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/dcramer/dex/agents-mdgit clone --depth 1 https://github.com/dcramer/dexWhat 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 | $0.00482 | $0.00482 |
| Opus 5 | $0.00241 | $0.00241 |
| Sonnet 5 | $0.00096 | $0.00096 |
| Haiku 4.5 | $0.00048 | $0.00048 |
Grade A, and why
dex 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.
What it actually says
Agent Instructions
Package Manager
Use pnpm: pnpm install, pnpm build, pnpm test
Commit Attribution
AI commits MUST include:
Co-Authored-By: <model name> <[email protected]>
Example: Co-Authored-By: Claude Sonnet 4 <[email protected]>
Architecture
src/
├── index.ts # Entry: routes to CLI or MCP
├── types.ts # Zod schemas
├── core/ # Storage + TaskService
├── tools/ # MCP tool handlers
├── mcp/server.ts # MCP server
└── cli/commands.ts # CLI handlers
Storage
JSONL format: .dex/tasks.jsonl (one task per line, auto-migrates from old formats)
Task Management
Use dex skill for task coordination. See plugins/dex/skills/dex/SKILL.md
Task Planning
Use dex-plan skill for creating tasks from planning docs. See plugins/dex/skills/dex-plan/SKILL.md
Local Development
pnpm install && pnpm build && pnpm link # Setup
pnpm build # Rebuild after changes
pnpm dev # Watch mode
pnpm unlink # Cleanup
Documentation
When adding or modifying CLI commands, update:
src/cli/help.ts— Built-in help textdocs/src/pages/cli.astro— CLI reference documentation
TypeScript Exports
Use export type for type-only exports (interfaces, type aliases). Bun requires explicit type exports:
// Good
export type { GitHubRepo } from "./remote.js";
export { getGitHubRepo } from "./remote.js";
// Bad - fails in Bun
export { GitHubRepo, getGitHubRepo } from "./remote.js";
Testing
When adding new behavior or modifying existing functionality, review TESTING.md to determine if tests are needed. Key points:
- Test error cases users will actually hit
- Add regression tests for bugs
- Co-locate tests with source (
foo.ts→foo.test.ts)
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 · 77 lines · 482 tokens per session scan A c735a4da9336
dex AGENTS.md is an instructions file published in the GitHub repository dcramer/dex (377 stars, last pushed 6mo ago), licensed MIT. It adds 482 tokens to every session, about $0.0024 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
plannotator AGENTS.md
Instructions for backnotprop/plannotator, covering plannotator, project structure, server runtimes, installation and environment variables.
solo AGENTS.md
Instructions for solo-agent/solo, covering project testing rules and project service lifecycle rules.
superset AGENTS.md
AGENTS.md instructions for superset-sh/superset, covering superset monorepo, project structure, exception: shadcn/ui components, database and releases.
untether GEMINI.md
Instructions for littlebearapps/untether, covering untether — gemini instructions, stack & conventions, architecture, key rules and testing.
agent-tools AGENTS.md
Instructions for kairyou/agent-tools, covering agent instructions, build and test, layout, settled decisions and docs.
awesome-copilot-id AGENTS.md
Instructions for GulajavaMinistudio/awesome-copilot-id, covering communication, explanation and documentation, markdown formatting, user communication style and workflow & methodology.