agentos-diagnostics
Establish falsifiable causality for a reported software defect. Use before a First or Second Mate briefs a bug Scout, when evaluating a diagnostic report, and before authorizing implementation from that report.
- License 许可
- MIT
- 所属仓库
- akua-dev/agentos
- 最近更新
- 2026-11-09
- Stars
- ★ 8
- Forks
- 0
01 前言 Front Matter
- name
- agentos-diagnostics
- description
- Establish falsifiable causality for a reported software defect. Use before a First or Second Mate briefs a bug Scout, when evaluating a diagnostic report, and before authorizing implementation from that report.
02 资源文件 1
- 参考文档agents/openai.yaml203 B
03 SKILL.md 正文
Diagnose a reported defect
Keep project investigation delegated. This Skill owns the evidence contract the supervising Mate puts into the brief and applies to the returned report.
Establish the observed behavior
- Start from the end-user path, not an internal error or favored hypothesis.
- Require a safe end-to-end reproduction. If that is impossible, name the limitation and the closest non-equivalent representative path.
- Record expected behavior, observed behavior, setup, inputs and repeatability.
- Keep these facts separate:
- trigger: the event or transition that starts the faulty behavior;
- mask: independent state, timing, cache, configuration or path that hides or exposes it;
- symptom: what the user or operator observes.
Test the explanation
- Compare the failing path with a proven path where the intended behavior works. Find their earliest meaningful divergence across inputs, state, dependencies, timing and control flow.
- Inspect relevant blame, commits, migrations and prior implementations when they clarify the intended invariant. A nearby recent change is not causal by proximity.
- Test the smallest counterfactual that should change the outcome if the leading explanation is true. Change one condition at a time when practical.
- Name evidence that would falsify the explanation and seek it deliberately. Preserve contradictions and uncertainty.
- Require the final causal boundary to explain both failure and success.
Route the result
- The Scout report must separate observations, hypotheses and unresolved uncertainty. It is evidence, not authority to edit code.
- The supervising Mate evaluates the report. If a load-bearing element is absent, dispatch a focused follow-up instead of accepting confidence as proof.
- Load
$agentos-decisionsbefore completing the Scout when the report exposes a genuine Captain choice. - When implementation is authorized, create a ship Assignment and carry the end-user reproduction into regression verification. Do not promote Scout scratch edits into the delivered worktree.
04 同仓库更多 Skills
example-replacement
Reconcile the example replacement AgentOS distribution.
example-additive
Inspect the example additive AgentOS behavior.
agentos-upgrade
Upgrade one persistent AgentOS Mate or, from First Mate with exact Captain authority, every active persistent Mate in one Fleet to an exact published stable release, including its run-once released database migrations. Use for stable First- or Second-Mate updates, resumed post-replacement verification, and authorized rollback boundaries. Do not use for dogfood, Crewmates, provisioning, retired Mates, services, or another Fleet.
agentos-supervision
Reconcile and supervise an AgentOS Mate's direct reports across PostgreSQL, Kubernetes, Herdr, PVCs, and Git. Use at every First- or Second-Mate session start, after restart or compaction, while delegated work is active, when Inbox or runtime state changes, and for blocked, stale, stuck, failed, interrupted, or recovering agents.
agentos-secrets
Safely create, retry, rotate, take over, roll back, project, and revoke AgentOS-managed Kubernetes Secrets without retaining or printing credential bytes. Use whenever an AgentOS workflow moves credential files into Kubernetes, changes an existing managed Secret, verifies a projected credential, encounters conflicting Secret ownership or legacy annotations, or retires a Kubernetes-delivered credential.
agentos-runtime
Inspect, create, and operate AgentOS runtime pods, Kustomize overlays, Herdr sessions, Mise toolchains, agent worktrees, terminals, PVCs, Kubernetes health, attach paths and runtime recovery. Use for normal First- or Second-Mate Kubernetes operations, child-Agent workload creation, tool resolution, stuck-agent debugging, remote terminal access, pod or session recovery, and readiness diagnosis.