analyzing-llm-rationale: Skill for Claude Code

.agents/skills/superlog-onboard/SKILL.md

superlog-onboard is a skill for Claude Code, Codex from pareelamre/analyzing-llm-rationale. It costs 71 tokens per session (5,251 once invoked), scanned A, a copy of superlog-onboard, MIT.

A setup guide for adding Superlog monitoring to every application and service in a project. Superlog receives OpenTelemetry traces, logs, and metrics.

In plain words
What is it for?
Use it to onboard a whole repository to Superlog, including Python, Next.js, Expo, Supabase Edge Functions, LiveKit, and other services.
Why use it?
It prevents teams from monitoring only the service they happen to be editing and gives them guidance for configuring the connection correctly. It also points to stack-specific monitoring guidance.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code; installed under .agents/ (shared by several agents); mentions Codex.

This is pareelamre/analyzing-llm-rationale's own configuration. It tells Claude Code and Codex how to work on analyzing-llm-rationale itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything analyzing-llm-rationale configures →

Reuse

Borrowing it

Nothing to install: this file belongs to pareelamre/analyzing-llm-rationale. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/pareelamre/analyzing-llm-rationale/main/.agents/skills/superlog-onboard/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/pareelamre/analyzing-llm-rationale

Made for: Claude Code, Codex.

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 superlog-onboard

README.md
[![agentmods](https://agentmods.dev/badge/skills/pareelamre/analyzing-llm-rationale/superlog-onboard/github.svg)](https://agentmods.dev/skills/pareelamre/analyzing-llm-rationale/superlog-onboard)
Your own site
<a href="https://agentmods.dev/skills/pareelamre/analyzing-llm-rationale/superlog-onboard"><img src="https://agentmods.dev/badge/skills/pareelamre/analyzing-llm-rationale/superlog-onboard/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 superlog-onboard

Your own site · 80×15
<a href="https://agentmods.dev/skills/pareelamre/analyzing-llm-rationale/superlog-onboard"><img src="https://agentmods.dev/badge/skills/pareelamre/analyzing-llm-rationale/superlog-onboard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,251 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin 100% copy Near-identical to another mod 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 $0.00071 $0.05251
Opus 5 $0.00036 $0.02625
Sonnet 5 $0.00014 $0.01050
Haiku 4.5 $0.00007 $0.00525

Measured 10d ago against content hash 81df991bd07b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

superlog-onboard scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

1. **Run the project's own dev or build command** (whatever its `package.json` / `pyproject` / `Makefile` already wires up). Confirm it starts cleanly with no errors that trace back to your OTel install. Also run a telem
Origin

This is a copy

100% identical to superlog-onboard — 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.

.agents/skills/superlog-onboard/SKILL.md · 251 lines

How it starts

The opening of the file, as written. The whole thing — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Superlog onboarding

Wire OpenTelemetry traces, logs, and metrics into the user's project so telemetry streams to Superlog. Cover every app and service in the repo — not just the one the user is currently sitting in.

Prefer native OpenTelemetry APIs and the framework's documented bootstrap over custom helper layers. If a specific stack stumps you, search the OTel docs for that language; don't guess.

Before editing, read the applicable companion skills:

  • otel-onboarding-style for general OTel taste.
  • otel-python-style for Python services.
  • otel-fastapi-style for FastAPI services.
  • otel-livekit-style for LiveKit agents.
  • otel-nextjs-style for Next.js/Vercel apps.
  • otel-expo-style for Expo / React Native apps.
  • otel-supabase-edge-style for Supabase Edge Functions.
  • otel-generic-style for any other language (Go, Java/Kotlin, Ruby, Rust, .NET/C#, PHP, Elixir, plain Node, …) — use this as the fallback when none of the above match.

Step 0 — Endpoint and public token handling

The OTLP endpoint is always https://intake.superlog.sh and goes directly in the bootstrap source.

The Superlog public ingest token starts with sl_public_. It is project-scoped, write-only, and intentionally safe to include in application source, including browser and mobile bundles. Treat it like a PostHog project token, Sentry DSN, or Datadog RUM client token: it can send telemetry to one project, but cannot read data, change settings, or access the Superlog account.

Inline the public token as a constant next to the endpoint. Do not put it in .env files, deploy settings, or generated shell commands; source-level config is the intended onboarding path and avoids broken deploys from missing env vars.

When an OTLP exporter requires headers, pass the public token through the exporter constructor as the x-api-key header. This is the single most common onboarding failure: the token is valid, but the exporter sends it under the wrong header name (or no header), so ingest returns 401 on every request and the install looks broken when the key is fine. Ingest reads the token from exactly two places — x-api-key: <token>, or Authorization: Bearer <token> (the literal Bearer prefix is required). Use x-api-key; it avoids the Bearer -prefix footgun and survives proxies/SDKs that strip Authorization. Do not invent other header names (api-key, x-superlog-token, Authorization: <token> without Bearer ) — all of them 401.

Read the full file on GitHub · 251 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 · 251 lines · 71 tokens per session scan A 81df991bd07b

Subscribe to this mod's changes

superlog-onboard is a skill published in the GitHub repository pareelamre/analyzing-llm-rationale (0 stars, last pushed yesterday), licensed MIT. It adds 71 tokens to every session and 5,251 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). It is 100% identical to superlog-onboard, differing in 0 lines, and is treated as a copy.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens