Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add easingthemes/dx-aem-flow --skill auto-doctorgit clone --depth 1 https://github.com/easingthemes/dx-aem-flowWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/easingthemes/dx-aem-flow/auto-doctor)<a href="https://agentmods.dev/skills/easingthemes/dx-aem-flow/auto-doctor"><img src="https://agentmods.dev/badge/skills/easingthemes/dx-aem-flow/auto-doctor/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/easingthemes/dx-aem-flow/auto-doctor"><img src="https://agentmods.dev/badge/skills/easingthemes/dx-aem-flow/auto-doctor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00035 | $0.02960 |
| Opus 5 | $0.00017 | $0.01480 |
| Sonnet 5 | $0.00007 | $0.00592 |
| Haiku 4.5 | $0.00003 | $0.00296 |
Grade A, and why
auto-doctor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You run a health check on the AI automation setup. Each project is self-contained — it owns its own Lambda and pipelines. Legacy profiles consumer, pr-only, and pr-delegation are treated as per-project (warn to re-run /auto-init if found).
0. Read Config
Read .ai/automation/infra.json. If missing: "Run /auto-init first." STOP.
Extract automationProfile. If value is consumer, pr-only, or pr-delegation: warn ⚠ Legacy profile '${profile}' — re-run /auto-init to migrate to per-project model. and treat as per-project for the remainder of this check.
Also extract: pipeline entries (only those without "disabled": true), region, prefix, Lambda function names.
1. Local File Integrity
Config files:
infra.json— no remaining{{PLACEHOLDER}}values (check for{{)repos.json— optional; validate only if present. No pipeline, Lambda, or skill readsrepos.jsonat runtime — it is documentation-only intent (future cross-repo discovery), so its absence is expected and harmless, especially for CLI-pipeline-only consumers (it was deliberately removed from some).- present + valid JSON →
✓ - present + invalid JSON →
✗ invalid JSON(the only failing case — a hand-edited file that won't parse) - absent →
— optional (unused — not read by any pipeline or agent)— NOT an issue; do NOT report✗, and do NOT let it affect the Overall verdict.
- present + valid JSON →
Check infra.json for unfilled placeholders:
python3 -c "
import json, re
with open('.ai/automation/infra.json') as f:
content = f.read()
placeholders = re.findall(r'\{\{[^}]+\}\}', content)
if placeholders:
print('UNFILLED PLACEHOLDERS:', list(set(placeholders)))
else:
print('OK — no unfilled placeholders')
"
Pipeline YAMLs (all profiles):
For each enabled pipeline entry in infra.json, check that the YAML file referenced in pipelines.<agent>.yaml exists on disk:
- Exists →
✓ - Missing →
✗ MISSING
Lambda handlers (when Lambda agents are enabled):
Skip Lambda file checks if no Lambda-based agents are enabled (i.e., only PR Review, PR Answer, and Eval are in the enabled list — those run as ADO pipelines without Lambda).
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 229 lines · 35 tokens per session scan A 19b54982d1b1
auto-doctor is a skill published in the GitHub repository easingthemes/dx-aem-flow (6 stars, last pushed 7d ago), licensed MIT. It adds 35 tokens to every session and 2,960 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
gke-ai-troubleshooting-jobset-interruption
Diagnoses GKE JobSet interruptions, restarts, and preemptions for AI/ML training workloads autonomously. Use when troubleshooting JobSet restart loops, spot VM preemptions, node readiness failures, host VM issues, or coordinator worker crashes. Don't use for general GKE cluster creation, basic workload deployment, or…
gke-workload-troubleshooting
Diagnoses GKE workload failures (CrashLoopBackOff, OOMKilled, ImagePullBackOff, Pending, etc.) via logs and events. Use when pods fail to start or crash repeatedly. Don't use for GKE cluster infrastructure provisioning, node pool creation, or non-Kubernetes Google Cloud services.
gke-node-notready
Diagnoses GKE nodes reporting NotReady or Unknown status by inspecting node conditions, events, kubelet/containerd logs, and node metrics, then proposing safe remediations. Use when nodes show NotReady, when the kubelet stops posting node status, or when workloads are evicted or stuck Pending due to node health. Don't…
gke-ai-troubleshooting-handle-disruption-gpu-tpu
Diagnoses, predicts, and mitigates node disruptions during Compute Engine host maintenance and hardware or software maintenance events for GPU and TPU workloads on GKE. Use when diagnosing node disruptions, predicting host maintenance events on GPU/TPU nodepools, inspecting node interruption PromQL metrics, auditing…
agentcore-investigation
Investigate Bedrock AgentCore runtime sessions via CloudWatch Logs Insights — resolve session/trace IDs, query OTEL spans, filter noise, build timelines. Use when debugging AgentCore agent sessions, tracing tool calls, or analyzing latency.
troubleshoot-sandbox
Troubleshoot OpenSandbox issues by running diagnostics (logs, inspect, events, summary) via CLI or HTTP API to diagnose sandbox failures like OOM, crash, image pull errors, network problems, etc.