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/brightwave-inc/tidebreak/claude-mdgit clone --depth 1 https://github.com/brightwave-inc/tidebreakWrote 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/brightwave-inc/tidebreak/claude-md)<a href="https://agentmods.dev/instructions/brightwave-inc/tidebreak/claude-md"><img src="https://agentmods.dev/badge/instructions/brightwave-inc/tidebreak/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 5.1 | $0.01143 | $0.01143 |
| Opus 5 | $0.00571 | $0.00571 |
| Sonnet 5 | $0.00229 | $0.00229 |
| Haiku 4.5 | $0.00114 | $0.00114 |
Grade A, and why
tidebreak 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working in Tidebreak
Guidance for coding agents. Humans start at CONTRIBUTING.md.
Tidebreak is a Cargo workspace of Rust crates plus a Tauri desktop app whose UI
is React/TypeScript under crates/tidebreak-desktop/ui.
Hard rules
- Do not use the
bwCLI. Use this repository's Cargo, pnpm, and GitHub commands. - Branch off
main; PR back intomain. Never commit straight tomain. - Commit or push only when asked. Do not merge unless the request was to merge.
- For parallel-track work, claim the GitHub issue (assignee +
in-progress) before the first edit. Interactive work the user is directing here does not need an issue. - Use GitHub REST (
gh/gh api), not GraphQL. Shared agent sessions exhaust the GraphQL quota. - Pin every direct dependency to an exact version that already matches the lockfile. Dependabot is the upgrade path.
- Add a test only if a failure would change what we do. Prefer contracts, easy-to-reverse decisions, bug reproductions, and end-to-end behavior.
- Run a cheap relevant subset locally; let CI do the rest. A conflicting PR ran nothing — rebase before trusting green.
- Enable auto-merge (
gh pr merge <n> --squash --auto --delete-branch) so a ready PR lands when its lanes go green. - This is a public repository. No secrets, no private design docs.
GitHub tracking
The Tidebreak GitHub Project
is the board. Milestones are delivery buckets. Parked product ideas stay in
docs/deferred.md until a slice is buildable; do not copy
that list onto the board.
- Open an issue only for a bounded outcome with an owner. Do not file per-file or per-session tasks.
- Multi-slice work uses an
epicparent. Children are the slices, not the files inside them.
Desktop UI workflow
- Read
crates/tidebreak-desktop/ui/DESIGN.mdbefore visual work. It defines the palette, type scale, status vocabulary, and the canonical patterns for settings, cards, approvals, empty states, and icons;src/stylesContract.test.tsenforces the mechanical rules, so arbitrary font sizes and raw Tailwind palette classes fail CI. - When adding or changing a reusable visual component or a meaningful UI state,
add or update its Storybook story under
crates/tidebreak-desktop/ui/src/stories/. - Show the states that matter for evaluation, including loading, empty, success, failure, and compact variants when they apply. Reuse the typed Storybook fixtures instead of duplicating ad hoc sample data.
- Run
scripts/storybook.shwhile developing UI, and runpnpm --dir crates/tidebreak-desktop/ui storybook:buildbefore publishing relevant UI changes.
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 · 92 lines · 1,143 tokens per session scan A 6ef8d7129e10
tidebreak CLAUDE.md is an instructions file published in the GitHub repository brightwave-inc/tidebreak (24 stars, last pushed today), licensed Apache-2.0. It adds 1,143 tokens to every session, about $0.0057 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
openhuman AGENTS.md
AGENTS.md instructions for tinyhumansai/openhuman, covering openhuman, repository layout, runtime scope, ios client (experimental, non-shipping) and commands (from repo root).
openhuman CLAUDE.md
Claude Code instructions for tinyhumansai/openhuman, a project described as: OpenHuman is an open source personal AI for Mac, Windows and Linux — local-first memory, agent orchestration, and deep research.
Crux CLAUDE.md
Instructions for CueCrux/Crux, covering crux daemon — claude code instructions, scope, build & test, architecture and key rules.
simplicio AGENTS.md
AGENTS.md instructions for wesleysimplicio/simplicio: This repository owns public distribution, installers, host-plugin packages and the Tauri Desktop source in apps/desktop. The Runtime implementation is maintained in simplicio-runtime; inspect its verified public contracts when changing this boundary.
remnic AGENTS.md
AGENTS.md instructions for joshuaswarren/remnic, covering remnic - agent guide, architecture boundaries (non-negotiable), upstream references, adapter implementation rules and openclaw compatibility window.
plur CLAUDE.md
Claude Code instructions for plur-ai/plur, covering claude.md, what is plur, development, package dependency and version bumps.