claudecodex

oddyssey

CLI toolbox for Observability-Driven Development (ODD): coding agents observe local runs on an OpenTelemetry/Grafana stack - or remote ones on any OpenTelemetry backend - and feed the next spec-driven improvement loop.

127 on GitHubby using-systemv1.13.3MITupdated yesterdayobservability
/

Plugin oddyssey from marketplace otelyssey in using-system/otelyssey. Commands read from the repo's manifest — today.

This plugin runs code on your machine — its hooks fire automatically on events like tool use and it starts local MCP servers. The exact commands are listed below; read them before installing.

What it installs

Skills (9)

  • backend-configuration

    Own the configured observability backend, in two sections invoked by name. Check: display the configured stack and the instance the runs will hit, prove the CLI connected, guide the user when it is not, and hand the preflight over to the mission. Switch: verify the target backend's CLI is installed

  • get-status

    Render the state of the ODD loop from the repository's committed .odd/ history and git alone - one screen by default (the loop state per lineage with its burn-down and next action), the full tables on request (per-service loop state, findings ledger, trends, open telemetry gaps) - read-only, no back

  • k6-guides

    Curated map of the official k6 load-testing docs - installation, running a script, scripting (checks/thresholds/scenarios), test types, protocols, and which questions a benchmark's inputs require before it can be authored. Use when authoring or reasoning about a k6 benchmark - pick the topic, open i

  • observability-cli-guides

    The package's knowledge of every observability stack it supports, one reference file per stack - the terminal query surface (how to authenticate and query metrics, traces, logs, and profiles from the CLI), how the stack's configuration is displayed and proven, and what its stack_config persists - pl

  • odd-memory

    The .odd/ memory - its contract and one reference per kind. The contract states what every kind shares (where the memory lives, the frontmatter and the whole body, append-only reports versus living-source benchmarks, recall by frontmatter then by section, the no-secrets rule, the work branch and the

  • otel-guides

    Curated map of the official OpenTelemetry documentation by language. Use when planning or implementing OpenTelemetry instrumentation for a codebase - pick the language, open its reference file, and follow the linked official docs for traces, metrics, logs, instrumentation libraries, exporters, and S

  • package-layout

    Where this package is installed and what each part of it is - every skill, its reference files, its scripts, and the sibling directories the install carries. Use when a mission block needs the skills' directory, when a contract must name a reference or a script by path, or when anything is about to

  • run-scenario

    Drive a reproducible request scenario against a locally running service - ad-hoc requests, or a stored k6 benchmark from .odd/benchmarks/ - and record it verbatim, so the telemetry it produces can be compared with a later run. Use when traffic must be generated before observing a service, when a sto

  • setup-local-stack

    Configure gcx against the local oddyssey Grafana stack and query its four signals (metrics, traces, logs, profiles) without touching the user's own gcx contexts. Owns the global configuration's "local" stack value. Use when the configured stack is "local", when querying the local stack (Grafana host

Slash commands (7)

  • /oddyssey:odd-config

    Display the current oddyssey backend configuration - configured stack and environment, targeted instance, connection proof - then offer to change it: pick a backend from the full list, built-in or custom, and route the switch to the backend-configuration skill's Switch; targets a deployment environm

  • /oddyssey:odd-instrument-bench

    Investigate a service and author a k6 load-test benchmark plan as code in .odd/benchmarks/ - asks back whatever only a human can decide before dispatching the authoring agent, which validates the script with k6 inspect and one smoke iteration and never runs the benchmark

  • /oddyssey:odd-instrument-otel

    Investigate a codebase and get every input needed to plan OpenTelemetry instrumentation for it

  • /oddyssey:odd-instrument-stack

    Author a custom observability stack as a directory in .odd/observability-stacks/ - guide.md plus the query scripts it names, verified live against the backend - through the stack-instrumentation-expert agent; also completes one from an instruction, links one another repository carries, and fixes one

  • /oddyssey:odd-observe

    Observe a running service through its telemetry (local stack or remote backend) and get the plan-ready observation report

  • /oddyssey:odd-status

    Where is the ODD loop? Read the repository's .odd/ history and render it as a one-screen synthesis - the loop state per lineage, its burn-down, the next recommended action - or, on request, the full tables (per-service loop state, findings ledger, trends, open telemetry gaps) - reports read-only, no

