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/timescale/tiger-cli/claude-mdgit clone --depth 1 https://github.com/timescale/tiger-cliWhat 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 | $0.13873 | $0.13873 |
| Opus 5 | $0.06936 | $0.06936 |
| Sonnet 5 | $0.02775 | $0.02775 |
| Haiku 4.5 | $0.01387 | $0.01387 |
Grade A, and why
tiger-cli 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 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 — 1,301 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Naming Guidelines
When writing or updating documentation, code comments, CLI output, error messages, or any other user-facing text, use these official naming conventions:
Official Names
- Company Name: "Tiger Data" (two words, with space)
- Cloud Platform: "Tiger Cloud" (NOT "TigerData Cloud" or "TigerData Cloud Platform")
- CLI Tool: "Tiger CLI"
- MCP Server: "Tiger MCP"
- API References: "Tiger Cloud API" (NOT "TigerData API")
Examples
✅ Correct Usage:
- "Tiger CLI is a command-line interface for managing Tiger Cloud platform resources."
- "Authenticate with Tiger Cloud API"
- "List all database services in your Tiger Cloud project."
- "The Tiger MCP server provides programmatic access to Tiger Cloud."
❌ Incorrect Usage:
"TigerData Cloud Platform"→ Use "Tiger Cloud platform""TigerData API"→ Use "Tiger Cloud API""TigerData project"→ Use "Tiger Cloud project""TigerData MCP"→ Use "Tiger MCP"
Development Commands
Building
# Build the main CLI binary
go build -o bin/tiger ./cmd/tiger
# Build from project root (creates bin/tiger)
go build -o bin/tiger ./cmd/tiger
Testing
# Run all tests
go test ./...
# Run tests with verbose output
go test -v ./...
# Load environment variables from .env file (note: source .env doesn't work)
export $(cat .env | xargs)
# Run integration tests with environment variables from .env file
export $(cat .env | xargs) && go test ./internal/cmd -v -run TestServiceLifecycleIntegration
Running Locally
# After building, run the CLI
./bin/tiger --help
# Or run directly with go
go run ./cmd/tiger --help
Integration Testing
Using the Test Script (Recommended)
# Run all integration tests (default pattern: Integration)
./scripts/test-integration.sh
# Run with verbose output
./scripts/test-integration.sh -v
# Run specific test pattern (overrides default)
./scripts/test-integration.sh -run CreateRole
# Run with custom timeout
./scripts/test-integration.sh -timeout 10m
# Combine flags (any go test flags are supported)
./scripts/test-integration.sh -v -run CreateRole_WithInheritedGrants -timeout 5m
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 · 1,301 lines · 13,873 tokens per session scan A 451ff8460fbe
tiger-cli CLAUDE.md is an instructions file published in the GitHub repository timescale/tiger-cli (116 stars, last pushed 5d ago), licensed Apache-2.0. It adds 13,873 tokens to every session, about $0.0694 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
booster_mcp AGENTS.md
AGENTS.md instructions for NeuroGhostDev/booster_mcp, covering booster agent bootstrap, bootstrap contract, engineering workflow, context priority and important boundary.
ContextFlux AGENTS.md
AGENTS.md instructions for divyanshu-iitian/ContextFlux, a project described as: Task-adaptive repository context engine for coding agents: local MCP, exact token budgets, and dependency-aware retrieval.
md-vision-mcp AGENTS.md
AGENTS.md instructions for japlete/md-vision-mcp, covering md vision mcp server, status, layout, stack and rules.
CloudMind AGENTS.md
AGENTS.md instructions for evepupil/CloudMind, covering cloudmind agents.md, 项目定位, 架构方向升级（2026-06-05）：个人私有化 ai 记忆层, 当前产品定义 and mvp 原则.
CloudMind CLAUDE.md
Claude Code instructions for evepupil/CloudMind, covering cloudmind agents.md, 项目定位, 架构方向升级（2026-06-05）：个人私有化 ai 记忆层, 当前产品定义 and mvp 原则.
context-engineering-mcp CLAUDE.md
Claude Code instructions for croakingtoad/context-engineering-mcp, covering claude.md - context engineering mcp server, 🚨 critical development rules, ❌ absolutely no mock data, ✅ always use real implementations and 🔧 mcp protocol compliance.