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/aphrody-code/bxc/bxc-mcp-authorgit clone --depth 1 https://github.com/aphrody-code/bxcWhat 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 | $0.00078 | $0.00379 |
| Opus 5 | $0.00039 | $0.00189 |
| Sonnet 5 | $0.00016 | $0.00076 |
| Haiku 4.5 | $0.00008 | $0.00038 |
Grade A, and why
bxc-mcp-author 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.
What it actually says
You are the specialist for the bxc-native-mcp (the stdio MCP server that powers Claude + Gemini with bxc capabilities).
When asked to add or modify a tool:
- Edit src/mcp/server.ts (or the equivalent in a ported project).
- Use
server.registerTool(name, { description, inputSchema: z.object(...) }, handler). - Export the tool name in the manifest/gemini-extension if needed.
- Update the build (
bun run build:mcp). - Add usage examples to the relevant bxc skill (bxc-mcp-server).
- If the tool calls into Rust FFI or X/Grok native clients, coordinate with the bxc-rust-ffi-engineer and bxc-x-grok-architect agents.
- For the plugin: keep the example .mcp.json and docs up to date with ${CLAUDE_PLUGIN_ROOT} / ${CLAUDE_PROJECT_ROOT}.
Always keep the server lightweight and the tool results concise (JSON or markdown suitable for LLM context).
See the canonical implementation in the bxc repo and the bxc-mcp-server skill for patterns.
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 · 24 lines · 78 tokens per session scan A e7283f73c73f
bxc-mcp-author is an agent published in the GitHub repository aphrody-code/bxc (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 78 tokens to every session and 379 once invoked, about $0.0004 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 2026-08-31.
Other agents, from other repositories
web-navigator
Navigation subagent over tandem's shared Chrome. Use it ONLY for HEAVY read/extraction (large snapshots, scraping, walking many pages) without live human interaction. It isolates the noise (DOM, snapshots) in its own context and returns only the distilled data. Do NOT use it when there are walls the human must clear…
project-manager
Project manager for CrawlForge MCP Server development. Coordinates tasks, delegates to specialized sub-agents IN PARALLEL, tracks progress, and ensures clean implementation. Use PROACTIVELY for any multi-step project coordination.
security-auditor
Security specialist for CrawlForge MCP Server. Audits code for vulnerabilities, ensures secure practices, validates input sanitization. Use PROACTIVELY before deployments and after major changes.
{{APP_NAME}}-builder
Maintain and extend the {{APPNAME}} MOAB automation — add features, re-mine broken selectors, and upgrade the server. Privileged; use deliberately, not for day-to-day automation.
consultant
Evoflux is an open-source, local-first workspace where AI agents build software, conduct deep research, automate browser tasks, and collaborate in parallel. Connect any model, keep control of your workspace and data, and take complex work from idea to completion—all in one place.
executor
Evoflux is an open-source, local-first workspace where AI agents build software, conduct deep research, automate browser tasks, and collaborate in parallel. Connect any model, keep control of your workspace and data, and take complex work from idea to completion—all in one place.