| name | auto-skill-build-agent-reliability-loop |
| description | Design production agent reliability loops across traces, evals, guardrails, gateways, model budgets, and shadow tests. Use when shipping AI/agent workflows that need simulate/evaluate/protect/monitor/optimize structure, gateway policy, eval suites, guardrail rollout, or trace-to-regression feedback. Skip when the task only needs a local Codex run ledger; use `$agent-observability` instead.
|
Agent Reliability Loop
Generated by: Codex Supercharge maintenance automation.
Goal: turn an agent workflow into a closed loop where production traces become
eval cases, eval failures become guardrails or fixes, and gateway policy keeps
cost, routing, and tool risk bounded.
Skip When
- The user only wants local Codex run/cost tracking.
- The work is a single benchmark or experiment with no production surface.
- The task is only MCP conformance; use
$auto-skill-build-mcp-conformance-harness.
Workflow
- Map the surface: list user journeys, models, tools, data classes,
side effects, risk levels, and quality/cost/latency targets.
- Instrument first: require request IDs, trace/span IDs, session IDs,
model/provider, token/cost, cache, fallback, guardrail, and tool metadata.
- Build eval bundles: create golden cases for task success, prompt
conformance, tool correctness, unsafe requests, PII/secrets, latency, and
cost. Keep judge prompts and heuristic checks versioned.
- Set gateway policy: define provider mapping, model fallbacks, cache
rules, virtual keys, budgets, rate limits, privacy redaction, and audit logs.
- Stage guardrails: run new pre/post checks in log or monitor mode first,
then enforce only after false positives and fail-open/fail-closed behavior
are explicit.
- Shadow safely: mirror sampled traffic to candidate models or prompts
only when shadow calls cannot trigger external side effects.
- Close the loop: cluster failed traces, match nearest successful traces,
add representative failures to evals, patch prompts/tools/policies, then
rerun the bundle before release.
Commands
rg -n "trace|span|cost|tokens|guardrail|fallback|budget|rate limit|request_id" .
rg -n "eval|rubric|judge|golden|dataset|experiment|shadow|canary" .
rg -n "tool|mcp|side effect|webhook|shell|filesystem|credential" .
Output
# Agent Reliability Plan
## Surface
## Instrumentation
## Eval Bundle
## Gateway Policy
## Guardrail Rollout
## Shadow Or Canary Plan
## Trace-To-Regression Loop
## Risks And Trust Notes
## Validation
Validation
- Every production route has at least one trace and one regression case.
- Every blocking guardrail has a false-positive review path.
- Every budget/rate limit has an owner and an alert threshold.
- Shadow/canary traffic cannot write to tools, accounts, payments, or user data.
Read references/future-agi-agent-reliability-loop.md for the source-backed
pattern and risk notes.