  • /oddyssey:odd-verify

    Verify that a fix or an implemented instrumentation plan landed - replay a stored report's protocol (observation or instrumentation report) and get the full observation report, carrying the verdict on everything it recorded - measurements, anomalies, telemetry gaps, or planned signals now present

Subagents (4)

  • k6-benchmark-expert

    Investigate a service and author a k6 load-test benchmark (script + manifest) as reviewed, committed code - validated with k6 inspect, a one-iteration smoke and a parse of the manifest before persisting, never executed as a benchmark. Input - the service to benchmark, and every authoring-inputs.md "

  • observe-run

    Observe a running service through its telemetry (metrics, traces, logs, profiles) on any stack - the local oddyssey stack or a remote backend (Grafana, Datadog, Dynatrace, Azure Monitor, CloudWatch, a custom stack, ...) - and hand the main agent every input it needs to build a spec-driven plan of fi

  • otel-instrumentation-expert

    Investigate a codebase or stack and hand the main agent every input it needs to build a complete spec-driven plan for implementing OpenTelemetry instrumentation. Input - the path (or repo) to investigate and, if known, the export stack. Recalls previous investigations from .odd/otel-instrumentation-

  • stack-instrumentation-expert

    Author a custom observability stack for a backend the package does not ship, as a directory in .odd/observability-stacks/ - guide.md with the reference contract's sections, and scripts/ with the query scripts the guide names - every invocation verified live against the backend before it is written a

MCP servers (1)

  • oddyssey

    runs: uvx --refresh-package oddyssey-mcp oddyssey-mcp==1.13.3

Hooks (4)

  • PostToolUse

    python3 "${CLAUDE_PLUGIN_ROOT}"/hooks/scripts/scan_odd_identifiers.py PostToolUse

  • PostToolUse

    python3 "${CLAUDE_PLUGIN_ROOT}"/hooks/scripts/check_report_frontmatter.py PostToolUse

  • PreToolUse

    python3 "${CLAUDE_PLUGIN_ROOT}"/hooks/scripts/guard_default_branch.py PreToolUse

  • PreToolUse

    python3 "${CLAUDE_PLUGIN_ROOT}"/hooks/scripts/guard_append_only.py PreToolUse

View source on GitHub

More from using-system/otelyssey

All 24 plugins →

pup

claudecodex

Datadog API CLI with 49 command groups, 300+ subcommands. Skills and domain agents for monitoring, logs, APM, security, and infrastructure.

13 skills · 51 agents

127

save-toolkit

claudecodex

Application-engineering and site-reliability agents and reusable skills.

25 skills · 1 command · 9 agents · hooks

127

Vendor-neutral OpenTelemetry skills for AI coding agents, grounded in upstream sources: SDK setup per language, the Collector and OCB, OTTL, declarative configuration, semantic conventions, upgrades and migrations.

19 skills

127

OpenTelemetry signal quality with durable workflows and fresh, version-correct upstream evidence.

15 skills

127

signoz

claudecodex

Official SigNoz plugin for MCP setup, docs, queries, dashboards, and alerts

13 skills · hooks

127

logpacer

claudecodex

Connect your coding agent to the hosted LogPacer MCP server, with skills for setting up collection, instrumenting apps and investigating logs.

8 skills · 1 MCP server

127

Similar plugins

claude-mem

claudecodex

Persistent memory for Claude Code: the next session starts where the last one left off.

29 skills · 1 MCP server · hooks

thedotmack/claude-mem 116,618

career-ops

claudecodex

Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications

5 skills · hooks

career-ops-hq/career-ops 82,253

context7

claudecodex

Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.

1 MCP server

upstash/context7 64,709

mempalace

claudecodex

AI memory system — mine projects and conversations into a searchable palace. 47 MCP tools, auto-save hooks, guided setup.

3 skills · 6 commands · 1 MCP server · hooks

MemPalace/mempalace 60,536

Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer

8 skills · 1 MCP server

ChromeDevTools/chrome-devtools-mcp 55,181

gitnexus

claudecodex

Code intelligence powered by a knowledge graph. Provides execution flow tracing, blast radius analysis, and augmented search across your codebase.

12 skills · 1 MCP server · hooks

abhigyanpatwari/GitNexus 48,482

Maintain oddyssey?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins24 plugins