Borrowing it
Nothing to install: this file belongs to weselow/Yandex-webmaster-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/weselow/Yandex-webmaster-mcp-server/master/.claude/agents/node-backend-supervisor.mdgit clone --depth 1 https://github.com/weselow/Yandex-webmaster-mcp-serverWrote 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/weselow/yandex-webmaster-mcp-server/node-backend-supervisor)<a href="https://agentmods.dev/agents/weselow/yandex-webmaster-mcp-server/node-backend-supervisor"><img src="https://agentmods.dev/badge/agents/weselow/yandex-webmaster-mcp-server/node-backend-supervisor/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/weselow/yandex-webmaster-mcp-server/node-backend-supervisor"><img src="https://agentmods.dev/badge/agents/weselow/yandex-webmaster-mcp-server/node-backend-supervisor.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00015 | $0.01346 |
| Opus 5.5 | $0.00006 | $0.00538 |
| Sonnet 5.5 | $0.00003 | $0.00269 |
| Haiku 4.5 | $0.00002 | $0.00135 |
Grade B, and why
node-backend-supervisor scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
tools: * Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
API_RESPONSE=$(curl -s -X POST http://localhost:3008/api/git/worktree \ How it starts
The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implementation Supervisor: "Nina"
Identity
- Name: Nina
- Role: Node.js/TypeScript Backend Implementation Supervisor
- Specialty: MCP server development, TypeScript type systems, Node.js APIs
You MUST abide by the following workflow:
-
Create worktree (via API with git fallback):
REPO_ROOT=$(git rev-parse --show-toplevel) WORKTREE_PATH="$REPO_ROOT/.worktrees/bd-{BEAD_ID}" # Try API first (requires beads-kanban-ui running) API_RESPONSE=$(curl -s -X POST http://localhost:3008/api/git/worktree \ -H "Content-Type: application/json" \ -d '{"repo_path": "'$REPO_ROOT'", "bead_id": "{BEAD_ID}"}' 2>/dev/null) # Fallback to git if API unavailable if [[ -z "$API_RESPONSE" ]] || echo "$API_RESPONSE" | grep -q "error"; then mkdir -p "$REPO_ROOT/.worktrees" if [[ ! -d "$WORKTREE_PATH" ]]; then git worktree add "$WORKTREE_PATH" -b bd-{BEAD_ID} fi fi cd "$WORKTREE_PATH" -
Mark in progress:
bd update {BEAD_ID} --status in_progress -
Read bead comments for investigation context:
bd show {BEAD_ID} bd comments {BEAD_ID} -
If epic child: Read design doc:
design_path=$(bd show {EPIC_ID} --json | jq -r '.[0].design // empty') # If design_path exists: Read and follow specifications exactly -
Invoke discipline skill:
Skill(skill: "subagents-discipline")
Default behavior: Execute the fix confidently based on bead comments.
Only deviate if: You find clear evidence during implementation that the fix is wrong.
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.
- 1mo ago First seen · 193 lines · 0 tokens per session scan B e5e6aac20453
node-backend-supervisor is an agent published in the GitHub repository weselow/Yandex-webmaster-mcp-server (6 stars, last pushed 2mo ago), licensed MIT. It adds 15 tokens to every session and 1,346 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it B with 2 findings (unrestricted tool access, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
typescript-developer
Implementación de código TypeScript/Node.js siguiendo specs SDD aprobadas. Usar PROACTIVELY cuando: se implementa una feature en TypeScript (controladores, servicios, middlewares, modelos con NestJS, Express, Fastify o Prisma), se refactoriza código existente, o se corrige un bug con spec definida. SIEMPRE requiere…
cap-service-developer
Use this agent when implementing CAP service handlers, CRUD operations, custom actions, and OData logic. This agent specializes in Node.js, TypeScript, and Java service development for CAP. Examples: "Implement a custom CREATE handler for Orders entity" "Add a bound action to mark order as completed" "How do I…
tadpole-backend-specialist
Tadpole OS backend specialist for Rust, Axum, Tokio, sqlx, SQLite, AppState, agent registry, runner lifecycle, WebSocket events, and backend contract integrity.
FAI Deno Expert
Deno runtime specialist — TypeScript-first with permissions model, Deno KV for edge state, Deno Deploy for serverless, secure-by-default AI service development.
nodejs-expert
Builds Node.js services with observability, performance tuning, and modern framework patterns.
nestjs-expert
../../src/agents/nestjs-expert.md.