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.
npx agentmods add instructions/jonanderson10/enhanced-opencode-prompt-stack/agents-mdgit clone --depth 1 https://github.com/jonanderson10/enhanced-opencode-prompt-stackWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00576 | $0.00576 |
| Opus 5 | $0.00288 | $0.00288 |
| Sonnet 5 | $0.00115 | $0.00115 |
| Haiku 4.5 | $0.00058 | $0.00058 |
Grade A, and why
enhanced-opencode-prompt-stack 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.
How it starts
The opening of the file, as written. The whole thing — 29 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository: Enhanced OpenCode Prompt Stack
A model-agnostic prompt replacement for OpenCode's built-in build and plan agent prompts, paired with a workflow-layer AGENTS.md for safety, verification, git hygiene, and code quality. The stack is tightly coupled to OpenCode as a harness — it is not portable to other agent harnesses.
Repo Structure
src/prompts/custom.txt— shared base prompt for all models (replaces OpenCode'sgpt.txt,kimi.txt,anthropic.txt,default.txt)src/prompts/build-specific.txt— build-mode additionssrc/prompts/plan-specific.txt— plan-mode additionssrc/AGENTS.md— the distributed AGENTS.md that ships to users (copied to~/.config/opencode/AGENTS.mdor project root)docs/research.md— research sources and how they map to prompt filesREADME.md— canonical project documentation
Key Facts for Agents
- No build, test, lint, or CI pipeline. This repo is prompt and markdown content only. There are no automated checks to run.
src/AGENTS.mdis the product. Edits to it affect what all downstream users receive. Understand the three-layer architecture (base prompt, mode prompt, workflow instructions) before modifying it.- Verification is manual. After editing prompts, the user confirms with
opencode debug agent buildandopencode debug agent planto inspect resolved agent prompts. There is no script to run. - No code to typecheck or lint. The
.txtprompt files and.mdfiles have no automated format enforcement. Match the existing style: concise, direct, no fluff. - The global
AGENTS.mdat~/.config/opencode/AGENTS.mdmay differ fromsrc/AGENTS.md. The global one is the installed copy;src/AGENTS.mdis the source of truth for this repo. .claude/settings.local.jsonexists — Claude Code settings are present. Respect them.
Editing Conventions
- Prompt files (
src/prompts/*.txt) are terse and instruction-dense. Preserve that style. src/AGENTS.mdis structured in sections with horizontal rules. Add new rules within the appropriate section; don't create new top-level sections without reason.- When changing prompt behavior, consider all three files: the change may belong in
custom.txt(universal) or in a mode-specific file (build or plan only). README.mddocuments the architecture, installation, and rationale. Update it if your change alters how the system works.
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.
- 2d ago First seen · 29 lines · 576 tokens per session scan A bd57f12a2449
enhanced-opencode-prompt-stack AGENTS.md is an instructions file published in the GitHub repository jonanderson10/enhanced-opencode-prompt-stack (3 stars, last pushed 5d ago), licensed MIT. It adds 576 tokens to every session, about $0.0029 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 2026-08-31.
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.
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).
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.
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.
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).
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.