divine-mobile: Skill for Claude Code

.agents/skills/fastly-compute-deployment-debugging/SKILL.md

fastly-compute-deployment-debugging is a skill for Claude Code, Codex from divinevideo/divine-mobile. It costs 97 tokens per session (1,262 once invoked), scanned C, original, MPL-2.0.

A troubleshooting guide for Fastly Compute deployments that appear successful but serve old content or 404 errors. Fastly Compute runs code at edge locations around the world.

In plain words
What is it for?
Use it to compare direct and custom-domain responses, test cached errors, check versions, and investigate missing routes after deployment.
Why use it?
It helps identify whether the problem is deployment, caching, domain configuration, or different edge locations returning different results.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code; installed under .agents/ (shared by several agents).

This is divinevideo/divine-mobile's own configuration. It tells Claude Code and Codex how to work on divine-mobile itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything divine-mobile configures →

Reuse

Borrowing it

Nothing to install: this file belongs to divinevideo/divine-mobile. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/divinevideo/divine-mobile/main/.agents/skills/fastly-compute-deployment-debugging/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/divinevideo/divine-mobile

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for fastly-compute-deployment-debugging

README.md
[![agentmods](https://agentmods.dev/badge/skills/divinevideo/divine-mobile/fastly-compute-deployment-debugging.svg)](https://agentmods.dev/skills/divinevideo/divine-mobile/fastly-compute-deployment-debugging)
Your own site
<a href="https://agentmods.dev/skills/divinevideo/divine-mobile/fastly-compute-deployment-debugging"><img src="https://agentmods.dev/badge/skills/divinevideo/divine-mobile/fastly-compute-deployment-debugging.svg" alt="Measured on agentmods" height="20"></a>
Per session 97 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,262 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00097 $0.01262
Opus 5 $0.00048 $0.00631
Sonnet 5 $0.00019 $0.00252
Haiku 4.5 $0.00010 $0.00126

Measured 7d ago against content hash 21eaa3076753, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade C, and why

fastly-compute-deployment-debugging scanned grade C with 2 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 7d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf pkg target

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl https://your-service.edgecompute.app/version
.agents/skills/fastly-compute-deployment-debugging/SKILL.md · 158 lines

How it starts

The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fastly Compute Deployment Debugging

Problem

After deploying to Fastly Compute, requests return stale content or 404s even though:

  • fastly compute publish reported success
  • The new version shows as "active" in fastly service-version list
  • The code is correct and works locally

Context / Trigger Conditions

  • Version endpoint returns old version string after deployment
  • New routes/features return 404
  • fastly purge --all doesn't fix the issue
  • Requests with cache buster (?v=random) work but regular requests don't
  • fastly domain list doesn't show your custom domain
  • Different POPs return different results

Solution

1. Verify Code is Actually Deployed

# Check the direct edgecompute.app URL (bypasses custom domain config)
curl https://your-service.edgecompute.app/version

# Compare to custom domain
curl https://your-custom-domain.com/version

If edgecompute.app works but custom domain doesn't, it's a domain configuration issue.

2. Diagnose Cached Error Responses

The most common issue: 404s get cached at edge POPs before new code propagates.

# Test with cache buster
curl "https://your-domain.com/endpoint?bust=$RANDOM"

# Test without
curl "https://your-domain.com/endpoint"

If cache-busted works but regular doesn't = cached error response.

Fix: Wait 2-5 minutes for full propagation, then purge:

fastly purge --all --service-id YOUR_SERVICE_ID

3. Check Domain Configuration (Two APIs!)

Fastly has TWO domain management systems:

System CLI Command API Endpoint
Classic Domains fastly domain list /service/{id}/version/{ver}/domain
Versionless Domains (not shown in CLI) /domain-management/v1/domains

If fastly domain list doesn't show your domain, check the versionless API:

# Get your API token
TOKEN=$(fastly profile token)

# Query domain-management API
curl -s -H "Fastly-Key: $TOKEN" \
  "https://api.fastly.com/domain-management/v1/domains?filter%5Bfqdn%5D=your-domain.com"

Read the full file on GitHub · 158 lines

Changes

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.

  1. 7d ago First seen · 158 lines · 97 tokens per session scan C 21eaa3076753

Subscribe to this mod's changes

fastly-compute-deployment-debugging is a skill published in the GitHub repository divinevideo/divine-mobile (265 stars, last pushed today), licensed MPL-2.0. It adds 97 tokens to every session and 1,262 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

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…

google/skills · 83 tokens

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.

google/skills · 69 tokens

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…

google/skills · 112 tokens

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…

google/skills · 117 tokens

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.

awslabs/mcp · 52 tokens

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.

opensandbox-group/OpenSandbox · 48 tokens