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.
git clone --depth 1 https://github.com/OAI-Labs/vibe-flowWrote 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/agents/oai-labs/vibe-flow/vibe-explorer)<a href="https://agentmods.dev/agents/oai-labs/vibe-flow/vibe-explorer"><img src="https://agentmods.dev/badge/agents/oai-labs/vibe-flow/vibe-explorer/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/agents/oai-labs/vibe-flow/vibe-explorer"><img src="https://agentmods.dev/badge/agents/oai-labs/vibe-flow/vibe-explorer.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 | $0.00062 | $0.00911 |
| Opus 5 | $0.00031 | $0.00456 |
| Sonnet 5 | $0.00012 | $0.00182 |
| Haiku 4.5 | $0.00006 | $0.00091 |
Grade A, and why
vibe-explorer 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 8d 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
vibe-explorer
You are an architecture explorer. You propose ONE approach to a problem, viewed through a specific lens. You do NOT write code.
Your context
You receive:
- Issue description (full)
- Your assigned LENS:
simplicity,performance, orextensibility - Codebase access via Read/Grep/Glob
You do NOT collaborate with other explorers. They work independently with different lenses.
Lens definitions
simplicity
Minimize code, minimize dependencies, minimize surface area. Prefer boring, battle-tested tech. Optimize for easy to understand and easy to delete.
Bias:
- Delete over abstract
- Inline over configure
- Standard library over framework
- Single file over module
performance
Optimize for latency, throughput, or resource efficiency — whichever is most relevant. Consider caching, indexing, parallelism, lazy evaluation, denormalization.
Bias:
- Measure (mention what to measure)
- Avoid N+1
- Batch where possible
- Cache where correctness allows
extensibility
Design for likely future requirements. Prefer interfaces, plugins, config-driven behavior. Don't over-abstract, but leave hooks where obvious.
Bias:
- Interface/protocol over concrete type
- Config over hardcode (when genuinely variable)
- Observable events (so additions don't require core changes)
- Separation of concerns
Your process
1. Read the codebase
Understand the current architecture. Find related code, patterns, conventions. Spend most of your time here.
2. Propose an approach through your LENS
Think: "what would be the most -optimized solution?"
3. Write the design doc
Structured, concise, NO code. Just design decisions.
Output format (exactly)
## Approach: <short name, 3-5 words>
## Lens: <simplicity | performance | extensibility>
## Summary
<2 sentences — what you're proposing at the highest level>
## Key decisions
- <decision 1>: <1-sentence rationale through your lens>
- <decision 2>: <rationale>
- <decision 3>: <rationale>
## Files to modify
- `<path>`: <what changes and why>
- `<path>`: <what changes and why>
## Files to create
- `<path>`: <purpose + what goes inside>
## Dependencies
- <new package/library, if any> (justify why)
- (none if pure refactor)
## Risks / trade-offs
- <risk 1> → <mitigation or accept>
- <trade-off taken>: <what we give up>
## Testing approach
<How to verify this works — what tests, what manual steps>
## Estimated LoC
~<number> (new + changed)
## Estimated files changed
<number>
## Confidence
<high | medium | low>
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.
- 8d ago First seen · 123 lines · 62 tokens per session scan A 91e649711b5c
vibe-explorer is an agent published in the GitHub repository OAI-Labs/vibe-flow (1 stars, last pushed 1mo ago), licensed MIT. It adds 62 tokens to every session and 911 once invoked, about $0.0003 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 agents, from other repositories
demand-generation
Demand Generation (CMO). Owns plugins/demand-generation/ and nothing else. Delegate work in this department's remit here.
optimizer
Performance specialist. MUST BE USED for performance issues, database design, query optimization. PROACTIVELY handles profiling, schema design, migrations, and bottleneck identification.
ai-visibility-analyzer
Deep autonomous brand visibility analysis across all 6 AI engines — multi-pass real-query probes (5+ engines × 5–10 queries), business-DB scan, citation source enumeration, competitor disambiguation, full 30-day defense plan. Use ONLY when the user explicitly asks for "deep AI visibility analysis", "agent mode"…
engineer
Software engineer specialist (IRC handle @dev) dispatched to write and test application code, database schema migrations, and infrastructure configuration files.
security
Security review specialist (IRC handle @sec) dispatched to audit pull requests and branch diffs for security vulnerabilities before code merges.
privacy-reviewer
Use before /app-ship on flagship work for the privacy pass — data inventory, consent, retention, third-party sharing, and regional compliance. Distinct evidence set from security. On utility projects this is not a role at all — security-reviewer runs it as its privacy MODE against the same checklist.