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/kid-sid/codex-spellbook/observabilitynpx skills add kid-sid/codex-spellbook --skill observabilitygit clone --depth 1 https://github.com/kid-sid/codex-spellbookWhat 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 | $0.00046 | $0.06127 |
| Opus 5 | $0.00023 | $0.03063 |
| Sonnet 5 | $0.00009 | $0.01225 |
| Haiku 4.5 | $0.00005 | $0.00613 |
Grade A, and why
observability 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 2d 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 — 664 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Observability
Observability is the practice of instrumenting systems so you can understand their internal state from external outputs — logs, metrics, and traces.
When to Activate
- Adding logging to a new service or endpoint
- Setting up Prometheus metrics for a service
- Implementing distributed tracing across services
- Writing alerting rules or on-call runbooks
- Defining SLOs and error budgets for a service
- Building a Grafana dashboard for a service
- Debugging a production issue using logs, metrics, or traces
The Three Pillars
| Pillar | Question it answers | Best tool | When to reach for it |
|---|---|---|---|
| Logs | "What happened?" | structlog, pino, slog | Debugging specific errors, audit trails |
| Metrics | "How is the system performing?" | Prometheus | Trending, alerting, capacity |
| Traces | "Why is this slow / where did it fail?" | OpenTelemetry | Latency debugging, distributed request flow |
OpenTelemetry is the unifying standard across all three pillars: one SDK for logs, metrics, and traces, vendor-agnostic, with exporters to any backend (Grafana, Datadog, Honeycomb, Jaeger, etc.).
Structured Logging
Always emit logs as JSON. Human-readable plaintext is fine in development, but production logs must be machine-parseable. Never log sensitive data (PII, card numbers, passwords, tokens).
Mandatory Fields
Every log line must include:
| Field | Type | Example |
|---|---|---|
timestamp |
ISO 8601 | 2024-01-15T10:30:00.000Z |
level |
string | INFO |
service |
string | payment-service |
trace_id |
string | abc123... |
span_id |
string | def456... |
request_id |
string | UUID per HTTP request |
message |
string | Human-readable description |
Log Levels
| Level | When to use | Example |
|---|---|---|
| DEBUG | Verbose dev-only detail | "Entering validatePayment()" |
| INFO | Normal operational events | "Payment processed for order 123" |
| WARN | Unexpected but recoverable | "Retry attempt 2/3 for order 123" |
| ERROR | Failure that needs attention | "Payment declined: card expired" |
| FATAL/CRITICAL | Service cannot continue | "DB connection pool exhausted" |
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.
- 2d ago First seen · 664 lines · 46 tokens per session scan A ae755aaa8c11
observability is a skill published in the GitHub repository kid-sid/codex-spellbook (21 stars, last pushed 3mo ago), licensed MIT. It adds 46 tokens to every session and 6,127 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
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…
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.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.