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/nonlinear-xyz/factory-kit/factory-observabilitynpx skills add nonlinear-xyz/factory-kit --skill factory-observabilitygit clone --depth 1 https://github.com/nonlinear-xyz/factory-kitWrote 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/nonlinear-xyz/factory-kit/factory-observability)<a href="https://agentmods.dev/skills/nonlinear-xyz/factory-kit/factory-observability"><img src="https://agentmods.dev/badge/skills/nonlinear-xyz/factory-kit/factory-observability.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 | $0.00096 | $0.02364 |
| Opus 5 | $0.00048 | $0.01182 |
| Sonnet 5 | $0.00019 | $0.00473 |
| Haiku 4.5 | $0.00010 | $0.00236 |
Grade A, and why
factory-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 6d 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 — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Factory observability
Each section leads with Principle (one sentence, stack-agnostic), then Why (constraint → option → tradeoff), then Recipe (the PostHog / Sentry / pino / structlog shape we use), and Failure mode when there's one to name.
Day-one stack — observability before features
Principle. PostHog + Sentry + trace IDs + structured logs go in on day one, before the first feature ships.
Why. Observability is the build's most asymmetric cost-vs-value: cheap on day one (an SDK install and a config block), expensive to backfill (every event needs a redeploy, session-replay data starts empty, six months of usage history is lost). The trap is treating it as "we'll add when we need it" — by the time you need it, the data you'd want doesn't exist.
Recipe.
| Layer | Tool | Purpose |
|---|---|---|
| Product analytics | PostHog | Per-feature usage, funnels, session replay |
| Error tracking | Sentry | Exceptions, performance, source maps |
| Audit log | DB table (admin_actions or audit_log) |
Mutation provenance, regulatory compliance |
| Request tracing | Trace ID middleware + logs | Cross-service debugging |
| Structured logs | pino (Node) / structlog (Python) |
Searchable, machine-parseable |
PostHog — client setup with ingest rewrite
Principle. PostHog ingest goes through your own domain via Next.js rewrites; ad-blockers drop direct PostHog calls.
Why. Browser-level ad-blockers (uBlock, Brave's shield) recognize i.posthog.com and drop ~30% of events in aggregate. Routing through /ingest on your own domain bypasses the blocklist — the events arrive, the analytics are accurate. The cost is one rewrite block; the savings are ~30% of every funnel calculation you'll ever do.
Recipe.
// src/components/PostHogProvider.tsx
'use client';
import posthog from 'posthog-js';
import { PostHogProvider } from 'posthog-js/react';
import { useEffect } from 'react';
if (typeof window !== 'undefined') {
posthog.init(process.env.NEXT_PUBLIC_POSTHOG_KEY!, {
api_host: '/ingest', // proxied — see rewrites below
capture_pageview: false, // we call manually with route context
person_profiles: 'identified_only',
});
}
export function PHProvider({ children }: { children: React.ReactNode }) {
return <PostHogProvider client={posthog}>{children}</PostHogProvider>;
}
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.
- 6d ago First seen · 228 lines · 96 tokens per session scan A 6d90a1974707
factory-observability is a skill published in the GitHub repository nonlinear-xyz/factory-kit (9 stars, last pushed 1mo ago), licensed MIT. It adds 96 tokens to every session and 2,364 once invoked, about $0.0005 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
hook-template
Generate hook script from template. Use when adding a new hook, wiring a PreToolUse/PostToolUse/Stop/Notification hook, or scaffolding hook config for settings.json.
agent-template
Generate custom agent from template. Use when creating a new subagent from scratch, or scaffolding an agent file with correct frontmatter.
workflow
Run the complete 5-step development workflow: focus problem → prevent over-development → test-first (TDD) → document → smart commit. Use when starting a new feature, or when the user runs /workflow or asks for the full development flow.
check-environment
Verify Claude, Codex, and Grok availability plus Director guidance, relay, agents, and skills. Audit optional hooks only when selected. Use after installation or when a native surface misbehaves.
doc-writer
Documentation templates and standards: README structure, API reference format, changelog (Keep a Changelog), and comment guidelines. Use when creating or updating documentation. Loaded automatically by the doc-writer agent.
smart-commit
Create clean Conventional Commits: inspect the diff, group related changes, run quality checks, and write type(scope) messages. Use when committing work, or when the user runs /smart-commit or asks to commit changes.