coinbase billing, Replit Auth). Owner: Robert Washburn. Public mirror: https://github.com/Huskyauto/VisionClaw-Agent-Public-Release.
The Cardinal Discipline: Search Before Reading
Inspired by the SocratiCode agent-instruction pattern. Whenever you need to find or understand something in this codebase, search before you read.
Wrong: open files speculatively, grep blindly, read 1000-line files end-to-end. Right: query an index first, then read only the lines the index points you to.
In this repo you have three indexes already wired up:
- Hybrid BM25 + pgvector knowledge search —
server/embeddings.ts::vectorSearchKnowledgedoes reciprocal-rank-fusion of full-text and vector search over the agent_knowledge table. - Skill-RAG with LLM-as-judge —
server/skill-rag.ts::enhanceRetrievaldecides whether a query needs HyDE rewrite, multi-hop decomposition, focus narrowing, or a direct answer. - Tool registry —
server/tools/index.tsexposes 393 tools, all described inTOOL_DEFINITIONS. UsegetAllToolDefinitions()rather than grepping the registry. (Authoritative counts:docs/CURRENT_PLATFORM_TOTALS.md.)
If the answer is not in those indexes, then fall back to ripgrep, then fall back to reading whole files. Reading whole files is the last resort, not the first.
Hard Rules (non-negotiable)
shared/schema.tsedits are allowed but require care. Before changing it: inspect the live DB withpsql $DATABASE_URLto confirm current column types and indexes; never alter a primary-key column type (serial ↔ varchar — generates destructiveALTER TABLE); runnpm run db:push(ornpm run db:push --forceif the safe push refuses); verify with anotherpsqlquery before declaring done. Sidecar files (e.g..local/code-health-checkpoint.json) remain a fine alternative when the state is genuinely transient.- Never
sql.raw()user input. Use parameterised queries via Drizzle. - Never log or print secrets. Treat
STRIPE_*,OPENAI_*,ANTHROPIC_*,GEMINI_*,MCP_API_KEY, OAuth tokens, and webhook secrets as poison. - Owner privacy: "Bob Washburn" privately, "Robert Washburn" publicly (i.e. anything that touches the public mirror).
- No emojis in code, prompts, or commit messages unless explicitly requested.
- Force-push pre-authorised for both private and public repos — but only via the
Auto Git PushandPublic Mirror Pushworkflows, never directly.
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.
- 7d ago First seen · 99 lines · 2,657 tokens per session scan A 0d2a458e7849
VisionClaw-Agent-Public-Release AGENTS.md is an instructions file published in the GitHub repository Huskyauto/VisionClaw-Agent-Public-Release (24 stars, last pushed 2d ago), licensed MIT. It adds 2,657 tokens to every session, about $0.0133 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 instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.