Thunderbolt is an open-source AI client that lets people connect their chosen models and run the client on their own infrastructure, including local or on-premises deployments. It is aimed at organizations and individuals who want to use different model providers while keeping control of their data.
Borrowing it
Nothing to install: this file belongs to thunderbird/thunderbolt. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/thunderbird/thunderbolt/main/AGENTS.mdgit clone --depth 1 https://github.com/thunderbird/thunderboltWrote 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/thunderbird/thunderbolt/agents-md)<a href="https://agentmods.dev/instructions/thunderbird/thunderbolt/agents-md"><img src="https://agentmods.dev/badge/instructions/thunderbird/thunderbolt/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/thunderbird/thunderbolt/agents-md"><img src="https://agentmods.dev/badge/instructions/thunderbird/thunderbolt/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.10370 | $0.10370 |
| Opus 5.5 | $0.04148 | $0.04148 |
| Sonnet 5.5 | $0.02074 | $0.02074 |
| Haiku 4.5 | $0.01037 | $0.01037 |
Grade A, and why
thunderbolt AGENTS.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 today.
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 — 337 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository layout
Each workspace below has its own dependencies and its own checks; there is no single command that builds or tests the lot.
| Directory | What it is |
|---|---|
src/ |
The React app — chat, settings, PowerSync database layer, search, widgets. |
shared/ |
Code imported by more than one workspace. shared/agent-core (the in-browser adapter around the npm Pi package) has its own test command. |
backend/ |
The Elysia API: auth, proxy, PowerSync tokens, transactional email, Drizzle schema and migrations. |
cli/ |
The single-binary terminal coding agent. Its own package.json and bun.lock, released by cli-release.yml. |
crates/ |
thunderbolt-acp-client, a relay-only iroh client compiled to wasm; the built artifact is committed at src/acp/iroh/pkg. |
src-tauri/ |
The Tauri (Rust) shell for the desktop and mobile builds. |
web/ |
The public Astro site — landing, blog, and the Starlight docs. |
e2e/ |
Playwright specs (SSO, proxy, ACP, version gate) run against a real backend. |
deploy/ |
Self-hosting: Docker Compose, the Helm chart, and the Pulumi AWS stacks. |
powersync-service/ |
Docker Compose PowerSync stack for local development, including its sync rules. |
scripts/ |
Repo automation — releases, license headers, migration bundling, thunderdoctor. |
docs/ |
Architecture and development docs. |
public/ |
Static assets served by Vite. |
cli, agent-core, wasm-artifact and rust are separate path-gated jobs in .github/workflows/ci.yml, so a change in one of those trees is not covered by the frontend job. The wasm-artifact job requires crate input changes to include regenerated src/acp/iroh/pkg, checks current inputs against SOURCES.txt, and verifies artifacts against CHECKSUMS.txt. Rebuild with crates/thunderbolt-acp-client/build.sh and commit the output in the same change. For input-check failures and provenance limits, see the CI guide; build details live in the crate README.
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.
- today Changed · +55 tokens per session 92b6394b2c93
- 7d ago Changed · +4 tokens per session f2447782878d
- 8d ago Changed · +147 tokens per session 971b66ac77af
- 9d ago Changed · +11 tokens per session 1a2cf274cbb6
- 12d ago Changed · +5 tokens per session a90de03646e8
- 15d ago Changed · +47 tokens per session bdbb81451f26
- 23d ago Changed · +42 lines · +1,868 tokens per session d64f4b22bc3f
- 1mo ago Changed · +1 lines · +75 tokens per session 4b2d4dbef0fe
- 1mo ago Changed · +22 lines · +1,609 tokens per session b0ded3be900a
- 1mo ago First seen · 272 lines · 6,549 tokens per session scan A 16f8be34778b
thunderbolt AGENTS.md is an instructions file published in the GitHub repository thunderbird/thunderbolt (4,816 stars, last pushed today), licensed MPL-2.0. It adds 10,370 tokens to every session, about $0.0415 per session on Opus 5.5. 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
create-trimble-app typescript.instructions.md
Instructions for julianoczkowski/create-trimble-app, covering typescript patterns for modus components, event type casting, common event types, component ref types and modal ref pattern.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).