Borrowing it
Nothing to install: this file belongs to aviz92/ai-agents-marketplace. 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/aviz92/ai-agents-marketplace/main/AGENTS.mdgit clone --depth 1 https://github.com/aviz92/ai-agents-marketplaceWrote 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/aviz92/ai-agents-marketplace/agents-md)<a href="https://agentmods.dev/instructions/aviz92/ai-agents-marketplace/agents-md"><img src="https://agentmods.dev/badge/instructions/aviz92/ai-agents-marketplace/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/aviz92/ai-agents-marketplace/agents-md"><img src="https://agentmods.dev/badge/instructions/aviz92/ai-agents-marketplace/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00635 | $0.00635 |
| Opus 5.5 | $0.00254 | $0.00254 |
| Sonnet 5.5 | $0.00127 | $0.00127 |
| Haiku 4.5 | $0.00064 | $0.00064 |
Grade A, and why
ai-agents-marketplace 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 2mo 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions
Versioning
Every time an artifact's content or metadata changes (anything under skills/,
plugins/, or rules/), bump the version field in its metadata.yaml.
This is how the CLI detects that an update is available.
Git
Never commit or push without explicit human approval.
Avi Zaguri — Workspace Rules
Senior Python developer. Be direct, concise, no fluff.
Rule Precedence
NEVER print the changes made to a file in the response. Always summarize the changes instead.
Project-local CLAUDE.md or AGENTS.md in the repo overrides this file. If they conflict, follow the project-local rules and flag the conflict once.
Plan Mode Response Format
- In plan mode, respond in 100 words or less
- Use numbered steps only
- No explanations, no commentary, no context
Libraries (check first)
I maintain an open-source Python ecosystem under github.com/aviz92/. Before implementing any utility — logging, exceptions, CLI scaffolding, API clients (GitHub/GitLab/Jira/Notion), DB access, email, secrets, DRF CRUD, test parameterization, test reporting, or a new project scaffold — consult LIBRARIES.md first. Before writing code that uses a library, fetch its current README from https://github.com/aviz92/<library_name>. Do not rely on memory for API shape.
Behavior
- Act autonomously on small-to-medium tasks: bug fixes, single-file changes, adding tests, refactoring within one module, dependency bumps, doc edits.
- Ask first for: changes touching 3+ files, public API changes, new dependencies, schema or migration changes, anything that alters project structure.
- Proactively flag tech debt, performance, and security issues.
Environment
- Package manager:
uvexclusively — never pip - Python: >=3.12
Security
- Never read/write .env, secrets/, credentials, token files
- Never commit API keys or passwords
- Always use parameterized queries
Git
- Conventional Commits (feat:, fix:, refactor:, test:, chore:, docs:)
- Branches: feature/, fix/, chore/ prefixes
- Pre-commit must pass before committing
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.
- 2mo ago First seen · 60 lines · 635 tokens per session scan A b9004d0fcec6
ai-agents-marketplace AGENTS.md is an instructions file published in the GitHub repository aviz92/ai-agents-marketplace (2 stars, last pushed 15d ago), licensed MIT. It adds 635 tokens to every session, about $0.0025 per session on Opus 5.5. 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.
ai-agents-marketplace AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ai-agents-marketplace AGENTS.mdaviz92/ai-agents-marketplace | Instructions file | 2 | 15d ago | MIT | A | 635 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |