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/telivityai/otaip/claude-mdgit 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/instructions/telivityai/otaip/claude-md)<a href="https://agentmods.dev/instructions/telivityai/otaip/claude-md"><img src="https://agentmods.dev/badge/instructions/telivityai/otaip/claude-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 | $0.05118 | $0.05118 |
| Opus 5 | $0.02559 | $0.02559 |
| Sonnet 5 | $0.01024 | $0.01024 |
| Haiku 4.5 | $0.00512 | $0.00512 |
Grade A, and why
otaip CLAUDE.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 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 — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OTAIP — Claude Code Constitution
Core Rule
DO NOT INVENT DOMAIN LOGIC. All travel domain knowledge comes from files in docs/knowledge-base/. If something is ambiguous or missing, write a // TODO: DOMAIN_QUESTION: {question} comment and move on. Do not guess. Do not fill gaps from "general knowledge." Hotel and airline domains have edge cases that seem obvious but aren't.
When Blocked
If you lack domain input to proceed: refactor, clean, document existing code, then surface the blocking question. Never invent travel industry behavior.
Tech Stack
- TypeScript (
strict: true, plusnoUncheckedIndexedAccess,noImplicitOverride,noPropertyAccessFromIndexSignature;exactOptionalPropertyTypesis off — enabling it would require widespread call-site changes, tracked as a separate cleanup) - Node.js >=24
- pnpm 10+ (workspace monorepo)
- Vitest for testing
- tsup for building
- ESLint + Prettier for linting/formatting
- ESM modules (type: "module")
Agent Contract
Every agent implements:
interface Agent<TInput, TOutput> {
readonly id: string;
readonly name: string;
readonly version: string;
initialize(): Promise<void>;
execute(input: AgentInput<TInput>): Promise<AgentOutput<TOutput>>;
health(): Promise<AgentHealthStatus>;
}
Imported from @otaip/core.
Error Handling
Use existing error classes from @otaip/core:
AgentNotInitializedError— execute() before initialize()AgentInputValidationError— bad input (with field + reason)AgentDataUnavailableError— external source downAgentError— base class for custom errors
Agent File Structure
Follow the pattern in packages/agents/reference/src/airport-code-resolver/:
{agent-name}/
types.ts — all input/output/internal types
{logic}.ts — core business logic (pure functions)
index.ts — Agent interface implementation
__tests__/
{agent}.test.ts — vitest tests
Rules
- No
anytypes without explicit justification comment - No secrets or API keys in code
- No hardcoded credentials
- Every agent needs tests
- Agents are stateless
- Use existing error classes, don't create new ones unless necessary
- Mock external APIs in tests — never call real APIs from tests
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 · 211 lines · 5,118 tokens per session scan A 3bc37fbdd1ec
otaip CLAUDE.md is an instructions file published in the GitHub repository TelivityAI/otaip (41 stars, last pushed 2d ago), licensed Apache-2.0. It adds 5,118 tokens to every session, about $0.0256 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 2026-08-30.
Other instructions, from other repositories
openscreen AGENTS.md
AGENTS.md instructions for getopenscreen/openscreen, covering agents.md, setup commands, development principles, project layout and code style.
Claw3D AGENTS.md
Instructions for iamlukethedev/Claw3D, covering agent instructions, cursor cloud specific instructions, service overview, running the app and lint, typecheck, and tests.
commonly CLAUDE.md
Claude Code instructions for Team-Commonly/commonly, covering claude.md / agents.md, 🧠 product vision & architecture philosophy, what commonly is, the architecture model and key concepts.
claude-ads CLAUDE.md
Instructions for AgriciDaniel/claude-ads, covering claude ads repository instructions, architecture, development and verification.
openstatus AGENTS.md
AGENTS.md instructions for openstatusHQ/openstatus, covering agents.md, verify your change, toolchain, architecture and tests.
windmill AGENTS.md
AGENTS.md instructions for windmill-labs/windmill, covering windmill, workflow, documentation, dev environment and per-worktree ports and database.