agentmods.dev

agnt: Instructions file for Codex

AGENTS.md

agnt AGENTS.md is an instructions file for Codex, OpenCode from standardbeagle/agnt. It costs 2,352 tokens per session, scanned A, original, Apache-2.0.

A project guide for coding agents working on the agnt repository, a tool that lets AI agents interact with a web browser for debugging and visual feedback.

In plain words
What is it for?
Use it when an agent needs to install, run, debug, or change agnt while following the repository's instructions.
Why use it?
It gives the agent the project rules, layout, installation details, and available commands in one place.

Instructions file for CodexOpenCode

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

This is standardbeagle/agnt's own configuration. It tells Codex and OpenCode how to work on agnt 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 agnt configures →

not rated 22repo changed 5d ago A scan 2,352 tokens original Apache-2.0
View source ↗ standardbeagle/agnt dev.standardbeagle.com
Reuse

Borrowing it

Nothing to install: this file belongs to standardbeagle/agnt. 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/standardbeagle/agnt/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/standardbeagle/agnt

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 agnt AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/standardbeagle/agnt/agents-md"><img src="https://agentmods.dev/badge/instructions/standardbeagle/agnt/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,352 This file is loaded in full into every session.
When invoked 2,352 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 $0.02352 $0.02352
Opus 5.5 $0.00941 $0.00941
Sonnet 5.5 $0.00470 $0.00470
Haiku 4.5 $0.00235 $0.00235

Measured 5d ago against content hash 77a37f92b7a7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agnt 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 5d 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 · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

agnt

Gives AI coding agents browser superpowers: a daemon-backed reverse proxy, process manager, and PTY wrapper that bridge the agent and a real browser for debugging, wireframing, and visual feedback.

  • Repository: https://github.com/standardbeagle/agnt — version is managed by scripts/release.sh (never hand-edit version numbers).
  • One real binary, agnt (cmd/agnt). agnt-daemon is a copy used for daemon auto-start because sandboxes forbid self-exec; devtool-mcp is a legacy alias.
  • The Claude Code plugin lives in a separate marketplace repo; this repo ships the binary and MCP server only.

Build and test

Run tests through tman (or the repo shims) per the global standards.

make build            # agnt binary
make all              # build + the agnt-daemon copy
make vendor-check     # vendor/ must equal what go.mod resolves to (no make: `tman vendor-check`)
make install-local    # ~/.local/bin
make test             # default suite (host-safe; excludes procisolation/sshe2e/chromee2e tags)
make test-pkg PKG=./internal/incident RUN=TestBus   # focused, serial; PKG/RUN both optional
make bench PKG=./internal/incident BENCH=Bus_EndToEnd COUNT=5   # -run '^$', -benchmem; no ordinary tests
make test-isolated    # procisolation tests inside a PID namespace (Linux)
make test-ssh         # SSH harness + containerized sshd smoke (loud skip without Docker/Podman)
make test-chrome-e2e  # real-Chrome tests — unloaded machine only, never alongside other runs
make test-js          # vitest + jsdom tier for injected scripts (loud skip without npm); JSFILTER=name narrows, npm ci runs only when the lockfile changed
make cross-compile-check   # windows/amd64 + darwin/arm64 build (no make: `tman cross-compile-check`)
make install-hooks    # once per clone: core.hooksPath=.githooks
  • Full-suite gate is go test -p 1 ./... (serial packages). Parallel ./... fails on cross-package port contention, not product bugs. CI runs it with go vet ./... and make vendor-check on every push and pull request (.github/workflows/test-linux.yml).
  • The pre-commit hook (.githooks/pre-commit) runs gofmt, go vet, and go test -race -p 1 on staged packages and blocks on failure. --no-verify is allowed in exactly two cases — see .claude/rules/testing-parallel-package-flakes.md § Sanctioned --no-verify cases.
  • Tests that start real OS processes must not use t.Parallel().
  • Daemon tests use NewForTest, never Start().

Read the full file on GitHub · 101 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. 5d ago Changed · +2 lines · +125 tokens per session 77a37f92b7a7
  2. 11d ago Changed · +2 lines · +77 tokens per session a41e28bee873
  3. 14d ago Changed · +5 lines · +567 tokens per session c35d6ccf7e22
  4. 1mo ago Changed · -185 lines · -4,924 tokens per session a6b16e6275fb
  5. 1mo ago Changed · +1 lines · +95 tokens per session 364a6115804a
  6. 1mo ago Changed · +5 lines · +449 tokens per session 7f4bf17ba1a8
  7. 1mo ago First seen · 271 lines · 5,963 tokens per session scan A 085b22a21f1a

Subscribe to this mod's changes

agnt AGENTS.md is an instructions file published in the GitHub repository standardbeagle/agnt (22 stars, last pushed today), licensed Apache-2.0. It adds 2,352 tokens to every session, about $0.0094 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.

Claude CodeGoai-agentsbrowser-debuggingdeveloper-toolsmcp
Related

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).

microsoft/vscode · 9,715 tokens

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.

vercel/next.js · 7,461 tokens

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).

microsoft/vscode · 5,262 tokens

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.

langchain-ai/langchain · 4,680 tokens

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).

microsoft/vscode · 2,731 tokens

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.

deepseek-ai/deepseek-harness · 4,261 tokens