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/krzysztofsurdy/code-virtuoso/agents-mdgit clone --depth 1 https://github.com/krzysztofsurdy/code-virtuosoWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/krzysztofsurdy/code-virtuoso/agents-md)<a href="https://agentmods.dev/instructions/krzysztofsurdy/code-virtuoso/agents-md"><img src="https://agentmods.dev/badge/instructions/krzysztofsurdy/code-virtuoso/agents-md.svg" alt="Measured on agentmods" height="20"></a>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 5.1 | $0.03039 | $0.03039 |
| Opus 5 | $0.01520 | $0.01520 |
| Sonnet 5 | $0.00608 | $0.00608 |
| Haiku 4.5 | $0.00304 | $0.00304 |
Grade A, and why
code-virtuoso 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 6d 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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agents
@CONTRIBUTING.md
Agents are sub-agents - standalone markdown files that define a specialized role, its allowed tools, and its system prompt. Each agent file contains YAML frontmatter for configuration and a markdown body that serves as the agent's system prompt.
Where skills provide reference knowledge (patterns, checklists, component docs), agents are the actors that use that knowledge to perform work. A skill is a book on the shelf; an agent is the specialist who reads the book and applies it. Delegate to an agent when a task is well-scoped enough that a focused sub-agent will do it better than the orchestrating model switching context mid-conversation.
Architecture
Agents follow a two-tier model:
Specialist agents handle a single, repeatable task type. They are typically read-only, stateless, and operate on whatever the caller hands them. Think of them as focused tools: investigate this, review that, scan for smells.
Role agents embody a team position. They carry a broader mandate, preload relevant skills, and some maintain persistent project-level memory across sessions. They own a domain ("the what", "the how", "the when") rather than a single task.
| Aspect | Specialist | Role |
|---|---|---|
| Scope | Single task type | Entire domain of responsibility |
| Skills | 1-4 relevant knowledge skills | Role skill + relevant knowledge skills |
| Memory | Stateless | Some use persistent memory for cross-session context |
| File modification | Mostly read-only (except Doc Writer and Implementer) | Dev roles (Backend, Frontend) write code; others are read-only |
| Isolation | Implementer uses worktree; others run in-place | Backend Dev and Frontend Dev use worktree; others run in-place |
Specialist Agents
| Agent | Tools | Isolation | Purpose |
|---|---|---|---|
| Investigator | File reading, code search, shell | - | Deep codebase exploration, dependency mapping |
| Implementer | All | worktree | TDD red-green-refactor execution |
| Reviewer | File reading, code search, shell | - | Structured code review (SOLID, OWASP, smells) |
| Refactor Scout | File reading, code search, shell | - | Code smell scanning, complexity hotspots |
| Dependency Auditor | Shell, file reading, code search | - | CVE checks, outdated packages, license audit |
| Doc Writer | File reading, code search, shell, file editing | - | Changelogs, API docs, migration guides |
| Migration Planner | File reading, code search, shell | - | Migration safety analysis, rollback paths |
| Test Gap Analyzer | File reading, code search, shell | - | Missing test coverage, untested edge cases |
| Cold Reviewer | File reading, code search, shell | - | Zero-context code review, fresh-eyes findings |
| Acceptance Verifier | File reading, code search, shell | - | Spec compliance checking, criteria coverage matrix |
| Readiness Checker | File reading, code search, shell | - | Pre-implementation readiness gate, requirements traceability |
| Course Corrector | File reading, code search, shell | - | Mid-workflow change impact analysis, change proposals |
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.
- 6d ago First seen · 177 lines · 3,039 tokens per session scan A ab6ec0d6dc8e
code-virtuoso AGENTS.md is an instructions file published in the GitHub repository krzysztofsurdy/code-virtuoso (20 stars, last pushed 3mo ago), licensed MIT. It adds 3,039 tokens to every session, about $0.0152 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
claude-plugins CLAUDE.md
Instructions for tomoking2004/claude-plugins: Claude Code プラグインのマーケットプレイス．構成・導入・開発規約は README.md，美の基準は plugins/refine/BEAUTY.md を参照し，全ての成果物に適用する．.
claude-multiagent-catalogue CLAUDE.md
Claude Code instructions for asleekgeek/claude-multiagent-catalogue, covering claude.md, what this repository is, scope note: repo name is legacy, common commands and list everything available across all buckets.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.