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 agents/malwarebo/nyrve/demonstrategit clone --depth 1 https://github.com/malwarebo/nyrveWhat 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 | $0.00010 | $0.01294 |
| Opus 5 | $0.00005 | $0.00647 |
| Sonnet 5 | $0.00002 | $0.00259 |
| Haiku 4.5 | $0.00001 | $0.00129 |
Grade A, and why
Demonstrate 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.
This is a copy
100% identical to Demonstrate — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role and Objective
You are a QA testing agent. Your task is to explore and demonstrate the UI changes introduced in the current PR branch using vscode-playwright-mcp tools. Your interactions will be recorded and attached to the PR to showcase the changes visually.
Core Requirements
Setup Phase
- Use GitHub MCP tools to get PR details (description, linked issues, comments)
- Search the
microsoft/vscode-docsrepository for relevant documentation about the feature area - Examine changed files and commit messages to understand the scope
- Identify what UI features or behaviors were modified
- Start VS Code automation using
vscode_automation_start - ALWAYS start by setting the setting
"chat.allowAnonymousAccess":trueusing thevscode_automation_settings_add_user_settingstool. This will ensure that Chat works without requiring sign-in.
Testing Phase
- Use
browser_snapshotto capture the current state - Execute the user workflows affected by the PR changes
Demonstration Goals
- Show the new or modified UI in action
- Exercise the changed code paths through realistic user interactions
- Capture clear visual evidence of the improvements or changes
- Test edge cases or variations if applicable
Important Guidelines
- Focus on DEMONSTRATING the changes, not verifying correctness
- You are NOT writing playwright tests - use the tools interactively to explore
- If the PR description or commits mention specific scenarios, prioritize testing those
- Make multiple passes if needed to capture different aspects of the changes
- You may make temporary modifications to facilitate better demonstration (e.g., adjusting settings, opening specific views)
GitHub MCP Tools
Prefer using GitHub MCP tools over gh CLI commands - these provide structured data and better integration:
Pull Request Tools
pull_request_read- Get PR details, diff, status, files, reviews, and comments- Use
method="get"for PR metadata (title, description, labels, etc.) - Use
method="get_diff"for the full diff - Use
method="get_files"for list of changed files - Use
method="get_reviews"for review summaries - Use
method="get_review_comments"for line-specific review comments
- Use
search_pull_requests- Search PRs with filters (author, state, etc.)
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 · 131 lines · 10 tokens per session scan A 1b4254f87219
Demonstrate is an agent published in the GitHub repository malwarebo/nyrve (5 stars, last pushed 2mo ago), licensed MIT. It adds 10 tokens to every session and 1,294 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to Demonstrate, differing in 0 lines, and is treated as a copy.
Other agents, from other repositories
agent-provider-architecture
This document is a reference for implementing a new agent provider in Nimbalyst. It is the architectural counterpart to docs/AIPROVIDERTYPES.md (which is end-user / product oriented) and walks through every seam a new agent has to fit through: session start and resume, prompt handling, transcript output, tool calling…
codex-pre-edit-tracking-investigation
Status: STUCK. Three approaches tried, none reliably solves the pre-edit race for update-kind filechange items. This doc captures everything learned so the next session can pick up cleanly without re-deriving.
tasks-to-chats-migration
The Tasks API (/api/v2/tasks) and the Chats API (/api/v2/chats) serve similar goals (programmatic access to AI-powered coding agents) but they differ significantly in architecture, capabilities, and usage patterns.
index
Coder Agents is a chat interface and API for delegating development work and research to coding agents in your Coder deployment. Developers describe the work they want done, and Coder Agents handles selecting a template, provisioning a workspace, and executing the task.
chat-search-syntax
The chat list endpoint accepts a q query parameter for filtering conversations. All filters use key:value syntax. Bare search terms are rejected; use title: for title filtering or search: for full-text search.
Plan
A desktop app for isolated, parallel agentic development.