prod-logs

prod-logs is an agent for Claude Code from Sharrmavishal/operating-kit. It costs 57 tokens per session (516 once invoked), scanned A, original, MIT.

A production-log checker that reads real application logs and reports errors, warnings, timeouts, retries, and unusual events. Production logs are records of what the running system actually did.

In plain words
What is it for?
Use it after deployments or load tests, or when investigating whether a live system is failing and what the logs prove.
Why use it?
It prevents incident reviews from relying only on dashboards or test-program output, which may show incomplete or misleading results.

Agent for Claude Code

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 agents/sharrmavishal/operating-kit/prod-logs
Clone the repo
git clone --depth 1 https://github.com/Sharrmavishal/operating-kit

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 prod-logs

README.md
[![agentmods](https://agentmods.dev/badge/agents/sharrmavishal/operating-kit/prod-logs.svg)](https://agentmods.dev/agents/sharrmavishal/operating-kit/prod-logs)
Your own site
<a href="https://agentmods.dev/agents/sharrmavishal/operating-kit/prod-logs"><img src="https://agentmods.dev/badge/agents/sharrmavishal/operating-kit/prod-logs.svg" alt="Measured on agentmods" height="20"></a>
Per session 57 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 516 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00057 $0.00516
Opus 5 $0.00028 $0.00258
Sonnet 5 $0.00011 $0.00103
Haiku 4.5 $0.00006 $0.00052

Measured 5d ago against content hash 845a6cfec977, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

prod-logs 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 5d 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.

.claude/agents/prod-logs.md · 45 lines

What it actually says

You are this project's production-log health checker. You pull real logs and report what's actually happening, not what a dashboard or a script's stdout claims is happening.

Template note: point {{LOG_QUERY}} at the project's real log source (cloud logging, journald, a file, kubectl logs, etc.). Keep the core rule regardless of stack.

Core rule: logs are the primary source

Never analyze a production incident or a load/test run from UI data or script stdout alone. Dashboards paginate (you see the last N events, not all of them) and a test harness's own timing is often wrong for streamed/async work (it measures when the stream opened, not when the work finished; "stream closed without error" is not "produced correct output"). Pull the logs.

If the logs are not available or you didn't check them, say so explicitly before presenting any finding. Do not present inference as fact (operating-principles.md A7).

Steps

1: Pull recent logs

{{LOG_QUERY}}   # last ~1–2h, enough volume to not truncate a full run

2: Filter for signal

Grep for: errors / exceptions / stack traces, timeouts, retries, the specific markers this system emits for its failure modes ({{PROJECT_SPECIFIC_MARKERS}}), and any decision/threshold log lines relevant to what you're diagnosing.

3: Distinguish unique failures from retries

The same job id appearing 5× is one failure retried, not five failures. Cross-reference ids before reporting a count, and COUNT(DISTINCT) over entities, not raw log lines (operating-principles.md A8).

What to report

  • Time window and how many log lines you actually pulled (so truncation is visible).
  • Errors/warnings grouped by root cause, with a representative excerpt each.
  • Distinct-failure count vs. total occurrences.
  • Anything you could not confirm from logs, stated as an open gap, not a guess.
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. 5d ago First seen · 45 lines · 57 tokens per session scan A 845a6cfec977

Subscribe to this mod's changes

prod-logs is an agent published in the GitHub repository Sharrmavishal/operating-kit (2 stars, last pushed 1mo ago), licensed MIT. It adds 57 tokens to every session and 516 once invoked, about $0.0003 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 2026-08-30.

Related

Other agents, from other repositories

cpp-reviewer

Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.

affaan-m/ECC · 41 tokens

dynamic-agents

Dynamic agents use functions instead of static values for instructions, model, and tools. These functions receive runtime context and return the appropriate configuration for each operation.

VoltAgent/voltagent · 0 tokens

pixel-art-animation-reviewer

Independent reviewer of pixel-art ANIMATION quality (loop seamlessness, motion physics, multi-component motion, frame timing, period selection, particle determinism). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check animation timing", "verify loop…

AnastasiyaW/codex-claude-code-config · 140 tokens

seo-meta-optimizer

Creates optimized meta titles, descriptions, and URL suggestions based on character limits and best practices. Generates compelling, keyword-rich metadata. Use PROACTIVELY for new content.

echoVic/blade-code · 39 tokens

answered-questions-subagent

Processes answered questions from plan.json and incorporates them into relevant tasks.

closedloop-ai/claude-plugins · 19 tokens

python-pro

Write idiomatic Python code with advanced features like decorators, generators, and async/await. Optimizes performance, implements design patterns, and ensures comprehensive testing. Use PROACTIVELY for Python refactoring, optimization, or complex Python features.

echoVic/blade-code · 51 tokens