goopspec: Instructions file for Codex

AGENTS.md

goopspec AGENTS.md is an instructions file for Codex, OpenCode from hffmnnj/goopspec. It costs 6,631 tokens per session, scanned A, original, MIT.

Repository instructions for the goopspec project, including how to build and check its OpenCode plugin. They also document the project layout and a known testing issue.

In plain words
What is it for?
Use them to install dependencies, build, type-check, lint, format, or run all, selected, changed, or watch-mode tests for the plugin.
Why use it?
They keep an agent aligned with the correct package commands and warn about a test-related problem that could otherwise lead to misleading results.

Instructions file for CodexOpenCode

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

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

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is import type { PluginContext } from "../../core/types.js";.

Reuse

Borrowing it

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

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 goopspec AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/hffmnnj/goopspec/agents-md"><img src="https://agentmods.dev/badge/instructions/hffmnnj/goopspec/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 6,631 This file is loaded in full into every session.
When invoked 6,631 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 $0.06631 $0.06631
Opus 5.5 $0.02652 $0.02652
Sonnet 5.5 $0.01326 $0.01326
Haiku 4.5 $0.00663 $0.00663

Measured 2mo ago against content hash a715dfa95996, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

goopspec 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 · 416 lines

How it starts

The opening of the file, as written. The whole thing — 416 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Guidelines for AI agents working in this codebase.

Build & Test Commands

bun install                                          # Install workspace dependencies
bun run --cwd packages/opencode-plugin build         # Build the plugin
bun run --cwd packages/opencode-plugin typecheck     # Type check the plugin
bun run --cwd packages/opencode-plugin test           # Run all plugin tests
bun run --cwd packages/opencode-plugin lint          # Run Biome lint on src
bun run --cwd packages/opencode-plugin lint:fix       # Fix Biome issues in src
bun run --cwd packages/opencode-plugin format        # Format src with Biome

# Testing
bun test packages/opencode-plugin/                   # Test plugin package
bun test packages/opencode-plugin/src/tools/goop-status/index.test.ts  # Single file
bun test -t "goop_status"                             # Tests matching name (regex)
bun test --changed=main                               # Only tests affected by git diff vs main (traces imports)
bun test --bail=3 --timeout=10000                     # Bounded run
bun test --watch                                      # Watch mode

⚠️ rtk test gotcha — HIGH severity

rtk bun test reports "0 passed / N skipped" for runs that actually execute thousands of tests. Only rtk proxy bun test ... is trustworthy. This caused real confusion during execution — a run that passed 1960 tests was reported as "0 passed / 44 skipped". Always use rtk proxy for test commands, never bare rtk.

Project Structure

packages/
└── opencode-plugin/       # @goopspec/opencode-plugin — MCP tools, hooks, and orchestration logic

packages/opencode-plugin/src/
├── core/                  # Types, config, resolver
├── tools/                 # MCP tool implementations
│   ├── goop-read-db/      # Read workflow docs from GoopSpecDB
│   ├── goop-write-db/     # Write/update workflow docs; auto-renders markdown sidecar
│   ├── goop-read-section/ # Read structured document sections
│   ├── goop-write-wave/   # Upsert wave/task progress rows
│   ├── goop-blocker/      # Open, resolve, and list workflow blockers
│   ├── goop-dashboard/    # Render cross-workflow dashboard
│   ├── goop-save-note/    # Save a Field Note to the global knowledge base
│   ├── goop-search-notes/ # Search Field Notes with FTS + tag filtering
│   └── ...                # Other tool directories
├── hooks/                 # OpenCode plugin hooks
├── features/              # Feature modules (memory, state, db, routing, model-routing)
│   └── db/                # GoopSpecDB — unified SQLite database (schema, migrations, types)
├── shared/                # Utilities (logger, paths)
├── test-utils.ts          # Shared test utilities
└── index.ts               # Plugin entry point

packages/opencode-plugin/
├── agents/                # 15 agent markdown definitions
├── commands/              # 9 slash command definitions
├── references/            # 19 consolidated reference documents (incl. field-notes-protocol)
└── templates/             # File templates

Read the full file on GitHub · 416 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 · 416 lines · 6,631 tokens per session scan A a715dfa95996

Subscribe to this mod's changes

goopspec AGENTS.md is an instructions file published in the GitHub repository hffmnnj/goopspec (52 stars, last pushed 2mo ago), licensed MIT. It adds 6,631 tokens to every session, about $0.0265 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.

Related

goopspec AGENTS.md compared with instructions from other repositories

goopspec AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
goopspec AGENTS.mdhffmnnj/goopspecInstructions file522mo agoMITA6,631Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, 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