القائمة
Emit OTEL spans when an agent starts and completes its task. Use when instrumenting an agent to measure duration, success rate, and invocation patterns.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
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.
استنادا إلى تصنيف SOC المهني
| name | agent-invocation-tracking |
| description | Emit OTEL spans when an agent starts and completes its task. Use when instrumenting an agent to measure duration, success rate, and invocation patterns. |
| license | MIT |
| compatibility | Claude Code, GitHub Copilot, OpenCode, Cursor, Codex, Gemini CLI |
| metadata | {"author":"paruff","suite":"uFawkesAI"} |
Load trigger:
"load agent-invocation-tracking skill"> DORA: Cap 2 (Observability) Token cost: Low
Track when agents start, complete, and how long they take. Enables answering: "Which agents are used most? Which take longest? Which fail most often?"
agent.invocation.startedEmit when the agent begins processing.
Attributes:
| Attribute | Type | Description |
|---|---|---|
agent.name | string | Agent identifier (matches filename without .md) |
session_id | string | Unique invocation identifier |
mode | string | Operational mode (if agent supports multiple) |
trigger | string | What triggered this invocation (human request, CI, direct invocation) |
input_files | string[] | Files read as context for this invocation |
agent.invocation.completedEmit when the agent finishes.
Attributes (all from started, plus):
| Attribute | Type | Description |
|---|---|---|
duration_ms | integer | Wall-clock duration in milliseconds |
total_skills_loaded | integer | Count of skills loaded during invocation |
total_findings | integer | Count of findings produced |
decision | string | Final decision (PASS/FAIL/BLOCKED/APPROVE/REQUEST_CHANGES/ESCALATE) |
agent.invocation.failedEmit when the agent encounters an error it cannot recover from.
Attributes (all from started, plus):
| Attribute | Type | Description |
|---|---|---|
error | string | Error message or summary |
stage | string | Stage where failure occurred (validate, execute, report) |
After completing the task, write the Phase 0 log entry (.agents/logs/YYYY-MM-DD.jsonl).
The telemetry spans can be derived from the log data by the aggregation script.