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/jubayertalha/vibeframe/agents-mdgit clone --depth 1 https://github.com/jubayertalha/vibeframeWrote 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/jubayertalha/vibeframe/agents-md)<a href="https://agentmods.dev/instructions/jubayertalha/vibeframe/agents-md"><img src="https://agentmods.dev/badge/instructions/jubayertalha/vibeframe/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 | $0.00571 | $0.00571 |
| Opus 5 | $0.00285 | $0.00285 |
| Sonnet 5 | $0.00114 | $0.00114 |
| Haiku 4.5 | $0.00057 | $0.00057 |
Grade A, and why
vibeframe 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent guide
vibeframe — VibeFrame model digest
A control plane for agentic coding — dogfooding itself
2 capabilities · 9 components · 2 decisions · 8 constraints · drift: 0 error / 0 warn
Capabilities
- agent-protocol — Agent protocol — the MCP linking loop (1 workflows, 6/6 steps bound)
- cli-surface — CLI command surface (1 workflows, 4/4 steps bound)
Components
- core — core — model schemas & primitives
- store — store — SQLite index → core
- indexer — indexer — code plane extraction → core, store
- engine — engine — graph & validation → core, store, indexer
- daemon — daemon — HTTP surface → core, store, indexer, engine
- cli — cli — vibeframe bin → core, store, indexer, engine, daemon
- ui — ui — lens browser UI
- plugin — plugin — Claude Code plugin
- scripts — scripts — repo tooling
Decisions
- 0001-zero-llm-calls — The framework makes zero LLM calls (LOCKED, approved)
- 0002-strict-dependency-direction — Strict package dependency direction; UI over HTTP only (LOCKED, approved)
Constraints (machine-checked)
- better-sqlite3 only in: store (sqlite-only-in-store)
- web-tree-sitter only in: indexer (tree-sitter-only-in-indexer)
- oxc-resolver only in: indexer (oxc-resolver-only-in-indexer)
- @parcel/watcher only in: indexer (parcel-watcher-only-in-indexer)
- graphology only in: engine (graphology-only-in-engine)
- hono only in: daemon (hono-only-in-daemon)
- @modelcontextprotocol/sdk only in: daemon, cli (mcp-sdk-daemon-cli-only)
- commander only in: cli (commander-only-in-cli)
Working with this model
- Before planning a feature, call the
vibe_contextMCP tool with the topic — it returns the relevant capabilities, components, decisions, and constraints in one brief. - Declare new capabilities/workflows/components with
vibe_decide/vibe_declareduring planning; bind implemented steps to code withvibe_linkafter implementing. - Run
vibe_validatebefore finishing; explain unmapped changes when the reconcile nudge appears.
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 · 45 lines · 571 tokens per session scan A 31639bbd2a98
vibeframe AGENTS.md is an instructions file published in the GitHub repository jubayertalha/vibeframe (0 stars, last pushed 8d ago), licensed MIT. It adds 571 tokens to every session, about $0.0029 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
cli CLAUDE.md
Claude Code instructions for archgate/cli, covering claude.md, technology stack, commands, validation gate and git hooks (git 2.54+).
mcp-adr-analysis-server copilot-instructions.md
Copilot instructions for tosin2013/mcp-adr-analysis-server, covering mcp adr analysis server - ai coding agent instructions, project overview, critical technical conventions, esm-only module system and typescript configuration.
adrkit AGENTS.md
Instructions for mbeacom/adrkit, covering adrkit, visual adr graph, inbound @adr markers (v0.5.0: explain, check, and ci), the spec kit extension (packages/adapters/spec-kit) and adr queue.
adrkit copilot-instructions.md
Instructions for mbeacom/adrkit, covering adrkit — github copilot and github copilot specifics.
adrkit CLAUDE.md
Instructions for mbeacom/adrkit, covering adrkit — claude code and claude code specifics.
ai-software-architect AGENTS.md
AGENTS.md instructions for codenamev/ai-software-architect, covering agents.md - ai software architect framework, project overview, framework development setup, repository structure and installation for framework development.