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 skills add jimtin/production-ai --skill error-logging-instrumentationgit clone --depth 1 https://github.com/jimtin/production-aiWrote 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/jimtin/production-ai/error-logging-instrumentation)<a href="https://agentmods.dev/skills/jimtin/production-ai/error-logging-instrumentation"><img src="https://agentmods.dev/badge/skills/jimtin/production-ai/error-logging-instrumentation/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.
<a href="https://agentmods.dev/skills/jimtin/production-ai/error-logging-instrumentation"><img src="https://agentmods.dev/badge/skills/jimtin/production-ai/error-logging-instrumentation.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00074 | $0.01097 |
| Opus 5 | $0.00037 | $0.00549 |
| Sonnet 5 | $0.00015 | $0.00219 |
| Haiku 4.5 | $0.00007 | $0.00110 |
Grade A, and why
error-logging-instrumentation 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 9d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Error Logging Instrumentation
Purpose
Use this skill to decide whether an existing web app has enough error logging to debug production failures safely, then patch gaps when the user asks for remediation. The default stance is Vercel-first and provider-aware: prefer the app's existing logging/error provider and Vercel runtime patterns before proposing a new vendor.
Operating Rules
- Start from repo truth: instructions, package scripts, routes, API handlers, server actions, jobs, auth, upload/parsing surfaces, deployment config, tests, and existing logging code.
- Use
$full-app-reviewfor broad non-mutating app audits. Use this skill for the deeper observability/error-logging workstream or for remediation. - Use Vercel observability patterns first when the repo is Vercel/Next.js based. Use
vercel:observabilityfor Vercel-specific logs, drains, OpenTelemetry, dashboards, and production log checks when available. - Do not add Sentry, Datadog, Axiom, Logtail, Honeycomb, or another provider unless the repo already uses it or the user explicitly approves.
- Do not log secrets, PII, raw document/file contents, raw prompts, tokens, cookies, session IDs, payment details, or full provider payloads.
- For code changes, add targeted unit, integration, and browser/E2E coverage for each changed failure path. Run
$test-readiness-preflightbefore expensive gates. - Before push-readiness, run
$security-threat-modelfor logging/privacy surfaces, dependency audit, and a repo-root scoped gitleaks scan.
Workflow
-
Baseline the app.
- Read repo instructions and canonical local/container gates.
- Identify framework, deployment target, route tree, API/server actions, background jobs, auth, storage, uploads, external providers, admin paths, and tests.
- Run
scripts/logging_inventory.py <repo> --format markdownwhen useful for a static first pass. Treat it as evidence collection only, not a sufficiency decision.
-
Map critical failure surfaces.
- Use
references/coverage-matrix.md. - Include client routes, API handlers, server actions, webhooks, cron/jobs, admin mutations, uploads/parsers, payments, auth callbacks, database migrations, provider calls, and deployment/runtime failures.
- For each surface, record the failure, user impact, operator question, current logging/capture evidence, and missing proof.
- 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.
- 9d ago First seen · 64 lines · 74 tokens per session scan A 11ecc5b9aa36
error-logging-instrumentation is a skill published in the GitHub repository jimtin/production-ai (1 stars, last pushed 2mo ago), licensed MIT. It adds 74 tokens to every session and 1,097 once invoked, about $0.0004 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
bug-detective
This skill should be used when the user asks to "debug this", "fix this error", "investigate this bug", "troubleshoot this issue", "find the problem", "something is broken", "this isn't working", "why is this failing", or reports errors/exceptions/bugs. Provides systematic debugging workflow and common error patterns.
systematic-debugging
A four-phase method for investigating software bugs and test failures before changing code. It focuses on finding and confirming the underlying cause.
bensz-collect-bugs
A process for recording bugs caused by defects in Bensz skills. It stores a structured local report and can publish one only when the user explicitly asks.
grace-fix
Debug and fix issues in a GRACE 4 project using .grace semantic navigation, assertions, and verification evidence.
bug-fix-protocol
8-step disciplined bug-fix protocol that treats every production bug as two failures — the code defect itself and the testing system that allowed it through. Use when fixing a production bug, investigating a regression, writing a post-mortem, or auditing a missed defect. Triggers on "fix this bug", "production bug"…
code-remediate
Apply selected review fixes; bare PR targets use current online items, while PR +review adds the latest matching artifact.