agentmods.dev

grokbridge: Instructions file for Codex

AGENTS.md

grokbridge AGENTS.md is an instructions file for Codex, OpenCode from naplesblue/grokbridge. It costs 532 tokens per session, scanned A, original, Apache-2.0.

A repository guide for coding agents working on the naplesblue/grokbridge project. It explains the project's folders, commands, coding rules, and tests.

In plain words
What is it for?
Use it when changing the MCP server, running tests or builds, updating versions, or maintaining the project's plugin and configuration files.
Why use it?
Without these instructions, an agent may use the wrong command, edit the wrong area, or miss project-specific checks.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions Codex.

This is naplesblue/grokbridge's own configuration. It tells Codex and OpenCode how to work on grokbridge itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything grokbridge configures →

not rated 3repo 3mo ago A scan 532 tokens original Apache-2.0
View source ↗ naplesblue/grokbridge
Reuse

Borrowing it

Nothing to install: this file belongs to naplesblue/grokbridge. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/naplesblue/grokbridge/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/naplesblue/grokbridge

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for grokbridge AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/naplesblue/grokbridge/agents-md/github.svg)](https://agentmods.dev/instructions/naplesblue/grokbridge/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/naplesblue/grokbridge/agents-md"><img src="https://agentmods.dev/badge/instructions/naplesblue/grokbridge/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.

agentmods 80×15 button for grokbridge AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/naplesblue/grokbridge/agents-md"><img src="https://agentmods.dev/badge/instructions/naplesblue/grokbridge/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 532 This file is loaded in full into every session.
When invoked 532 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00532 $0.00532
Opus 5.5 $0.00213 $0.00213
Sonnet 5.5 $0.00106 $0.00106
Haiku 4.5 $0.00053 $0.00053

Measured 2mo ago against content hash 66285de361cf, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

grokbridge 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.

AGENTS.md · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository guidelines

Guidance for coding agents working in this repository.

Project structure

  • mcp-server/src/ — the MCP server. server.mjs registers tools and runs the stdio transport; tools/ holds one file per tool plus shared execution helpers; lib/ holds the engine (Grok CLI wrapper, job state, Git context, prompts, process control, xAI fallback). dev-runner.mjs and worker.mjs drive tools outside Codex.
  • tests/ — node --test suites and the fake-grok fixture.
  • scripts/ — version tooling (bump-version.mjs).
  • .codex-plugin/ and .mcp.json — Codex plugin packaging; dev/ — local dev install and config snippets.

Commands

  • npm test — run the test suites.
  • npm run build — tsc type-check (JSDoc types, no emit).
  • npm run bump-version / npm run check-version — keep the coupled version strings in sync.

Style

  • ESM .mjs with JSDoc types. Type-check must pass; no any.
  • No runtime dependencies beyond @modelcontextprotocol/sdk and zod.
  • Lowercase-hyphen filenames. Keep tool input schemas as zod objects.

Testing

  • Tests are tests/*.test.mjs, run with node --test.
  • Use the fake-grok fixture to stub Grok CLI interactions. Never hit the network except localhost stubs.
  • Cover job lifecycle, fallback triggers, and the write gate when touching those paths.

Safety invariants

These must never regress:

  • Job success is read from Grok's stopReason (EndTurn = clean), never from exit codes.
  • Write mode stays double-gated: GROK_BUILD_ALLOW_WRITE=true and per-call write: true.
  • The xAI API fallback is read-only and opt-in; it is never used for write tasks.
  • always_approve rule-allows Bash wholesale for a write run (needed for headless jobs, since grok cancels at the first un-rule-allowed permission prompt). The WRITE_DENIES rules must always take precedence over that allowance, so rm/mv/cp and Git-write commands stay denied and the workspace sandbox still bounds execution.

Read the full file on GitHub · 46 lines

Changes

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.

  1. 2mo ago First seen · 46 lines · 532 tokens per session scan A 66285de361cf

Subscribe to this mod's changes

grokbridge AGENTS.md is an instructions file published in the GitHub repository naplesblue/grokbridge (3 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 532 tokens to every session, about $0.0021 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.

Related

grokbridge AGENTS.md compared with instructions from other repositories

grokbridge AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
grokbridge AGENTS.mdnaplesblue/grokbridgeInstructions file33mo agoApache-2.0A532Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode