get-status

Render the ODD loop status from committed .odd/ reports and git metadata.

9|2|Updated Aug 16, 2026
One-click install
npx skills add https://github.com/using-system/oddyssey --skill get-status-using-system
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: get-status
Source: https://github.com/using-system/oddyssey/tree/main/.apm/skills/get-status
Command: npx skills add https://github.com/using-system/oddyssey --skill get-status-using-system

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve? Answering "where is the observability loop?" normally requires querying live backends or re-running a stack. This Skill computes the loop's state entirely offline from the repository's committed .odd/ report history and git metadata, producing a one-screen status or full working tables without any backend queries. ## Core Features & Use Cases - Offline loop status: Renders per-lineage loop state, findings burn-down (open, fixed-and-verified, regressed, declined), trends, and open telemetry gaps from stored observation and instrumentation reports. - Verdict and next action: Computes an ok/warning/error verdict with reasons and the next recommended action per lineage, citing evidence for every row. - Judgment workflow: Defers ambiguous rulings to a "Judgment needed" list, then applies caller rulings via flags (--ruled, --runtime, --repository) and re-renders with one truth. - Use Case: After several observation and verification runs, ask where the loop stands for a service on a given stack and environment, and get the burn-down, trends, and the next command to run without touching any live system. ## Quick Start Ask the assistant to show the current ODD loop status for this repository, optionally scoped to a service, stack, or environment.

Frequently Asked Questions about get-status

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I check the ODD loop status of a repository?

Run the get-status skill, which executes scripts/odd_status.py --render against the repository's .odd/ directory. It prints a one-screen status by default, or the full tables with --full or when scoped to a service, stack, or environment.

Does computing the loop status require a running observability backend?

No. The status is computed entirely from committed .odd/ reports, the decisions ledger, and git metadata. It never queries a backend, starts a stack, or writes any file.

What happens when a status filter matches no reports?

The skill states exactly what was searched (each filter and value) and what exists instead: the distinct services, stacks, and environments present in stored frontmatters. It never renders an empty table silently or falls back to the unfiltered picture.

How are ambiguous verification rulings handled?

Rulings the rules cannot settle are deferred to a Judgment needed list. The caller rules on them via flags like --ruled REPORT/ID=STATE, then the script re-renders with those rulings applied before the burn-down is computed.

What are the limitations of the offline status computation?

Reports naming an unreachable external repository have an unknown code boundary, and pre-convention reports without a verifies field leave the chain unknown. Unreadable reports are reported and skipped rather than failing the whole status.