glidemq: Instructions file for Codex

AGENTS.md

glidemq AGENTS.md is an instructions file for Codex, OpenCode from agent-sh/glidemq. It costs 508 tokens per session, scanned A, a copy of agentsys CLAUDE.md, Apache-2.0.

Project-wide instructions for using glide-mq, a message-queue library that lets applications process jobs in the background. They cover available migration skills, coding priorities, model choices, and required checks.

In plain words
What is it for?
Use them when developing or migrating glide-mq applications, especially when deciding which migration skill or validation steps to apply.
Why use it?
They give the coding agent consistent rules for working on glide-mq projects, including testing, pull requests, hooks, and reporting failures.

Instructions file for CodexOpenCode

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

This is agent-sh/glidemq's own configuration. It tells Codex and OpenCode how to work on glidemq 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 glidemq configures →

Reuse

Borrowing it

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

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 glidemq AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/agent-sh/glidemq/agents-md"><img src="https://agentmods.dev/badge/instructions/agent-sh/glidemq/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 508 This file is loaded in full into every session.
When invoked 508 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 86% copy Near-identical to another mod 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 $0.00508 $0.00508
Opus 5.5 $0.00203 $0.00203
Sonnet 5.5 $0.00102 $0.00102
Haiku 4.5 $0.00051 $0.00051

Measured 16d ago against content hash dd168aaff63f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

glidemq 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 16d 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.

Origin

This is a copy

86% identical to agentsys CLAUDE.md — 13 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

AGENTS.md · 31 lines

What it actually says

glidemq

This repo is the glidemq plugin: glide-mq message queue skills for greenfield development and for migration from BullMQ or Bee-Queue. Part of the agentsys ecosystem; skills follow https://agentskills.io.

Vendored skills

The three skills (glide-mq, glide-mq-migrate-bullmq, glide-mq-migrate-bee) and their references/ are copied from avifenesh/glide-mq skills/, and the root LICENSE from that repo's root LICENSE. Upstream is the source of truth. Change them upstream and re-sync with ./scripts/sync-upstream.sh [ref], because the next sync overwrites local edits. skills/UPSTREAM.md records the pinned commit and explains the sync and the weekly drift check (scripts/check-upstream-drift.sh). This repo owns AGENTS.md, skills/UPSTREAM.md, scripts/, .github/ and the package metadata.

Rules

  • Output is plain text: no emojis or ASCII art. Status markers are [OK], [ERROR], [WARN], [CRITICAL].
  • Commit only product files. Summaries, plans and audit notes belong in the PR or the conversation.
  • A change is done when its checks pass; a script fix comes with a check that covers it.
  • Non-trivial changes go through a PR, not a direct push to main. Run the git hooks; do not bypass them.
  • In prose use - (single dash with spaces), not --.
  • If a script fails, report the failure before doing the step by hand, so broken tooling gets fixed.
  • Priorities, in order: plugin users' experience, automation that needs no babysitting, token efficiency, output quality, simplicity.

Checks

npm test                          # script syntax, link regression and standalone skill links
./scripts/check-upstream-drift.sh # 0 up to date or pending, 1 drift, 2 error
agnix .                           # agent config lint

References

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. 16d ago Changed · +2 tokens per session dd168aaff63f
  2. 1mo ago Changed · -28 lines · +7 tokens per session 793f98b2a037
  3. 1mo ago Changed · +9 lines · +85 tokens per session 8d4e300b4b4f
  4. 2mo ago First seen · 50 lines · 414 tokens per session scan A 1d646414dae2

Subscribe to this mod's changes

glidemq AGENTS.md is an instructions file published in the GitHub repository agent-sh/glidemq (3 stars, last pushed 9d ago), licensed Apache-2.0. It adds 508 tokens to every session, about $0.0020 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 86% identical to agentsys CLAUDE.md, differing in 13 lines, and is treated as a copy.

Related

glidemq AGENTS.md compared with instructions from other repositories

glidemq AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
glidemq AGENTS.mdagent-sh/glidemqInstructions file39d agoApache-2.0A508Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,649GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode ai-customization.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA1,907GitHub Copilot