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/copilot-instructionsgit 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 | $0.01027 | $0.01027 |
| Opus 5 | $0.00513 | $0.00513 |
| Sonnet 5 | $0.00205 | $0.00205 |
| Haiku 4.5 | $0.00103 | $0.00103 |
Grade A, and why
systematic copilot-instructions.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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot Instructions for Systematic
Read AGENTS.md at the repository root before writing any code. It is the canonical source for project structure, conventions, and command reference.
Stack
- Runtime: Bun (not Node.js, not Deno)
- Language: TypeScript 5.7+ with
strict: true - Modules: ESM only (
"type": "module"in package.json) - Linter: Biome — not ESLint, not Prettier
- Tests:
bun:testwithdescribe/it— not Jest, not Vitest - Package manager: Bun — not npm, not pnpm, not yarn
Verification Commands
Run these before marking work complete:
bun run build # Build to dist/
bun run typecheck # TypeScript strict mode
bun run lint # Biome linter
bun test # Unit and integration tests
All four must pass. Do not skip any.
Do / Don't
Imports
// ✅ Do: node: protocol for builtins
import { readFile } from 'node:fs/promises'
import { join } from 'node:path'
// ✅ Do: .js extension on relative imports (ESM requirement)
import { parseFrontmatter } from './frontmatter.js'
// ✅ Do: import type for type-only imports
import type { SkillConfig } from './types.js'
// ❌ Don't: bare builtin imports
import { readFile } from 'fs/promises'
// ❌ Don't: missing .js extension
import { parseFrontmatter } from './frontmatter'
Type Safety
// ✅ Do: unknown + type guards
function processInput(value: unknown): string {
if (typeof value !== 'string') {
throw new TypeError(`Expected string, got ${typeof value}`)
}
return value
}
// ✅ Do: explicit return types on exports
export function findSkills(dir: string): Promise<SkillDefinition[]> { ... }
// ❌ Don't: any, @ts-ignore, @ts-expect-error, non-null assertions (!)
function processInput(value: any) { ... }
// @ts-ignore
someCall()!
Architecture
// ✅ Do: functions — this codebase has zero classes
export function createHandler(config: Config): Handler { ... }
// ❌ Don't: classes
class Handler { ... }
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 · 142 lines · 1,027 tokens per session scan A dbfe83eeddf5
systematic copilot-instructions.md is an instructions file published in the GitHub repository marcusrbrown/systematic (24 stars, last pushed 3d ago), licensed MIT. It adds 1,027 tokens to every session, about $0.0051 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).