log-dive

A read-only search tool for logs in Loki, Elasticsearch or OpenSearch, and AWS CloudWatch. Logs are records of what software and services did, and the tool turns plain-language requests into each system's query format.

In plain words
What is it for?
Use it to find errors, trace what happened in a service, inspect log sources, or follow recent logs while keeping the results within the current conversation.
Why use it?
It lets you investigate incidents across different log systems without learning every query language.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/cacheforge-ai/cacheforge-skills/log-dive
Any agent
npx skills add cacheforge-ai/cacheforge-skills --skill log-dive
Clone the repo
git clone --depth 1 https://github.com/cacheforge-ai/cacheforge-skills

Made for: Claude Code, Codex.

Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,052 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
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 $0.00042 $0.03052
Opus 5 $0.00021 $0.01526
Sonnet 5 $0.00008 $0.00610
Haiku 4.5 $0.00004 $0.00305

Measured 2d ago against content hash 1b9b4f4c7af4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

log-dive 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 2d ago.

The scan reads SKILL.md. This mod also ships 4 executable files (scripts/log-dive-cw.sh, scripts/log-dive-es.sh, scripts/log-dive-loki.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

| "curl: command not found" | curl not installed | `apt install curl` or `brew install curl` |
skills/log-dive/SKILL.md · 335 lines

How it starts

The opening of the file, as written. The whole thing — 335 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Search logs across Loki, Elasticsearch/OpenSearch, and AWS CloudWatch from a single interface. Ask in plain English; the skill translates to the right query language.

⚠️ Sensitive Data Warning: Logs frequently contain PII, secrets, tokens, passwords, and other sensitive data. Never cache, store, or repeat raw log content beyond the current conversation. Treat all log output as confidential.

Activation

This skill activates when the user mentions:

  • "search logs", "find in logs", "log search", "check the logs"
  • "Loki", "LogQL", "logcli"
  • "Elasticsearch logs", "Kibana", "OpenSearch"
  • "CloudWatch logs", "AWS logs", "log groups"
  • "error logs", "find errors", "what happened in [service]"
  • "tail logs", "follow logs", "live logs"
  • "log backends", "which log sources", "log indices", "log labels"
  • Incident triage involving log analysis
  • "log-dive" explicitly

Permissions

permissions:
  exec: true          # Required to run backend scripts
  read: true          # Read script files
  write: false        # Never writes files — logs may contain secrets
  network: true       # Queries remote log backends

Example Prompts

  1. "Find error logs from the checkout service in the last 30 minutes"
  2. "Search for timeout exceptions across all services"
  3. "What log backends do I have configured?"
  4. "List available log indices in Elasticsearch"
  5. "Show me the labels available in Loki"
  6. "Tail the payment-service logs"
  7. "Find all 5xx errors in CloudWatch for api-gateway"
  8. "Correlate errors between user-service and payment-service"
  9. "What happened in production between 2pm and 3pm today?"

Backend Configuration

Each backend uses environment variables. Users may have one, two, or all three configured.

Loki

Variable Required Description
LOKI_ADDR Yes Loki server URL (e.g., http://loki.internal:3100)
LOKI_TOKEN No Bearer token for authentication
LOKI_TENANT_ID No Multi-tenant header (X-Scope-OrgID)

Read the full file on GitHub · 335 lines

Files

What ships with it

9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2d ago First seen · 335 lines · 42 tokens per session scan A 1b9b4f4c7af4

Subscribe to this mod's changes

log-dive is a skill published in the GitHub repository cacheforge-ai/cacheforge-skills (10 stars, last pushed 6mo ago), licensed MIT. It adds 42 tokens to every session and 3,052 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

k8s-incident-triage

Read-only Kubernetes incident triage using kubectl. Accepts natural language or structured input. Produces root-cause hypotheses, evidence, and next-step commands.

initializ/forge · 41 tokens

greptimedb-development-docker-image

Builds a development-only GreptimeDB Docker image from a local debug binary for local-cluster testing, and optionally pushes it to a development registry. Use when the user asks to package, build, tag, publish, or cross-build a non-release GreptimeDB or GreptimeDB Enterprise image for debugging.

GreptimeTeam/greptimedb · 71 tokens

greptimedb-fuzz-ci-failure-investigation

Investigate a failed GreptimeDB fuzz CI target link by downloading GitHub Actions job logs plus fuzz artifacts such as kind logs, monitor dumps, and CSV dumps, then correlate the failure with local GreptimeDB source code. Use when the user provides a failed fuzz CI target/job URL or asks to diagnose GreptimeDB fuzz CI…

GreptimeTeam/greptimedb · 80 tokens

greptimedb-release-note

Generate a GreptimeDB release changelog with git cliff (correct range, subtract already-released patch PRs, rebuild contributors, add human-curated highlights), output to a file, and prepare the docs-repo blog PR. Use when asked to write/generate a GreptimeDB release note or changelog.

GreptimeTeam/greptimedb · 70 tokens

greptimedb-release

Runbook for publishing a new GreptimeDB version (tag + GitHub release + docs release-note PR) on the upstream GreptimeTeam/greptimedb repo. Use when asked to "release" / "publish" a GreptimeDB version (e.g. v1.1.0, v1.0.3).

GreptimeTeam/greptimedb · 75 tokens

opentelemetry-net-instrumentation

Provides guidance for implementing OpenTelemetry instrumentation in .NET codebases, covering tracing (Activities/Spans), metrics, logs, naming conventions, error handling, performance, SDK setup, resources, context propagation, and API design best practices.

Aaronontheweb/dotnet-skills · 56 tokens