Borrowing it
Nothing to install: this file belongs to maximyz3d/relaybridge. 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/maximyz3d/relaybridge/main/AGENTS.mdgit clone --depth 1 https://github.com/maximyz3d/relaybridgeWrote 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/maximyz3d/relaybridge/agents-md)<a href="https://agentmods.dev/instructions/maximyz3d/relaybridge/agents-md"><img src="https://agentmods.dev/badge/instructions/maximyz3d/relaybridge/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/maximyz3d/relaybridge/agents-md"><img src="https://agentmods.dev/badge/instructions/maximyz3d/relaybridge/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 | $0.01966 | $0.01966 |
| Opus 5.5 | $0.00786 | $0.00786 |
| Sonnet 5.5 | $0.00393 | $0.00393 |
| Haiku 4.5 | $0.00197 | $0.00197 |
Grade B, and why
relaybridge AGENTS.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 1mo 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.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
`start_safe_session(kind:"powershell")` opens a real host PowerShell process. `send_session_input` can execute arbitrary commands under the user's account after host approval. RelayBridge is not a filesystem sandbox. How it starts
The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RelayBridge Agent Guide
This repository contains RelayBridge, a local Windows PowerShell and AI CLI control plane with browser, REST, and MCP interfaces.
First Call
When connected through MCP, call get_context_bundle first. It returns the bounded handoff packet: health, provider readiness, active work, terminal tails, collaborations, projects, runs, receipts, registry fingerprints, and exact follow-up tools for omitted detail.
Codex-Claude Pipeline
Explicit user provider restrictions take precedence over the default phase
roles below. When the user selects only Codex Astra/ultra, create the existing
workflow with profile:"codex-astra-ultra". Its persisted policy dispatches
only read-only Codex/Astra/ultra advisors; unavailable Codex fails closed.
Codex holds implementation and revision leases externally. Use
claim_pipeline_revision and complete_pipeline_revision for corrections,
then the existing fresh final-review action. Never call a Claude-only fallback
or relabel Codex evidence as a Claude verdict. Older installations that lack
this profile require an explicit Codex-only external workflow; do not send an
unsupported selector and assume it was enforced.
Codex is the orchestrator and primary implementation writer. Use the
$codex-claude-pipeline skill for cross-agent work:
- Codex records a bounded research brief.
- A fresh read-only Claude planner returns the implementation plan.
- Codex alone implements the accepted plan.
- A fresh read-only Claude reviewer reports prioritized findings.
- When review requests changes, the Claude Sonnet reviser may write only after Codex releases and explicitly transfers the single writer lease.
- A fresh Claude Sonnet/high final review is the closing review gate. A read-only Codex verifier may supply focused supplementary evidence.
Never run overlapping writers in the same canonical workspace or duplicate an active task. Independent read-only discovery and provider calls may run in parallel across clients, including multiple Claude or Codex instances. Parallel writers must use separate workspaces/worktrees with their own writer leases. Return compact summaries instead of raw transcripts. Keep each handoff bound to the run/request/receipt identifiers, file scope, base revision, decisions, risks, and acceptance evidence. Start a fresh session at plan and review boundaries; compact a continuing coordination thread around 60–70% context use.
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.
- 1mo ago Changed · +9 lines · +94 tokens per session 4743a6b06641
- 1mo ago Changed · +11 lines · +147 tokens per session 454ceddd4826
- 1mo ago Changed · +96 lines · +1,187 tokens per session d177650a8b25
- 2mo ago First seen · 68 lines · 538 tokens per session scan B 2d3634a0e82a
relaybridge AGENTS.md is an instructions file published in the GitHub repository maximyz3d/relaybridge (0 stars, last pushed 9d ago), licensed MIT. It adds 1,966 tokens to every session, about $0.0079 per session on Opus 5.5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
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).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.