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/withkynam/vibecode-pro-max-kit/agents-mdgit clone --depth 1 https://github.com/withkynam/vibecode-pro-max-kitWhat 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 | $0.08750 | $0.08750 |
| Opus 5 | $0.04375 | $0.04375 |
| Sonnet 5 | $0.01750 | $0.01750 |
| Haiku 4.5 | $0.00875 | $0.00875 |
Grade A, and why
vibecode-pro-max-kit 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.
How it starts
The opening of the file, as written. The whole thing — 705 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Bootstrap guard: If process/context/all-context.md does not exist, the harness has not been set up yet (a bare process/context/ holding only generated-skills-catalog.json from install does NOT count). Run vc-setup before any task — the context router and protocol docs are absent and agents will not route correctly.
This file is the Codex compatibility layer for the existing .claude/ system.
Keep this file aligned with CLAUDE.md as much as possible while adapting Claude-native concepts to Codex-native constructs.
Codex discovers project-local skills from .agents/skills/. In this repo, .agents/skills/
is a symlink to .claude/skills/ so Codex and Claude share the same underlying skill tree:
.claude/skills/is the canonical source for shared skills and command-style workflows.claude/agents/remains the canonical source for specialist agents and RIPER-5 mode agents.codex/agents/mirrors.claude/agents/for Codex subagent roles- shared reusable skills that Codex should discover must live under
.claude/skills/as realSKILL.mdfiles with YAML frontmatter; agent wrappers should not exist
Prefer updating .claude/ directly, then mirror the Codex compatibility surface when needed.
Because .agents/skills/ resolves to the same folder, new skills added in either path appear
in both places automatically.
See process/context/all-context.md for project-specific coding preferences and conventions.
RIPER-5 Spec-Driven Development System
This project uses RIPER-5 methodology for systematic, spec-driven development. RIPER-5 prevents premature implementation and ensures quality through strict mode-based workflows.
Shared Development Protocols
Canonical shared workflow rules now live in process/development-protocols/all-development-protocols.md.
Read these files as needed:
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 · 705 lines · 8,750 tokens per session scan A d28bf505b002
vibecode-pro-max-kit AGENTS.md is an instructions file published in the GitHub repository withkynam/vibecode-pro-max-kit (1,112 stars, last pushed 2mo ago), licensed MIT. It adds 8,750 tokens to every session, about $0.0438 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
opencli AGENTS.md
Instructions for zjshen14/opencli, covering agents.md, project overview, getting started with a task, commands and source structure.
multiagent-template CLAUDE.md
Instructions for Neftedollar/multiagent-template, covering how to start (required for every session), 1. determine mode, 2. load context (depends on mode), 3. act and workspace structure.
multiagent-template copilot-instructions.md
Instructions for Neftedollar/multiagent-template, covering workspace structure, how to work in this repo, multi-agent pipeline, orchestrator role and escalate to human only for.
task-orchestrator CLAUDE.md
Instructions for jpicklyk/task-orchestrator, covering project: mcp task orchestrator, build commands, docker (most common), architecture and modes of operation.
agent-cli AGENTS.md
AGENTS.md instructions for VictorTomaili/agent-cli, covering agents.md, what this is, install / update / init, working in this checkout and conventions to preserve.
muggle-ai-teams CLAUDE.md
Instructions for multiplex-ai/muggle-ai-teams, covering claude.md, what this repo is, installation & setup, option a: npm (copies files to /.claude/) and option b: git clone (symlinks to /.claude/).