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/orangeproai/orangepro-mcp/vscodegit clone --depth 1 https://github.com/OrangeproAI/orangepro-mcpWrote 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/agents/orangeproai/orangepro-mcp/vscode)<a href="https://agentmods.dev/agents/orangeproai/orangepro-mcp/vscode"><img src="https://agentmods.dev/badge/agents/orangeproai/orangepro-mcp/vscode.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 | $0.00000 | $0.00278 |
| Opus 5 | $0.00000 | $0.00139 |
| Sonnet 5 | $0.00000 | $0.00056 |
| Haiku 4.5 | $0.00000 | $0.00028 |
Grade A, and why
vscode 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.
What it actually says
OrangePro With VS Code / Copilot
Install
npm install -g @orangepro/orangepro-mcp
cd /path/to/your/repo
opro
opro writes .orangepro/behavior-coverage.html, .orangepro/rtm.md, and next actions. With a configured provider key, weak AI grounding and AI-suggested candidate flows run automatically and stay out of Proven coverage.
MCP Setup
Add OrangePro as an MCP server in your user or workspace MCP config:
{
"servers": {
"orangepro-local": {
"command": "npx",
"args": ["-y", "@orangepro/mcp-server@latest", "mcp"]
}
}
}
Do not hardcode provider keys in a committed workspace config. Prefer your shell environment, .env.provider.local, .env.local, .env, or opro setup.
Agent Prompt
Use OrangePro first. Call orangepro_start for this repo, then follow next_actions. Generate tests with orangepro_generate_tests, write only runnable outputs with run_hints, run the suggested command, and call `orangepro_prove` with the returned `prove_run` args after a pass for Dynamically Proven. Use record_run only for static diagnostics.
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 · 35 lines · 0 tokens per session scan A 95d269ebf18a
vscode is an agent published in the GitHub repository OrangeproAI/orangepro-mcp (17 stars, last pushed 7d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 278 tokens. 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 agents, from other repositories
ci-medic
Runs the ci-settle loop (formula convergence, step X3) — watches CI checks, triages bot comments, fixes real findings or declines with a stated reason, regenerates generated artifacts. No merge authority.
seneschal
The project's strategic pairing agent (Yegge's Seneschal). Nick invokes it inside this repo, one task at a time, for design/strategy work — docs IA, website design system, architecture decisions, roadmap shaping. It does not implement; its deliverables are specs/ADRs/issues fed into the queue.
ux-designer
For website changes, owns the "spec" phase as a design spec — information architecture, wireframe/description of the change, interaction notes. Gate 1 approves design, not prose. Persona frontend-ux.
debugger
Debugs errors, test failures, and unexpected behavior. Knows PromptScript architecture.
speckit.implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
speckit.analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.