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/marcusrbrown/systematic/agents-mdgit clone --depth 1 https://github.com/marcusrbrown/systematicWhat 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 | $0.01528 | $0.01528 |
| Opus 5 | $0.00764 | $0.00764 |
| Sonnet 5 | $0.00306 | $0.00306 |
| Haiku 4.5 | $0.00153 | $0.00153 |
Grade A, and why
systematic 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 yesterday.
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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md - Coding Agent Guidelines for Systematic
Generated: 2026-05-01 | Commit: 2e9453a | Branch: main
Overview
Systematic is a plugin providing compound-engineering loops (brainstorm, plan, work, review) for OpenCode, Pi, and Claude Code. It ships as an npm package with two distinct parts: TypeScript source (src/) for plugin logic and bundled Markdown assets (skills/, agents/) for content. Full architectural detail lives in ARCHITECTURE.md; directory layout and where to add new code lives in STRUCTURE.md. This file covers contributor conventions, commands, and anti-patterns.
For Architecture Questions
| Question | Go to |
|---|---|
| How does the plugin work? | ARCHITECTURE.md |
| Which plugin hooks are registered? | ARCHITECTURE.md |
| What invariants must hold? | ARCHITECTURE.md |
| What is the config priority order? | ARCHITECTURE.md |
| Where do I put new code? | STRUCTURE.md |
| What does each directory contain? | STRUCTURE.md |
| What are the naming conventions? | STRUCTURE.md |
| What harnesses and compatibility evidence are verified? | HARNESSES.md |
| What conventions apply to my code? | This file (Conventions section below) |
| What patterns should I follow? | This file (Conventions + Anti-Patterns below) |
Before implementing features or diagnosing failures, search docs/solutions/ for related past solutions by frontmatter metadata and reuse verified patterns where they still apply.
Commands
bun install # Install deps
bun run build # Build to dist/
bun run typecheck # Type check (strict)
bun run lint # Biome linter
bun test tests/unit # Unit tests (60 files)
bun test tests/integration # Integration tests (11 files)
bun test # All tests
bun test --filter "pattern" # Filter tests
bun run docs:dev # Local docs site
bun run docs:build # Build docs (generates reference + builds Starlight)
bun run docs:generate # Sync reference content from bundled assets
bun run docs:verify # Run docs build the same way CI does (use before approving docs-framework dep bumps)
bun run registry:build # Build OCX registry
bun run registry:drift # Check registry source drift vs generated assets
bun run registry:validate # Validate registry without building
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.
- yesterday First seen · 86 lines · 1,528 tokens per session scan A 4cb2a6e90503
systematic AGENTS.md is an instructions file published in the GitHub repository marcusrbrown/systematic (24 stars, last pushed 2d ago), licensed MIT. It adds 1,528 tokens to every session, about $0.0076 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.
Other instructions, from other repositories
opencode.nvim AGENTS.md
Instructions for nickjvandyke/opencode.nvim, covering opencode.nvim — agent guide, what it is, entrypoints, config quirks and dependencies.
opencode-ensemble AGENTS.md
AGENTS.md instructions for hueyexe/opencode-ensemble, covering opencode-ensemble — agent guidelines, what this is, design context, users and brand personality.
ocx AGENTS.md
Instructions for kdcokenny/ocx, a project described as: OpenCode extension manager with portable, isolated profiles. Your setup, anywhere.
opencode-claude-memory AGENTS.md
Instructions for kuitos/opencode-claude-memory, covering agents.md, structure, where to look, critical coupling and conventions.
no-vibe CLAUDE.md
Instructions for rizukirr/no-vibe, covering claude.md, repo purpose, verification, architecture — parallel surfaces, one behavior and two data layers (easy to confuse).
no-vibe GEMINI.md
Instructions for rizukirr/no-vibe, covering no-vibe — gemini cli context, adaptation iron law (binding when .no-vibe/active exists), activation marker, session start status and turn response contract (binding for every reply while on).