agentmods.dev

vibecosystem AGENTS.md

Repository instructions for vibeeval and vibecosystem, including their runtime components and Codex adapter. They define working rules, project constraints, and validation commands.

In plain words
What is it for?
Use them when modifying hooks, installers, configuration, or other repository components covered by the instructions.
Why use it?
They tell a coding agent what to inspect, preserve, avoid, and test before changing this codebase.

Instructions file for CodexOpenCode

530 25d ago A scan 241 tokens original MIT
View the source file vibeeval/vibecosystem
Install

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.

agentmods
npx agentmods add instructions/vibeeval/vibecosystem/agents-md
Clone the repo
git clone --depth 1 https://github.com/vibeeval/vibecosystem

Made for: Codex, OpenCode.

Per session 241 This file is loaded in full into every session.
When invoked 241 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00241 $0.00241
Opus 5 $0.00120 $0.00120
Sonnet 5 $0.00048 $0.00048
Haiku 4.5 $0.00024 $0.00024

Measured 3d ago against content hash a6af64ffcb1a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

vibecosystem 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 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.

AGENTS.md · 23 lines

What it actually says

vibecosystem

This repository contains Claude runtime components and a Codex luna_worker adapter. The default runtime is core; full is opt-in. Do not treat the number of files in the repository as the number of components injected into a session.

Working rules

  • Inspect the relevant files and configuration before editing.
  • Keep changes within the requested repository and task scope.
  • Preserve unrelated user changes and do not expose credentials.
  • Do not start swarm, memory, learner, or model-routing automation unless explicitly requested.
  • The Codex worker uses gpt-5.6-luna with max reasoning. Project config must not override it.
  • Claude-only opus and sonnet metadata must not be used by Codex.
  • Prefer the smallest complete change and run focused verification afterward.
  • Stop before destructive actions, external messages, or irreversible migrations that were not requested.

Validation

For hook changes run cd hooks && npm run check && npm test. For installer or config changes run the dry-run path with a temporary HOME and parse all JSON/TOML. Report changed paths, checks performed, and unresolved caveats.

Changes

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.

  1. 3d ago First seen · 23 lines · 241 tokens per session scan A a6af64ffcb1a

Subscribe to this mod's changes

vibecosystem AGENTS.md is an instructions file published in the GitHub repository vibeeval/vibecosystem (530 stars, last pushed 25d ago), licensed MIT. It adds 241 tokens to every session, about $0.0012 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.

ai-agentsautomationclaude-codeclaude-skillsdeveloper-toolshooks
Related

Other instructions, from other repositories

klaudiush CLAUDE.md

Instructions for smykla-skalski/klaudiush, covering claude.md, project overview, commands, completion (shell completion scripts) and doctor (diagnose setup and configuration).

smykla-skalski/klaudiush · 5,328 tokens

vibeguard AGENTS.md

Instructions for majiayu000/vibeguard, covering agent instructions, scope, start here, core rules and delivery policy.

majiayu000/vibeguard · 1,335 tokens

safedeps AGENTS.md

Instructions for aldegad/safedeps, covering agents.md — safedeps, engine support, architecture invariants (do not break), version ssot and docs.

aldegad/safedeps · 4,251 tokens

mumei AGENTS.md

Instructions for iroha924/mumei, covering agent reviewer guidance, what mumei is, setup commands, distribution boundary — flag violations and code style.

iroha924/mumei · 4,858 tokens

dev-flow AGENTS.md

Instructions for daphnee-ovo/dev-flow, covering dev-flow plugin, language policy, 注意事项, 命令 and 流程.

daphnee-ovo/dev-flow · 1,675 tokens

cc-safe-setup CLAUDE.md

Instructions for yurukusa/cc-safe-setup, covering project rules, safety, code style and git.

yurukusa/cc-safe-setup · 98 tokens