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/mattflower/tempest/claude-mdgit clone --depth 1 https://github.com/MattFlower/tempestWrote 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/mattflower/tempest/claude-md)<a href="https://agentmods.dev/instructions/mattflower/tempest/claude-md"><img src="https://agentmods.dev/badge/instructions/mattflower/tempest/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 | $0.00893 | $0.00893 |
| Opus 5 | $0.00447 | $0.00447 |
| Sonnet 5 | $0.00179 | $0.00179 |
| Haiku 4.5 | $0.00089 | $0.00089 |
Grade B, and why
tempest CLAUDE.md scanned grade B with 1 finding 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 4d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
| Per-session MCP tool injection (`show_webpage`, `show_mermaid_diagram`, `show_markdown`) | Yes (`--mcp-config`) | — | **No** — Codex reads MCP from `~/.codex/config.toml` globally | How it starts
The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tempest — Electrobun Rewrite
Overview
Tempest is a macOS developer tool rewritten from Swift/SwiftUI to Electrobun/TypeScript. Two-process architecture: Bun backend + React webview frontend, communicating via typed RPC.
Tech Stack
- Framework: Electrobun (private fork, see below) — Bun + native WebView.
- UI: React 19 + Tailwind CSS 4 + Zustand
- Terminal: xterm.js 6 with WebGL renderer + Bun.Terminal PTY
- Browser: System webview (WKWebView on macOS) via
<electrobun-webview>
Forked Electrobun
The electrobun dependency in package.json is not the published
npm package. It's a tarball URL pointing at a release on
MattFlower/electrobun (branch auto-mask-overlays, local checkout
at ~/code/electrobun). The fork is rebased on upstream v1.18.1 and
adds two things Tempest relies on: an auto-mask attribute on
<electrobun-webview> for popups over native browser panes, and a
re-sync bugfix in OverlaySyncController. (Traffic-light positioning
via setWindowButtonPosition was previously a fork patch but has
since landed in upstream — Tempest now consumes it directly.)
Read AI_DOCS/electrobun-fork.md before changing anything that
touches <electrobun-webview>, the bun-side electrobun APIs, or the
native window chrome — and before answering questions about how the
electrobun dependency is wired. Cutting a new fork release uses the
runbook at ~/code/electrobun/RELEASING-TEMPEST-FORK.md.
Key Architectural Rules
- Terminal lifecycle: Never unmount terminal components on tab switch. Use opacity-0 + pointer-events-none.
- PaneNode is immutable: All tree operations return new trees.
- RPC hot path: Terminal I/O uses fire-and-forget messages. Base64 encode PTY data. Sequence numbers for ordering.
- Microtask coalescing: PTY output batched via queueMicrotask.
Coding Agents
Tempest supports three terminal-hosted coding agents. Their integration depth differs because each CLI exposes different extension points.
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.
- 4d ago First seen · 67 lines · 893 tokens per session scan B 540e2abc8ddc
tempest CLAUDE.md is an instructions file published in the GitHub repository MattFlower/tempest (7 stars, last pushed 26d ago), licensed MIT. It adds 893 tokens to every session, about $0.0045 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
apm python.instructions.md
Python development guidelines.
CodexPotter AGENTS.md
AGENTS.md instructions for breezewish/CodexPotter, covering repository guidelines, workflow principles, engineering rules, core principles: simplicity & readability and better maintainability.
OpenMicro AGENTS.md
Instructions for stephenleo/OpenMicro, covering openmicro — project conventions and releases.
squarebox CLAUDE.md
Instructions for SquareWaveSystems/squarebox, covering claude.md, agent skills, issue tracker, triage labels and domain docs.
CodexBar AGENTS.md
AGENTS.md instructions for bob-zebedy/CodexBar, covering repository guidelines, 项目结构与模块组织, 构建、测试与开发命令, 写作风格 and 代码和注释.
AGENTS.md AGENTS.md
AGENTS.md instructions for tkumata/AGENTS.md, covering global agent instructions, language, precedence, core rules and workflow and approval.