load-shedding-instrumenter

load-shedding-instrumenter is an agent for Claude Code from luanpdd/kit-mcp. It costs 48 tokens per session (2,355 once invoked), scanned A, original, MIT.

An agent that adds load-shedding protections to Edge Functions or HTTP handlers. Load shedding means refusing some work when a service is overloaded so it can keep responding to other requests.

In plain words
What is it for?
Use it when a service is becoming saturated and needs concurrency limits, queue limits, deadline-aware handling, server-side rate limits, or slow-start recovery.
Why use it?
It applies several protections consistently instead of leaving each service to handle overload differently. These protections can limit concurrent work, bound queues, respect deadlines, rate-limit requests, and recover gradually.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is import { LoadShedder } from '../_shared/load-shedder.ts'.

Good fit Use it when a service is becoming saturated and needs concurrency limits, queue limits, deadline-aware handling, server-side rate limits, or slow-start recovery.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/luanpdd/kit-mcp
agentmods
npx agentmods add agents/luanpdd/kit-mcp/load-shedding-instrumenter

Made for: Claude Code.

Wrote 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.

agentmods badge for load-shedding-instrumenter

README.md
[![agentmods](https://agentmods.dev/badge/agents/luanpdd/kit-mcp/load-shedding-instrumenter/github.svg)](https://agentmods.dev/agents/luanpdd/kit-mcp/load-shedding-instrumenter)
Your own site
<a href="https://agentmods.dev/agents/luanpdd/kit-mcp/load-shedding-instrumenter"><img src="https://agentmods.dev/badge/agents/luanpdd/kit-mcp/load-shedding-instrumenter/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.

agentmods 80×15 button for load-shedding-instrumenter

Your own site · 80×15
<a href="https://agentmods.dev/agents/luanpdd/kit-mcp/load-shedding-instrumenter"><img src="https://agentmods.dev/badge/agents/luanpdd/kit-mcp/load-shedding-instrumenter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,355 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00048 $0.02355
Opus 5 $0.00024 $0.01177
Sonnet 5 $0.00010 $0.00471
Haiku 4.5 $0.00005 $0.00235

Measured 10d ago against content hash f7b88206ecee, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

load-shedding-instrumenter 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 10d 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.

kit/agents/load-shedding-instrumenter.md · 292 lines

How it starts

The opening of the file, as written. The whole thing — 292 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Você é o instrumentador de load shedding. Recebe target_path (Edge Function ou handler HTTP) e aplica patches via Edit tool: queue depth gauge, drop policy, deadline-aware handler, server-side rate limit, slow start na recovery.

Você consulta:

Compat: Full em todos os IDEs (filesystem-only). Veja COMPATIBILITY.md.

Por que existe

Load shedding é cross-cutting concern — server detecta saturation E rejeita 503 graceful E dispara observability E não cai. Sem template canônico, cada equipe reinventa de forma frágil. Esse agent aplica os 5 patterns canônicos em código existente, preservando lógica core.

Inputs esperados (do caller)

  • target_path: arquivo a instrumentar (Edge Function ou handler HTTP)
  • (Opcional) patterns: subset de [concurrency-limit, queue-bound, deadline-aware, rate-limit, slow-start] (default: todos aplicáveis)
  • (Opcional) max_concurrent: default 1000
  • (Opcional) cpu_threshold: default 90
  • (Opcional) queue_max_size: default 10000

Passos

Step 0 — Preflight

TARGET_PATH="${target_path}"
[ ! -f "$TARGET_PATH" ] && { echo "ERROR: $TARGET_PATH not found"; exit 1; }

# detectar runtime
case "$TARGET_PATH" in
  *.ts|*.tsx|*.js|*.mjs)
    RUNTIME="node-deno"
    ;;
  *.py)
    RUNTIME="python"
    ;;
  *)
    echo "ERROR: runtime não suportado: $TARGET_PATH"
    exit 1
    ;;
esac

# detectar tipo de handler
HANDLER_TYPE=""
if grep -q "Deno.serve" "$TARGET_PATH"; then
  HANDLER_TYPE="deno-serve"
elif grep -qE "app\.(post|get|put)" "$TARGET_PATH"; then
  HANDLER_TYPE="express-like"
fi

Step 1 — Aplicar pattern: concurrency limit + 503 graceful

Para Deno Edge Function:

// PATCH: shared load shedder
// Criar arquivo se não existe: supabase/functions/_shared/load-shedder.ts

interface LoadShedderOpts {
  maxConcurrent: number
  cpuThreshold?: number
  saturationGauge?: () => Promise<number>
}

export class LoadShedder {
  private inFlight = 0
  constructor(private opts: LoadShedderOpts) {}

  async tryAcquire(): Promise<{ ok: true } | { ok: false; reason: string; retryAfterSec: number }> {
    if (this.inFlight >= this.opts.maxConcurrent) {
      return { ok: false, reason: 'concurrency_limit', retryAfterSec: 5 }
    }
    if (this.opts.saturationGauge) {
      const sat = await this.opts.saturationGauge()
      if (sat > 0.95) {
        return { ok: false, reason: 'saturation', retryAfterSec: 30 }
      }
    }
    this.inFlight++
    return { ok: true }
  }

  release(): void {
    this.inFlight = Math.max(0, this.inFlight - 1)
  }
}

Read the full file on GitHub · 292 lines

Changes

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.

  1. 10d ago First seen · 292 lines · 48 tokens per session scan A f7b88206ecee

Subscribe to this mod's changes

load-shedding-instrumenter is an agent published in the GitHub repository luanpdd/kit-mcp (1 stars, last pushed 3d ago), licensed MIT. It adds 48 tokens to every session and 2,355 once invoked, about $0.0002 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.

Related

Other agents, from other repositories

Power Platform MCP Integration Expert

Expert in Power Platform custom connector development with MCP integration for Copilot Studio - comprehensive knowledge of schemas, protocols, and integration patterns.

github/awesome-copilot · 31 tokens

php-developer

Write idiomatic PHP code with design patterns, SOLID principles, and modern best practices. Implements PSR standards, dependency injection, and comprehensive testing. Use PROACTIVELY for PHP architecture, refactoring, or implementing design patterns.

davepoon/buildwithclaude · 51 tokens

backend-reviewer

Use when reviewing service-layer logic, module boundaries, business rules, or cross-service contracts — verifies architecture integrity and service correctness against the api and architect persona standards.

jeremylongshore/tons-of-skills-marketplace · 36 tokens

integrations-engineer

Third-party integration specialist for SMB Product-Builder archetypes. Owns the integration contract — OAuth2/API-key flows, webhook signature verification, idempotency keys, retry/backoff with jitter, rate-limit handling, secret storage, and sandbox→prod promotion — for Stripe, Twilio, QuickBooks, Google/Microsoft…

avelikiy/great_cto · 106 tokens

gate

API quality gates — linting, style enforcement, breaking change CI, and API governance.

tonone-ai/tonone · 19 tokens

dotnet-architecture-reviewer

Reviews a .NET codebase or repository and produces a structured architecture report — layering and dependency-rule violations, coupling, CQRS/handler hygiene, EF Core boundary leaks, testability, and concrete prioritized fixes. Use when the user wants an architecture review, a "second opinion" on structure, a PR-level…

StefanTheCode/dotnet-ai-toolkit · 102 tokens