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/liyoncso-theone/vibe-state-cli/agents-mdgit clone --depth 1 https://github.com/liyoncso-Theone/vibe-state-cliWrote 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/liyoncso-theone/vibe-state-cli/agents-md)<a href="https://agentmods.dev/instructions/liyoncso-theone/vibe-state-cli/agents-md"><img src="https://agentmods.dev/badge/instructions/liyoncso-theone/vibe-state-cli/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 | $0.00996 | $0.00996 |
| Opus 5 | $0.00498 | $0.00498 |
| Sonnet 5 | $0.00199 | $0.00199 |
| Haiku 4.5 | $0.00100 | $0.00100 |
Grade A, and why
vibe-state-cli 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 4d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — vibe-state-cli
Project
Last Session
- Progress: [2026-06-10 10:21] docs(backlog): record v0.3.6 design side-effects for v0.3.7+ consideration; Merge pull request #9 from liyoncso-Theone/release/v0.3.6; Merge pull request #8 from liyoncso-Theone/dependabot/github_actions/actions/checkout-6.0.3
- Pending: 3 tasks —
_build_basic_memory_sectiontemplate wording 太絕對,_build_memory_sectionconfig 載入 silent except, silent except pattern 還有 2 處未修
Session Start — READ THESE FILES
At the beginning of every session, read these files for project context:
.vibe/state/current.md— latest progress and sync history.vibe/state/tasks.md— active task checklist.vibe/state/standards.md— coding conventions and project rules
Persistent Knowledge — QUERY BEFORE RECALL
This project's persistent cross-machine knowledge lives in Basic Memory (markdown-on-disk knowledge graph, MCP-accessible from any agent).
Before answering recall questions ("what did we decide", "where did we leave off", "what's our principle on X"), query the knowledge layer first:
mcp__basic-memory__search_notes(query="…")— text + semantic searchmcp__basic-memory__search_notes(metadata_filters={"type": "decision"})— structured query by typemcp__basic-memory__build_context(url="memory://<topic>", depth=2)— graph traversal from a seed note
Projects: query whichever Basic Memory projects this agent has access to (use mcp__basic-memory__list_memory_projects to enumerate). Configure preferred projects in .vibe/config.toml under [memory].projects = [...].
Fallback: If Basic Memory is offline, the MCP server is not registered, or a query fails/times out, fall back to .vibe/state/ files (current.md, tasks.md, standards.md) as your baseline — they are the on-disk ground truth this repo always carries. Print a one-line warning to the human (e.g. ⚠ Basic Memory unavailable — using .vibe/state only), do NOT retry MCP calls, do NOT block on the recall.
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.
- 4d ago First seen · 79 lines · 996 tokens per session scan A a797b6addff9
vibe-state-cli AGENTS.md is an instructions file published in the GitHub repository liyoncso-Theone/vibe-state-cli (2 stars, last pushed 1mo ago), licensed MIT. It adds 996 tokens to every session, about $0.0050 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
interactive-mcp copilot-instructions.md
Instructions for ttommyth/interactive-mcp, covering interaction with user and ai notes - cursor documentation system.
claude-code-conversation-search-mcp CLAUDE.md
Instructions for TonySimonovsky/claude-code-conversation-search-mcp, a project described as: Stop losing Claude Code conversations. Search across all projects, find old chats, and resume where you left off.
serena AGENTS.md
AGENTS.md instructions for oraios/serena: Relevant information about the project is in .serena/memories. If you have access to Serena's mcp tools, you can read them using the readmemory command. Otherwise you can just read them using normal file reading tools.
mex CLAUDE.md
Claude Code instructions for mex-memory/mex, a project described as: Persistent project memory for AI coding agents. Structured scaffold + drift detection CLI.
recall CLAUDE.md
Instructions for joseairosa/recall, covering claude.md, project context, build & run commands, testing and unit tests with vitest (primary test runner).
knowns AGENTS.md
AGENTS.md instructions for knowns-dev/knowns, covering agents, runtime guidance, minimum rules and quick reference.