Borrowing it
Nothing to install: this file belongs to DevVig/microbridge. 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/DevVig/microbridge/main/AGENTS.mdgit clone --depth 1 https://github.com/DevVig/microbridgeWrote 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/devvig/microbridge/agents-md)<a href="https://agentmods.dev/instructions/devvig/microbridge/agents-md"><img src="https://agentmods.dev/badge/instructions/devvig/microbridge/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/devvig/microbridge/agents-md"><img src="https://agentmods.dev/badge/instructions/devvig/microbridge/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 | $0.00323 | $0.00323 |
| Opus 5.5 | $0.00129 | $0.00129 |
| Sonnet 5.5 | $0.00065 | $0.00065 |
| Haiku 4.5 | $0.00032 | $0.00032 |
Grade A, and why
microbridge 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.
What it actually says
Learned User Preferences
- Aim for Claude-parity Cursor integration (approve/reject/interrupt/focus/new session), not lifecycle-only Limited status.
- When shipping a Microbridge release, confirm version bumps and that DMG (and other release) assets were published—not only that the PR merged.
- Do not admin-bypass failing required CI on Microbridge merges; CodeRabbit rate-limit failures alone are non-blocking.
Learned Workspace Facts
- Local checkout
t3PRHelpis the GitHub repoDevVig/microbridge(Tauri UI inapps/microbridge-ui, daemon incrates/microbridged). - Integrations split into community adapters (Cursor, Factory, T3 Code, OpenCode) and host-attributed/native hosts (Claude Code, Codex, Synara, CNVS); host-attributed names appear on sessions and may not get separate Integrations tiles.
- Claude reaches full control via FSEvents on
~/.claude/projectsjournals; Cursor historically used hooks-onlyingest_lifecycle(Limited)—ACP is the intended path toward Claude-parity. - Community adapter “Setup needed” / “Waiting” usually means hooks or the host app are not yet delivering lifecycle events, not only a UI selection bug.
- Release pipeline is tag-driven: GitHub Release (DMGs/tarballs) → Homebrew formula bump PR →
finalize-releasesmoke/promote; Intel finalize must usebrew services list --json(not pipe-to-awk/grep) to avoid Broken pipe flakes.
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 · 14 lines · 323 tokens per session scan A c93d5c1bd24d
microbridge AGENTS.md is an instructions file published in the GitHub repository DevVig/microbridge (27 stars, last pushed 9d ago), licensed MIT. It adds 323 tokens to every session, about $0.0013 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.
microbridge AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| microbridge AGENTS.mdDevVig/microbridge | Instructions file | 27 | 9d ago | MIT | A | 323 | 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 | yesterday | 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 |