stellar-raven: Skill for Claude Code

.agents/skills/cloudflare-observability-review/SKILL.md

cloudflare-observability-review is a skill for Claude Code, Codex from stellar-experimental/stellar-raven. It costs 69 tokens per session (4,839 once invoked), scanned A, original, Apache-2.0.

A runbook for investigating what happened in live Cloudflare Workers, using request logs, invocation events, and tracing data. It also explains how to record evidence during testing or multi-agent reviews.

In plain words
What is it for?
Use it to investigate failed or unusual requests, inspect telemetry, trace agent runs, review evaluations, and decide whether Cloudflare’s data is enough or app-level logs are needed.
Why use it?
It helps connect production requests and agent runs without requiring models to pass tracking IDs. It also sets rules for protecting secrets and preserving investigation evidence.

Skill for Claude CodeCodex

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

This is stellar-experimental/stellar-raven's own configuration. It tells Claude Code and Codex how to work on stellar-raven 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 stellar-raven configures →

Reuse

Borrowing it

Nothing to install: this file belongs to stellar-experimental/stellar-raven. 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/stellar-experimental/stellar-raven/main/.agents/skills/cloudflare-observability-review/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/stellar-experimental/stellar-raven

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 cloudflare-observability-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/stellar-experimental/stellar-raven/cloudflare-observability-review/github.svg)](https://agentmods.dev/skills/stellar-experimental/stellar-raven/cloudflare-observability-review)
Your own site
<a href="https://agentmods.dev/skills/stellar-experimental/stellar-raven/cloudflare-observability-review"><img src="https://agentmods.dev/badge/skills/stellar-experimental/stellar-raven/cloudflare-observability-review/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.

agentmods 80×15 button for cloudflare-observability-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/stellar-experimental/stellar-raven/cloudflare-observability-review"><img src="https://agentmods.dev/badge/skills/stellar-experimental/stellar-raven/cloudflare-observability-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,839 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Data Exfiltration · line 98
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
How audits are shown
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 $0.00069 $0.04839
Opus 5 $0.00034 $0.02420
Sonnet 5 $0.00014 $0.00968
Haiku 4.5 $0.00007 $0.00484

Measured 10d ago against content hash d857cf680a63, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

cloudflare-observability-review scanned grade A with 1 finding 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 10d 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.

Makes network callslowCapability

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

curl -i -sS https://raven.stellar.org/mcp \
.agents/skills/cloudflare-observability-review/SKILL.md · 383 lines

How it starts

The opening of the file, as written. The whole thing — 383 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cloudflare Observability Review

Use this runbook to answer "what happened in production?" for stellar-raven-codemode using Cloudflare Workers Logs, platform invocation events, and OTel spans.

When the investigation is part of an eval round, agent-run forensic review, or other multi-agent maintenance pass, record the query inputs, Ray IDs, and verdict in the relevant round ledger (.agents/rounds/) or .agents/TODO.md so the evidence survives outside the current context window.

Principle

Prefer Cloudflare-native request identity for one invocation. Use the app's privacy-safe OAuth subject/client hashes only for cross-request attribution.

Observability works without a model-facing correlationId contract. Same-user concurrent MCP tasks are rare, and for debugging/evals we join requests by Ray ID, time window, user-agent/client marker, host/path/method/status, and auth mode. If an investigation needs stronger cross-request grouping, add privacy-safe auth subject/client fields to app logs rather than asking models to forward ids.

Safety Rules

  • Never print secrets from .env, .dev.vars, Wrangler, Cloudflare, or MCP responses.
  • Use Cloudflare API MCP for historical evidence. wrangler tail is only a convenience stream; a miss there is not evidence that logs are absent.
  • Do not copy raw IPs, IP hashes, or IP-derived fingerprints into app logs. Cloudflare platform events already expose IP-bearing request headers.
  • It is OK to query and use Cloudflare-native private/platform fields (IP-bearing headers, geo, TLS/client fingerprint fields, user-agent) inside a bounded investigation when they are needed to join or separate requests. Report them only when directly relevant; otherwise report Ray IDs, time windows, paths, statuses, and app event fields.
  • Do not infer identity from IP/geo/TLS fields unless explicitly doing an abuse review with a separate privacy decision.

What Joins Reliably

For one HTTP invocation:

  • Response cf-ray header -> Workers Logs. Strip the colo suffix: a15a1ed37fa5b049-ATL -> a15a1ed37fa5b049.
  • Workers app JSON logs: $metadata.type = "cf-worker".
  • Workers platform invocation logs: $metadata.type = "cf-worker-event".
  • OTel spans: $metadata.type = "span", joined by cloudflare.ray_id.

Read the full file on GitHub · 383 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. 10d ago First seen · 383 lines · 69 tokens per session scan A d857cf680a63

Subscribe to this mod's changes

cloudflare-observability-review is a skill published in the GitHub repository stellar-experimental/stellar-raven (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 69 tokens to every session and 4,839 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

eve

Build durable backend AI agents with the eve framework. Use when creating, editing, or debugging an eve project — agent instructions, skills, tools, connections, channels, sandboxes, subagents, schedules, or evals.

ComposioHQ/composio · 47 tokens

bug-fixing

Fix defects in the Composio SDK repository with focused reproduction, root-cause analysis, regression tests, and narrow verification. Use when the user reports a bug, failing test, CI regression, runtime defect, or incorrect SDK behavior. Do not use for new feature design or broad refactors.

ComposioHQ/composio · 63 tokens

typescript-testing

Select and run TypeScript SDK verification for packages, examples, type checks, linting, builds, Vitest suites, and runtime E2E tests. Use when adding tests, diagnosing TypeScript CI, choosing a focused test command, or validating TypeScript package changes. Do not use for Python-only checks.

ComposioHQ/composio · 65 tokens

azure-kubernetes-automatic-readiness

Assess Kubernetes workloads and cluster configuration for AKS Automatic compatibility. Identifies incompatibilities, generates fixes, and guides migration from AKS Standard to AKS Automatic. WHEN: migrate to AKS Automatic, check AKS Automatic readiness, validate manifests for Automatic, assess cluster for Automatic…

microsoft/skills · 87 tokens

cli-e2e

Write, modify, or debug Docker-based Composio CLI end-to-end tests under ts/e2e-tests/cli, including binary invocation, fixture isolation, output assertions, and package manifests. Use for CLI E2E test suites only; use cli-command for CLI source implementation.

ComposioHQ/composio · 62 tokens

python-testing

Select and run Python SDK verification with nox, Makefile targets, Ruff, mypy, pytest markers, sanity tests, type inference checks, and build checks. Use when adding Python tests, diagnosing Python CI, or validating Python SDK/provider changes. Do not use for TypeScript-only checks.

ComposioHQ/composio · 62 tokens