メニュー
Emit and consume telemetry spans for agent invocations, skill loads, findings, and decisions. Use when instrumenting the agent system itself or when analyzing agent behavior patterns.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Generate and maintain AI_STANCE.md for any uFawkes* repo. Use when onboarding a repo to the uFawkesAI suite, when reviewing AI policy currency, or when a new AI tool is being adopted. Implements DORA AI Capability 1.
Ensure graphify corpus is current and complete before each agent session. Define minimum AI-accessible documentation per repo. Use at session startup to verify internal context is available to AI tools. Implements DORA AI Capability 3.
15-minute JTBD + acceptance criterion exercise. Use before any spec session. Produces a discovery-brief.md that anchors the entire increment to a real user need and a measurable DORA outcome. Implements DORA AI Capability 6.
Enforce minimum documentation standard across uFawkes* repos. Use when auditing a repo before release, onboarding a new repo to the suite, or implementing roadmap item 0.6 (cross-repo README links). Directly supports DORA AI Capability 3 and the 2023 DORA finding that documentation quality amplifies all technical capabilities.
Create and manage DOJO content for platform engineering education and knowledge sharing.
Maintain AI_STANCE.md as a living document. Use quarterly or when a new AI tool is adopted. Handles review triggers, the three-bucket update process, socialization checklist, and cross-repo consistency. Companion to ai-stance skill.
| name | agent-observability |
| description | Emit and consume telemetry spans for agent invocations, skill loads, findings, and decisions. Use when instrumenting the agent system itself or when analyzing agent behavior patterns. |
| license | MIT |
| compatibility | Claude Code, GitHub Copilot, OpenCode, Cursor, Codex, Gemini CLI |
| metadata | {"author":"paruff","suite":"uFawkesAI"} |
Load trigger:
"load agent-observability skill"> DORA: Cap 2 (Observability) + Cap 6 (Reliability) Token cost: Low
Instrument the agent system itself with the same observability standards applied to application code. Agent actions become observable, measurable, and improvable.
| Span Name | When to Emit | Attributes |
|---|---|---|
agent.invocation.started | Agent begins its task | agent.name, session_id, mode |
agent.skill.loaded | Skill file is loaded for context | skill.name, skill.domain |
agent.finding.produced | A finding is identified | severity, category, actionable, manual_review_needed |
agent.decision.made | Agent produces its final decision | decision, blocker_count, finding_count |
agent.invocation.completed | Agent finishes its task | duration_ms, total_skills_loaded, total_findings |
agent.invocation.failed | Agent encounters an error | error, stage |
Phase 0 logs (.agents/logs/YYYY-MM-DD.jsonl) are the data source. Agent telemetry spans are the OTEL representation of the same events.
Mapping:
agent.invocation.started + agent.invocation.completed → one log entryagent.skill.loaded → skills_loaded[] array in log entryagent.finding.produced → each item in findings[] arrayagent.decision.made → decision and blockers fields| Skill | Purpose |
|---|---|
agent-observability/invocation-tracking | Track agent start, completion, and duration |
agent-observability/skill-load-events | Track which skills are loaded and how often |
agent-observability/finding-quality | Measure finding actionability and accuracy |
agent-observability/decision-logging | Log agent decisions for post-hoc analysis |