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/exmergo/dex/copilot-instructionsgit clone --depth 1 https://github.com/exmergo/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 | $0.00157 | $0.00157 |
| Opus 5 | $0.00078 | $0.00078 |
| Sonnet 5 | $0.00031 | $0.00031 |
| Haiku 4.5 | $0.00016 | $0.00016 |
Grade A, and why
dex 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.
What it actually says
dex: drive the engine via its command contract
Follow AGENTS.md at the repository root.
In short: dex's logic lives in the exmergo-dex-core engine. Drive it by running
uv run python -m exmergo_dex_core <subcommand>, read the single JSON envelope it
prints, and decide the next step. Never re-implement the engine in instructions.
The guardrails (read-only against data, writes confined to the repo as diffs,
dev-target-only builds, cost surfaced before spend, no credentials or raw rows in
context, PII flagged not surfaced) are enforced in the engine. See AGENTS.md for
the full command surface and envelope spec.
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 · 12 lines · 157 tokens per session scan A 0895c4f7afac
dex copilot-instructions.md is an instructions file published in the GitHub repository exmergo/dex (24 stars, last pushed 2d ago), licensed Apache-2.0. It adds 157 tokens to every session, about $0.0008 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
tuva-core AGENTS.md
Instructions for tuva-health/tuva-core, covering tuva core agent operating manual, tuva core 1.0 contract, repository boundaries, architecture and public-contract rules and extension columns.
strata-oss AGENTS.md
AGENTS.md instructions for G-Schumacher44/strata-oss, covering strata agent rules, collaboration model, the conductor loop, authority order and required reading (start here).
InvestSkill GEMINI.md
Instructions for yennanliu/InvestSkill, covering investskill — gemini cli setup & usage guide, installation & setup, quick start, navigate to the investskill directory and start gemini cli (loads gemini.md automatically).
she-love-me CLAUDE.md
Instructions for 863401402/she-love-me, covering claude.md and 唯一工作流.
wayland-core copilot-instructions.md
Instructions for FerroxLabs/wayland-core, covering ijfw rules, output discipline, memory routing, context discipline and cross-audit.
ZipAgent AGENTS.md
Instructions for JiayuXu0/ZipAgent, covering repository guidelines, project structure & module organization, build, test & development commands, coding style & naming conventions and testing guidelines.