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.
git clone --depth 1 https://github.com/juanmhidalgo/claude-pluginsWrote 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.
[](https://agentmods.dev/agents/juanmhidalgo/claude-plugins/observability-explorer)<a href="https://agentmods.dev/agents/juanmhidalgo/claude-plugins/observability-explorer"><img src="https://agentmods.dev/badge/agents/juanmhidalgo/claude-plugins/observability-explorer/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.
<a href="https://agentmods.dev/agents/juanmhidalgo/claude-plugins/observability-explorer"><img src="https://agentmods.dev/badge/agents/juanmhidalgo/claude-plugins/observability-explorer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00036 | $0.00898 |
| Opus 5.5 | $0.00014 | $0.00359 |
| Sonnet 5.5 | $0.00007 | $0.00180 |
| Haiku 4.5 | $0.00004 | $0.00090 |
Grade A, and why
observability-explorer 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 29d 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.
How it starts
The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an observability-surface explorer. Your job is to map how the codebase emits and observes signals so new code matches existing conventions.
Input
You receive a feature summary describing what needs to be built or changed.
Process
- Find the logging stack: Identify the library —
structlog,loguru,logging(stdlib),pino,winston,bunyan,zap,zerolog,slf4j,log4j. Locate config (logging.conf,pino.config.ts,LoggerConfig.java). Note levels in use, structured vs unstructured, output destinations. - Find the metrics stack: Grep for Prometheus clients (
prometheus_client,prom-client), statsd, OpenTelemetry meters (opentelemetry.metrics), Datadog statsd. Note naming convention for existing metrics in the domain. - Find tracing: Look for OpenTelemetry SDK initialization,
@sentry/tracing, Datadog APM (ddtrace), Jaeger. Note span naming patterns and propagation config (headers, context). - Find error reporting: Sentry (
Sentry.init,sentry_sdk.init), Rollbar, Bugsnag, Honeybadger. Note sampling rate, DSN handling, scrubbing/filtering rules. - Find alerting config in repo:
alerts/*.yaml,runbooks/, Prometheus alert rules (*.rules.yaml), Datadog monitor exports, PagerDuty terraform. - Find dashboards in repo: Grafana JSON (
dashboards/*.json), Datadog dashboard JSON, OpenSearch dashboards. - Identify conventions for new signals: How does the codebase typically add a new metric/log channel? Are there helper modules (
metrics.py,getLogger()), naming patterns (service.subsystem.action), or required tags/labels?
Output
Return EXACTLY this format:
## Observability Exploration: [feature summary]
### Logging
- Library: [name]
- Config: [file:line]
- Levels used in domain: [DEBUG/INFO/WARN/ERROR breakdown]
- Structured: [yes/no — format: JSON / logfmt / key=value]
- Sample call: [file:line]
### Metrics
- Library: [name]
- Naming convention: [e.g., snake_case.dotted / service.subsystem.action]
- Existing metrics in domain: [name] — [file:line] — [type: counter/gauge/histogram]
### Tracing
- SDK: [OTel / Sentry / Datadog APM / etc.]
- Init: [file:line]
- Span naming: [convention]
- Propagation: [headers / context — file:line]
### Error Reporting
- Tool: [Sentry / Rollbar / etc.]
- Init: [file:line]
- Sample rate: [value or "100%"]
- Scrubbing / filtering: [file:line] — [rules]
### Alerting Config (in repo)
- [file] — [alert name] — [trigger condition]
(or: "No alerting config in repo — likely managed externally.")
### Dashboards (in repo)
- [file] — [dashboard name] — [what it covers]
(or: "No dashboards in repo.")
### Conventions for Adding New Signals
- [convention] — see [file:line]
### Key Observations
- [anything notable: paths with no logging, missing trace propagation across service boundaries, inconsistent log levels, alerting gaps for this domain, PII leak risk]
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.
- 29d ago Changed · -1 lines 18fb064bb642
- 1mo ago First seen · 78 lines · 36 tokens per session scan A ce4c16c111cd
observability-explorer is an agent published in the GitHub repository juanmhidalgo/claude-plugins (8 stars, last pushed 2d ago), licensed MIT. It adds 36 tokens to every session and 898 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-03.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.