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 agents/telivityai/otaip/stage-9-platformgit clone --depth 1 https://github.com/TelivityAI/otaipWrote 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/telivityai/otaip/stage-9-platform)<a href="https://agentmods.dev/agents/telivityai/otaip/stage-9-platform"><img src="https://agentmods.dev/badge/agents/telivityai/otaip/stage-9-platform.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 | $0.00000 | $0.01361 |
| Opus 5 | $0.00000 | $0.00681 |
| Sonnet 5 | $0.00000 | $0.00272 |
| Haiku 4.5 | $0.00000 | $0.00136 |
Grade A, and why
stage-9-platform 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stage 9 -- Platform Agents
Package: @otaip/agents-platform
Multi-agent orchestration, knowledge retrieval, monitoring/alerting, audit/compliance, plugin management, and platform health aggregation.
Agent 9.1 -- Orchestrator
ID: 9.1
Class: Orchestrator
Status: Implemented
Multi-agent workflow coordination. Defines named workflows (search-to-price, book-to-ticket, full booking, exchange flow, refund flow) as step sequences. Supports conditional steps, parallel execution, error handling (stop/skip/continue), and pipeline building.
Input (OrchestratorInput):
workflow-- workflow nameinput-- workflow input dataoptions?--stop_on_error?,timeout_ms?
Output (OrchestratorOutput):
workflow-- workflow namestatus--'completed' | 'failed' | 'partial'steps-- per-step results (agent ID, status, duration, output/error)total_duration_msfinal_output?-- last step output
Constructor: Accepts injectable StepExecutor for testing without real agent imports.
Agent 9.2 -- Knowledge Retrieval
ID: 9.2
Class: KnowledgeRetrieval
Status: Implemented
RAG (Retrieval-Augmented Generation) over the travel knowledge base. Indexes documents by topic, supports BM25 + vector hybrid search with injectable embedding provider.
Input (KnowledgeInput):
operation--'query' | 'index_document' | 'list_topics' | 'get_document'- Query: query string, topic filter, max results
- Index: document ID, title, content, tags, topic
Output (KnowledgeOutput):
results?-- ranked results with relevance score, excerpt, full contentdocument?-- specific documenttopics?-- available topic listquery_time_ms?
Agent 9.3 -- Monitoring & Alerting
ID: 9.3
Class: MonitoringAlerting
Status: Implemented
Agent health monitoring: latency tracking (p50/p95), error rates, SLA compliance reporting. Records metrics, fires alerts on threshold violations, supports alert acknowledgment.
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 · 169 lines · 0 tokens per session scan A 3422c42de0bc
stage-9-platform is an agent published in the GitHub repository TelivityAI/otaip (40 stars, last pushed 10d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,361 tokens. 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 agents, from other repositories
claw-polisher
Open-source contributor specializing in NVIDIA Claw ecosystem projects (OpenClaw, NemoClaw, NanoClaw) with security-aware audit, false positive prevention, and convention-strict PR workflow.
framework-scout
Open-source agent framework assessor that evaluates community health, supersession risk, architecture alignment, and governance sustainability to classify investment readiness before committing resources.
marketing-claw-playbook
This playbook lets an external claw act as FlowWink's marketing department — running paid growth, content, audience research, and reporting end-to-end.
agent_invite
The onboarding text handed to an external agent that will operate a FlowWink instance over MCP — connection, protocols, resources and cadence.
finance-claw-playbook
This playbook lets an external claw act as FlowWink's finance department — running invoicing, expense booking, bank reconciliation, and period close (record-to-report) — without…
operations-claw-playbook
This playbook lets an external claw act as FlowWink's operations department — running inventory, purchasing, order fulfillment, manufacturing, and field service — without FlowPi…