evlog is a TypeScript-first logging and observability project built around wide events and structured errors across runtimes. It is intended to help developers record application behavior and diagnose failures.
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 HugoRCD/evlog --skill cost-watchdoggit clone --depth 1 https://github.com/HugoRCD/evlogWrote 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/hugorcd/evlog/cost-watchdog)<a href="https://agentmods.dev/skills/hugorcd/evlog/cost-watchdog"><img src="https://agentmods.dev/badge/skills/hugorcd/evlog/cost-watchdog.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00055 | $0.01372 |
| Opus 5 | $0.00028 | $0.00686 |
| Sonnet 5 | $0.00011 | $0.00274 |
| Haiku 4.5 | $0.00006 | $0.00137 |
Grade A, and why
cost-watchdog 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cost and model watchdog
A recurring read of how evlog spends its model budget and whether the models in use are still the right ones. Run it weekly, on the last full week. Grounded in the AI Gateway report and the current model landscape, never in your memory of prices.
The core question: for every surface, is the model it runs still a sensible buy? The honest answer is often "yes, no change." A quiet week is a real result.
What the report gives you
ai_gateway__report with groupBy: 'tag' returns one row per tag value scoped to the current environment: the evi:env:* row (the total) plus one evi:surface:* row per surface. Each row carries total_cost, market_cost, input_tokens, output_tokens, cached_input_tokens, reasoning_tokens and request_count. groupBy: 'model' returns one row per model.
The surface list is whatever evi:surface:* rows the report actually returns. Do not assume the set; read it from the data.
Resources
Open these directly instead of searching; they are the stable home for everything the model-landscape step needs.
- AI Gateway model catalog, as JSON (pricing and capabilities for every model in one fetch):
https://ai-gateway.vercel.sh/v1/models - AI Gateway models browser (human-readable, filter by provider, pricing, latency, throughput):
https://vercel.com/ai-gateway/models - AI Gateway docs, models & providers:
https://vercel.com/docs/ai-gateway/models-and-providers - Model quality leaderboard (ex-LMArena, blind A/B human preference Elo):
https://arena.ai/leaderboard - Independent cost-efficiency and benchmarks (Intelligence Index, Cost per Task, speed):
https://artificialanalysis.ai/
Use web_search/web_fetch only for what these do not cover, such as a candidate model's fit for a specific surface. Every figure cited still needs a source and a recency.
Steps
1. Define the window
Run Monday morning. Cover the last 7 full days ending yesterday, and pull the 7 days before that as the comparison window, so every drift figure is period-over-period.
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 · 80 lines · 55 tokens per session scan A 4d9c46cd0ced
cost-watchdog is a skill published in the GitHub repository HugoRCD/evlog (1,841 stars, last pushed yesterday), licensed MIT. It adds 55 tokens to every session and 1,372 once invoked, about $0.0003 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
upgrade-stripe
Guide for upgrading Stripe API versions and SDKs.
stripe-best-practices
Best practices for building a Stripe integrations.
run-tests
Runs .NET tests with dotnet test. Use when user says "run tests", "execute tests", "dotnet test", "test filter", "tests not running", or needs to detect the test platform (VSTest or Microsoft.Testing.Platform), identify the test framework, apply test filters, or troubleshoot test execution failures. Covers MSTest…
gh-issue
Size-audit, write, and split BanyanDB issues that somebody else or an automated TDD workflow can implement. Use whenever the user asks to file or revise an issue, decide whether an issue is too large, make an issue TDD-ready, turn a design into tickets, or split an umbrella into executable leaves. Do not draft or file…
gh-pull-request
Create a GitHub pull request for SkyWalking BanyanDB. Use when the user asks to create a PR, submit changes, or open a pull request.
vendor-update
Upgrade Go/Node.js vendor dependencies and sync tool versions. Use whenever the user says "upgrade dependencies", "update vendors", "vendor update", "run vendor-upgrade", "bump dependencies", "update packages", or asks to run the vendor-update Make target. This skill also checks scripts/build/version.mk after…