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 agentmods add skills/culiops/culiops-agent/runtime-tracenpx skills add culiops/culiops-agent --skill runtime-tracegit clone --depth 1 https://github.com/culiops/culiops-agentWhat 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 | $0.00131 | $0.08191 |
| Opus 5 | $0.00066 | $0.04096 |
| Sonnet 5 | $0.00026 | $0.01638 |
| Haiku 4.5 | $0.00013 | $0.00819 |
Grade A, and why
runtime-trace 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 yesterday.
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 — 432 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Runtime Trace
Produce a self-contained runtime profile of an AWS service by querying four cheap, read-only data sources — Cost Explorer (the spend oracle), CloudTrail LookupEvents (the control-plane log), CloudWatch GetMetricData (activity baselines, targeted), and Resource Explorer (cross-region inventory) — and writing the result to .culiops/runtime-trace/<service>-runtime-profile.md in the target repo. Six gates, hard cost cap of $1.00 per run, every claim traceable to an API call.
This skill answers four questions that infrastructure-as-code discovery cannot:
- What's actually billing? (Cost Explorer reveals services and usage types diagrams omit.)
- Who's actually calling it? (CloudTrail surfaces IAM principals, deploy events, cross-account access — last 90 days.)
- What does its activity look like? (CloudWatch baselines for the four golden signals — traffic, latency, errors, saturation — over 14 days.)
- Where does it actually live? (Resource Explorer finds tagged resources outside the assumed primary region.)
runtime-trace is a sibling to service-discovery (which catalogs resources from IaC or from live cloud APIs in real-discovery mode). It is not a cost-investigation tool (that's cloud-cost-investigate) and not an orchestrator — a future service-takeover skill will compose service-discovery + runtime-trace + interview/readiness steps into an end-to-end takeover workflow.
References
The design draws on the following intellectual foundations. They are cited here so a future maintainer (or you, six months from now) understands the why behind the workflow.
| Reference | What it informs |
|---|---|
| Observability Engineering (Majors, Fong-Jones, Miranda) — Ch. 1–5, 8 | The "high-cardinality / slice-retroactively" framing. Justifies querying Cost Explorer and CloudTrail (queryable after-the-fact) instead of pre-built dashboards. |
| Site Reliability Engineering (Google) — Ch. 32 "The Evolving SRE Engagement Model" | Source of the service-takeover / Production Readiness Review pattern. Justifies the gate-driven workflow and the capability-detection-before-query step. |
| Site Reliability Engineering — Ch. 6 "Monitoring Distributed Systems" | Source of the four-golden-signals framing (traffic, latency, errors, saturation). Justifies the CloudWatch metric set per resource type. |
| Working Effectively with Legacy Code (Feathers) | "Characterization, not assumption" — prove what the system does before assuming what it should do. Justifies the "every claim cites its API call" discipline. |
| The Pragmatic Programmer (Hunt, Thomas) — "Tracer Bullets" chapter | Source-by-source gate model: thin end-to-end probe per source before fanning out. Justifies per-source approval at Gate 4. |
| AWS Well-Architected Framework — Operational Excellence pillar | Source of the readiness-question framing that downstream service-takeover will use. |
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday First seen · 432 lines · 131 tokens per session scan A 271f132af0f9
runtime-trace is a skill published in the GitHub repository culiops/culiops-agent (2 stars, last pushed 1mo ago), licensed MIT. It adds 131 tokens to every session and 8,191 once invoked, about $0.0007 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.