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-2-pricinggit 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-2-pricing)<a href="https://agentmods.dev/agents/telivityai/otaip/stage-2-pricing"><img src="https://agentmods.dev/badge/agents/telivityai/otaip/stage-2-pricing.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 | $0.01546 |
| Opus 5 | $0.00000 | $0.00773 |
| Sonnet 5 | $0.00000 | $0.00309 |
| Haiku 4.5 | $0.00000 | $0.00155 |
Grade A, and why
stage-2-pricing 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 5d 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stage 2 -- Pricing Agents
Package: @otaip/agents-pricing
Fare rules, fare construction, tax calculation, offer building, corporate policy validation, and (coming soon) dynamic pricing and revenue management.
Agent 2.1 -- Fare Rule Agent
ID: 2.1
Class: FareRuleAgent
Status: Implemented
Parses ATPCO fare rules (categories 1-20) into human-readable structured format using curated tariff snapshot data.
Input (FareRuleInput):
fare_basis-- fare basis codecarrier-- marketing carrier IATA codeorigin-- origin IATA codedestination-- destination IATA codetravel_date?-- ISO date for date-based rule filteringcategories?-- specific ATPCO categories 1-50 (all if omitted)
Output (FareRuleOutput):
rules--FareRuleResult[]with parsed categories, penalty summary, advance purchase, min/max stay, seasonalitytotal_rules-- count of matched rulesvalid_for_date-- whether fare is valid for the specified travel datein_blackout-- whether travel date falls in a blackout period
Agent 2.2 -- Fare Construction
ID: 2.2
Class: FareConstruction
Status: Implemented
NUC × IROE construction with published TPM/MPM, Resolution 024d (HX/NX) rounding, and fail-closed HIP/BHC/CTM hooks. All financial math uses decimal.js.
Licensed IROE / 024d / TPM-MPM data are not shipped in the package. Pass them via data_sources. Missing IROE, TPM, or 024d → DomainInputRequired. Haversine-as-TPM and banker's rounding are banned.
KB: docs/knowledge-base/fare-construction-data-dependencies.md
Input (FareConstructionInput):
journey_type--'OW' | 'RT' | 'CT'(one-way, round-trip, circle-trip)components-- fare components (origin, destination, carrier, fare basis, NUC amount)selling_currency-- ISO 4217 currencypoint_of_sale?-- country for IROE selection contextdata_sources?-- licensed{ iroe, rounding_024d, mileage }(required for a constructed fare)
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.
- 5d ago First seen · 146 lines · 0 tokens per session scan A 5453f302dbad
stage-2-pricing is an agent published in the GitHub repository TelivityAI/otaip (41 stars, last pushed 2d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,546 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
audit-amazon
Amazon Ads evidence and controls specialist. Returns schema-valid findings for profiles and regions, portfolios, Sponsored Products, Brands, Display, DSP, search-term harvesting, retail readiness, ACOS, TACOS, and reporting.
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…
audit-creative
Cross-platform creative specialist. Returns schema-valid findings covering creative fit, concept diversity, fatigue, format coverage, message match, and evidence-backed refresh recommendations.
trellis-check
Code quality check expert. Reviews code changes against specs and self-fixes issues.
reviewer
You are a senior code reviewer with deep expertise in software quality, maintainability, and best practices.
AGENTS
GitMesh: Policy-as-Code Engine for Open Source AI Agent Orchestration.