goopspec AGENTS.md

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

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/hffmnnj/goopspec/agents-md
Clone the repo
git clone --depth 1 https://github.com/hffmnnj/goopspec

Made for: Codex, OpenCode.

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. Scan, not verified.
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 $0.06631 $0.06631
Opus 5 $0.03315 $0.03315
Sonnet 5 $0.01326 $0.01326
Haiku 4.5 $0.00663 $0.00663

Measured 2d ago against content hash a715dfa95996, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 2d 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. 2d 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 (46 stars, last pushed 20d ago), licensed MIT. It adds 6,631 tokens to every session, about $0.0332 per session on Opus 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

Other instructions, from other repositories

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

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 · 6,785 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 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 · 4,345 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, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

next.js 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 · 7,296 tokens