What is rosetta AGENTS.md?

A guide for coding agents working in the Rosetta software project. It tells them which project documents to read and where to find rules about design, operations, issues and code changes.

Orienting an agent before non-trivial work, routing questions to the right documentation, following GitHub issue and pull request rules, and finding project-specific skills.

It prevents agents from missing important project context or putting work in the wrong place.

rosetta AGENTS.md — Instructions file by tikoci

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/agents-md

Clone the repo

git clone --depth 1 https://github.com/tikoci/rosetta

Made for: Codex, OpenCode.

Per session 595 This file is loaded in full into every session.

When invoked 595 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.

Model	Per session	Once invoked
Fable 5	$0.00595	$0.00595
Opus 5	$0.00298	$0.00298
Sonnet 5	$0.00119	$0.00119
Haiku 4.5	$0.00060	$0.00060

Measured 3d ago against content hash fafcb40d5c5f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

rosetta 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 3d 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.

AGENTS.md · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codex instructions for rosetta

Codex reads this file as the repo-local entrypoint. Keep it short. The canonical project orientation remains CLAUDE.md; durable rationale lives in DESIGN.md; operator/reference material lives in MANUAL.md; narrow normative rules live in .github/instructions/*.instructions.md.

First reads

Read CLAUDE.md before non-trivial work. It is the routing index for the repo.
Read DESIGN.md when touching retrieval, MCP/TUI behavior, data sources, extraction, skills, command validation, or Docusaurus migration work.
Read .github/copilot-instructions.md as the peer short routing note for Copilot, but do not duplicate its rules here.
Manually read the matching .github/instructions/*.instructions.md files. Codex does not get Copilot's applyTo selection automatically.
Active work is tracked in GitHub Issues (agent-ready / umbrella / blocked labels); PRs close issues via Closes #N — read .github/instructions/issue-pr-linking.instructions.md. tasks/ is a frozen archive (see tasks/README.md); briefing rules are in briefings/README.md.
Repo-local skills live in .github/skills/*/SKILL.md (symlinked into .claude/skills/ for Claude Code); read the relevant file when a user asks for that workflow, such as picking the next issue, promoting an idea, re-extracting, verifying acceptance criteria, or gating a PR's review threads before claiming it's mergeable.

Development defaults

Rosetta is Bun + TypeScript. Prefer bun, bun test, and make verify where applicable; do not swap in Node/npm-oriented substitutes.
MCP, query, classifier, TUI, and canonicalizer behavior should route through shared core code, usually src/query.ts, with src/mcp.ts and src/browse.ts kept as thin adapters.
Rosetta is read-only documentation/schema context. It does not connect to or modify a user's router.
Community RouterOS skills are supplemental, not official MikroTik docs; keep the attribution boundary visible when they surface.

Read the full file on GitHub · 46 lines

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.

3d ago First seen · 46 lines · 595 tokens per session scan A fafcb40d5c5f

Subscribe to this mod's changes

rosetta AGENTS.md is an instructions file published in the GitHub repository tikoci/rosetta (43 stars, last pushed 16d ago), licensed MIT. It adds 595 tokens to every session, about $0.0030 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.

ai bun claude-code copilot mcp mcp-server

rosetta AGENTS.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Codex instructions for rosetta

First reads

Development defaults

What this file has done since we first saw it

Other instructions, from other repositories

bun-mcp copilot-instructions.md

memorix GEMINI.md

calc-mcp CLAUDE.md

mcp-security-scanner CLAUDE.md

relay AGENTS.md

copilot-mcp CLAUDE.md