Borrowing it
Nothing to install: this file belongs to nyktora/noctrace. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/nyktora/noctrace/main/.claude/skills/auto-scan/SKILL.mdgit clone --depth 1 https://github.com/nyktora/noctraceWrote 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/nyktora/noctrace/auto-scan)<a href="https://agentmods.dev/skills/nyktora/noctrace/auto-scan"><img src="https://agentmods.dev/badge/skills/nyktora/noctrace/auto-scan.svg" alt="Measured on agentmods" 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 | $0.00124 | $0.01929 |
| Opus 5 | $0.00062 | $0.00964 |
| Sonnet 5 | $0.00025 | $0.00386 |
| Haiku 4.5 | $0.00012 | $0.00193 |
Grade A, and why
auto-scan 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 — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auto-Scan: Provider & Competitor Intelligence
You are a product intelligence analyst for noctrace, an open-source multi-provider AI coding agent observability tool. Your job is to scan upstream providers and competitor tools, then produce an actionable feature list.
Noctrace currently supports: Claude Code, OpenAI Codex CLI, and GitHub Copilot Chat.
When to run
- On demand when the user invokes
/auto-scan - Proactively when starting a session if the last scan in
docs/research/is older than 7 days
Scan targets
Upstream providers (what they ship = what we can observe)
| Provider | What to search for | Why it matters |
|---|---|---|
| Claude Code | Changelog, new JSONL record types, new hook events, new tools, OTel changes, new agent features | New records = new waterfall rows. New hooks = new real-time events. |
| GitHub Copilot | VS Code Copilot Chat updates, agent mode changes, new tool IDs, session file format changes, OTel support | New tool IDs need mapping. Format changes can break the parser. |
| Codex CLI | GitHub releases, new JSONL event types, new tools, session format changes | Same as Claude Code but for the Codex provider. |
Competitors (what they build = what users expect)
| Competitor | URL / search term | What to look for |
|---|---|---|
| claude-devtools | github.com/matt1398/claude-devtools | Context forensics, subagent trees, notification triggers |
| Cogpit | cogpit.dev or search "cogpit claude code" | Desktop app features, real-time dashboard, file attention |
| Agent Watch | agent-watch.com | Multi-agent monitoring, remote control, team-wide dashboards |
| ccusage | github.com/ryoppippi/ccusage | Cost tracking, session reports, Codex support |
| claude-code-viewer | github.com/d-kimuson/claude-code-viewer | Web client, interactive sessions, project management |
| Simon Willison Timeline | tools.simonwillison.net/claude-code-timeline | Timeline visualization, UI innovations |
| Datadog/Dynatrace/SigNoz | Search "[platform] claude code monitoring" | Enterprise observability features noctrace could do locally |
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 · 202 lines · 124 tokens per session scan A d602f377006b
auto-scan is a skill published in the GitHub repository nyktora/noctrace (5 stars, last pushed 4mo ago), licensed MIT. It adds 124 tokens to every session and 1,929 once invoked, about $0.0006 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
langsmith-observability
LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.
phoenix-observability
Open-source AI observability platform for LLM tracing, evaluation, and monitoring. Use when debugging LLM applications with detailed traces, running evaluations on datasets, or monitoring production AI systems with real-time insights.
agent-inspect
Local evidence debugger and trajectory-test toolkit for TypeScript AI agents. Use when capturing framework-faithful traces, asserting TraceContract/TraceFacts, packaging Evidence v2, or inspecting local runs over read-only MCP (gettracefacts).
sre-expert
Expert-level site reliability engineering, SLOs, incident management, and operational excellence. Use when the user mentions reliability, monitoring, incident management, SLOs, or observability, or when the task involves SRE Fundamentals, Reliability Practices, SRE Principles, or On-Call.
debugging-workflow
Find the cause of a defect by hypothesis and bisection rather than by guessing, then fix it behind a regression test. Use when the user reports a bug, a crash, a test that fails intermittently, a performance regression or a production incident, asks why code behaves unexpectedly, or when the task involves reproducing…
linkerd-expert
Expert-level Linkerd service mesh management, traffic control, reliability, and production operations. Use when the user mentions service mesh, Kubernetes, microservices, mTLS, or observability, or when the task involves Linkerd Architecture, Mesh Injection, Traffic Management, or Reliability Features.