observability-check

observability-check is a command for Claude Code from alifanov/darkflow. It costs 18 tokens per session (1,198 once invoked), scanned A, original, MIT.

An application health review that examines errors, slow web requests, database queries, traffic levels, and service reporting in an observability tool. Observability tools collect measurements about how software runs.

In plain words
What is it for?
Use it to investigate rising errors, slow endpoints, inefficient database queries, unusual traffic, and missing monitoring data.
Why use it?
It helps reveal production problems that may not appear in source code, then records significant findings as tasks.

Command 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 commands/alifanov/darkflow/observability-check
Clone the repo
git clone --depth 1 https://github.com/alifanov/darkflow

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 observability-check

README.md
[![agentmods](https://agentmods.dev/badge/commands/alifanov/darkflow/observability-check.svg)](https://agentmods.dev/commands/alifanov/darkflow/observability-check)
Your own site
<a href="https://agentmods.dev/commands/alifanov/darkflow/observability-check"><img src="https://agentmods.dev/badge/commands/alifanov/darkflow/observability-check.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,198 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 $0.00018 $0.01198
Opus 5 $0.00009 $0.00599
Sonnet 5 $0.00004 $0.00240
Haiku 4.5 $0.00002 $0.00120

Measured 4d ago against content hash e8a9b455b729, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

observability-check 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 4d 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.

templates/.claude/commands/darkflow/observability-check.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Step 1 — Read project config

Load the project config (contract in .darkflow.d/claude.mdProject config). Uses: language.

Step 2 — Do the work

Check the observability tool configured for this project (SigNoz, Datadog, Grafana, or equivalent). Specifically:

  1. Errors — new or spiking error rates in the last 24h; group by error type
  2. Slow endpoints — URLs with p95 latency > 1s; note the slowest 5
  3. Database queries — slow queries (> 100ms), N+1 patterns, queries without indexes, highest-volume queries per endpoint
  4. Request volume — unusual spikes or drops vs the previous 7-day average
  5. Integration health — are all services reporting? Any gaps in traces or missing spans?

For each finding:

  • State the metric and its current value
  • Compare to the previous period (yesterday / last week)
  • Suggest a concrete fix (add index, cache result, paginate query, etc.)

Create a task for each significant finding. Use --source signoz (or the relevant observability tool) and a priority.

Auto-approve — additive index only. When the finding is purely adding a database index (no schema/data change, no query rewrite), create the task directly with --status approved instead of --status proposed, and add the line "Auto-approved — see docs/auto-approve.md." to the task body. This applies only to plain index additions — query rewrites, N+1 fixes, caching, denormalization, and any change that alters behavior or data stay --status proposed for human review.

Priority vocabulary: critical / high / medium / low. Only create tasks for critical / high / mediumlow-priority findings are skipped (record them under Hypotheses in the snapshot instead).

Task format (required):

  • Title: action-oriented verb — "Add index on X", "Cache Y endpoint", "Fix N+1 in Z" — never just a description of the symptom ("Slow endpoint detected", "High error rate on X")
  • Body:
    ## Problem
    <metric, current value, comparison to previous period>
    
    ## Plan
    - [ ] 1. <concrete fix — specific table, query, endpoint, or config to change>
    - [ ] 2. <next step, if the fix needs one>
    
    ## Acceptance criteria
    - [ ] <measurable outcome, e.g. "p95 latency on /api/users drops below 500ms">
    - [ ] <additional criterion if needed>
    

Read the full file on GitHub · 118 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. 4d ago First seen · 118 lines · 18 tokens per session scan A e8a9b455b729

Subscribe to this mod's changes

observability-check is a command published in the GitHub repository alifanov/darkflow (2 stars, last pushed 5d ago), licensed MIT. It adds 18 tokens to every session and 1,198 once invoked, about $0.0001 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.