rosetta instruction-scopes.instructions.md

A set of rules for organizing instruction files used by coding agents. It keeps each file focused, limits which files a rule applies to, and points to one source for each rule.

In plain words
What is it for?
Use it when creating or editing AGENTS.md, CLAUDE.md, Copilot instruction files, or other agent guidance.
Why use it?
It prevents conflicting or repeated instructions and keeps shared agent guidance easier to maintain.

Instructions file for GitHub Copilot

Install

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.

agentmods
npx agentmods add instructions/tikoci/rosetta/instruction-scopes
Clone the repo
git clone --depth 1 https://github.com/tikoci/rosetta

Made for: GitHub Copilot.

Per session 184 This file is loaded in full into every session.
When invoked 184 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What 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.

ModelPer sessionOnce invoked
Fable 5 $0.00184 $0.00184
Opus 5 $0.00092 $0.00092
Sonnet 5 $0.00037 $0.00037
Haiku 4.5 $0.00018 $0.00018

Measured 2d ago against content hash 86a5bba42be3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

rosetta instruction-scopes.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.

.github/instructions/instruction-scopes.instructions.md · 14 lines

What it actually says

Instruction scopes

When adding or editing instruction or agent-entrypoint files:

  • Put one rule or one tightly related topic in each file.
  • Use the smallest honest applyTo scope; broad scopes are fine when the rule is genuinely broad.
  • Keep one normative home per rule. Other instruction files should point to it instead of copying the prose.
  • Prefer adding a new narrow file over inflating a generic router file.
  • Keep CLAUDE.md, AGENTS.md, and .github/copilot-instructions.md as thin routers, not competing rulebooks.
Changes

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.

  1. 2d ago First seen · 14 lines · 184 tokens per session scan A 86a5bba42be3

Subscribe to this mod's changes

rosetta instruction-scopes.instructions.md is an instructions file published in the GitHub repository tikoci/rosetta (43 stars, last pushed 16d ago), licensed MIT. It adds 184 tokens to every session, about $0.0009 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.