Borrowing it
Nothing to install: this file belongs to empir3hq/empir3-bridge. 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/empir3hq/empir3-bridge/main/AGENTS.mdgit clone --depth 1 https://github.com/empir3hq/empir3-bridgeWrote 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/empir3hq/empir3-bridge/agents-md)<a href="https://agentmods.dev/instructions/empir3hq/empir3-bridge/agents-md"><img src="https://agentmods.dev/badge/instructions/empir3hq/empir3-bridge/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/empir3hq/empir3-bridge/agents-md"><img src="https://agentmods.dev/badge/instructions/empir3hq/empir3-bridge/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 | $0.00606 | $0.00606 |
| Opus 5.5 | $0.00242 | $0.00242 |
| Sonnet 5.5 | $0.00121 | $0.00121 |
| Haiku 4.5 | $0.00061 | $0.00061 |
Grade A, and why
empir3-bridge 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 2mo 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.
Copies of this mod
2 near-identical copies found in the catalogue:
- empir3-bridge GEMINI.md — 100% identical, 0 lines differ
- empir3-bridge CLAUDE.md — 100% identical, 0 lines differ
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.
Empir3 Bridge — Agent & Contributor Guide
This is the standalone Empir3 Bridge repo: the local control plane that exposes browser and desktop tools to AI agents over MCP, plus the Windows tray/daemon and the signed payload + installer release pipeline.
What lives here
- The
localhost:3006dashboard, the/welcomeconsole, and/desktop-test - The MCP server (browser + desktop tools) and the scriptable CLI
- The CDP bridge that drives the dedicated Chrome profile
- The tray app, daemon reconnect/quit/port-cleanup, and the Windows payload + installer build
Before you edit
git status --short --branch
git pull --ff-only # only when the tree is clean
If the tree is dirty, identify the dirty files before editing — parallel sessions
may have uncommitted work in progress. Stage exact files only; never use
git add -A / git add . / git commit -a.
Run locally
npm install
npm start # launches the bridge; dashboard at http://localhost:3006
Useful checks:
npm run build:mcp # bundle the MCP server
npx tsc --noEmit # typecheck
npm test
Release / publish
Before changing a version, signing a package, publishing downloads, exporting
public source, creating a GitHub Release, or publishing npm, private maintainers
must read docs/internal/RELEASE_OPERATIONS.md when that file is present. It is
the canonical operator contract and is intentionally omitted from public
exports. If this is a public snapshot and the internal runbook is absent, use
docs/RELEASE.md for local/test builds but do not infer private release access.
package.json is the version source of truth. Bump it, then:
npm run build:windows # Empir3Setup.exe + signed payload under build/dist/
npm run release:check # verify the artifacts
npm run publish:downloads -- --dry-run
npm run publish:downloads # set EMPIR3_DOWNLOAD_HOST / EMPIR3_DOWNLOAD_DIR first
The deploy target is read from the environment, not hardcoded — see docs/RELEASE.md for the full flow, and docs/SAFETY.md / docs/TESTING.md for the safety model and test harness.
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.
- 2mo ago First seen · 67 lines · 606 tokens per session scan A 66a08a81df26
empir3-bridge AGENTS.md is an instructions file published in the GitHub repository empir3hq/empir3-bridge (3 stars, last pushed 12d ago), licensed MIT. It adds 606 tokens to every session, about $0.0024 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 2026-08-31.
empir3-bridge AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| empir3-bridge AGENTS.mdempir3hq/empir3-bridge | Instructions file | 3 | 12d ago | MIT | A | 606 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |