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/team-attention/tide/claude-mdgit clone --depth 1 https://github.com/team-attention/tideWrote 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/team-attention/tide/claude-md)<a href="https://agentmods.dev/instructions/team-attention/tide/claude-md"><img src="https://agentmods.dev/badge/instructions/team-attention/tide/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 | $0.00633 | $0.00633 |
| Opus 5 | $0.00316 | $0.00316 |
| Sonnet 5 | $0.00127 | $0.00127 |
| Haiku 4.5 | $0.00063 | $0.00063 |
Grade A, and why
tide 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tide — Monorepo
This repo hosts two independent Tide products that share the brand but not code (different languages, separate builds). Pick the right app directory before working.
| App | Path | Stack | Build |
|---|---|---|---|
| Terminal (v1) | apps/terminal/ |
Rust + WGPU native macOS app | cargo (run from apps/terminal/) |
| Desktop (v2) | apps/desktop/ |
Electron + Node + React | npm (run from apps/desktop/) |
Before building, define the work
Whenever a request means creating or changing something — a feature, a fix, a refactor, anything you'd write code for — do not start until these three are explicit. They are the contract for the work:
- Goal — exactly what is wanted, as a concrete outcome, not a vague direction.
- Current state & gap — how it works today and precisely what's missing or wrong. If you can't state the gap, you don't understand the task yet.
- Verification scenario — the concrete steps that prove it's done: what you'll do, what you expect to see. If you can't name how you'd check it, you can't claim it works.
If any of the three is missing or ambiguous, ask before writing code — one focused round of questions to pin it down. Don't guess the goal, don't invent a gap, and don't build something you have no way to verify. Filling these in is the first step of the work, not overhead.
Rules
- Each app is self-contained. Its build files (
Cargo.toml/package.json), source, tests, docs, and scripts all live under its own directory. The repo root holds only brand-level files (README.md,LICENSE,assets/,.github/). - Never run a build from the repo root.
cd apps/terminalfor Rust,cd apps/desktopfor the Electron app. - No code is shared across the two apps (Rust ≠ TypeScript). If you ever share anything it is the process-boundary contract shape, mirrored per language.
- Each app has its own detailed instructions — read those before changing code:
apps/terminal/CLAUDE.md(+apps/terminal/AGENTS.md,apps/terminal/docs/)apps/desktop/docs_v2/and thetide-v2-planskill.
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 · 53 lines · 633 tokens per session scan A 8dd3a779cef1
tide CLAUDE.md is an instructions file published in the GitHub repository team-attention/tide (74 stars, last pushed 1mo ago), licensed MIT. It adds 633 tokens to every session, about $0.0032 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
cowork-forge AGENTS.md
Instructions for sopaco/cowork-forge, covering agents.md — cowork forge, project overview, workspace structure, dev environment setup and prerequisites.
plannotator AGENTS.md
AGENTS.md instructions for backnotprop/plannotator, covering plannotator, project structure, server runtimes, installation and environment variables.
solo AGENTS.md
AGENTS.md instructions for solo-agent/solo, covering project testing rules and project service lifecycle rules.
superset AGENTS.md
AGENTS.md instructions for superset-sh/superset, covering superset monorepo, project structure, exception: shadcn/ui components, database and releases.
untether GEMINI.md
Gemini CLI instructions for littlebearapps/untether, covering untether — gemini instructions, stack & conventions, architecture, key rules and testing.
agent-tools AGENTS.md
AGENTS.md instructions for kairyou/agent-tools, covering agent instructions, build and test, layout, settled decisions and docs.