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 repo-health-sweepgit 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/repo-health-sweep)<a href="https://agentmods.dev/skills/hugorcd/evlog/repo-health-sweep"><img src="https://agentmods.dev/badge/skills/hugorcd/evlog/repo-health-sweep/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/hugorcd/evlog/repo-health-sweep"><img src="https://agentmods.dev/badge/skills/hugorcd/evlog/repo-health-sweep.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00102 | $0.01459 |
| Opus 5 | $0.00051 | $0.00730 |
| Sonnet 5 | $0.00020 | $0.00292 |
| Haiku 4.5 | $0.00010 | $0.00146 |
Grade A, and why
repo-health-sweep 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 12d 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repo health sweep
The self-review owns the agent's own surface. This sweep owns the rest of the repository: the published docs, the skills that describe the package, the repo's own conventions, and the runnable examples. Where they overlap, this skill covers the parts the self-review does not.
The failure mode is the same as self-review: a confident claim that is quietly
out of date, and the expensive version is claiming something does not exist.
Every check in this sweep is grounded in the current main before it is
written down. This is the source-research procedure over the whole repo, not
anything recalled.
The rule that never bends
A finding names the file and the rule or source it contradicts, or it is
dropped. A claim that an option, export, adapter or page is missing is proven
by enumerating the real surface, never by the absence of a memory. Load
source-research and follow it before drawing a conclusion about any package
behavior.
The four lenses
Skills vs reality
Every SKILL.md, internal and published, checked against the package surface it describes.
- Internal:
.agents/skills/*(create-adapter, create-enricher, create-framework-integration, create-map-rule) andapps/evi/agent/skills/*. - Published:
skills/*(analyze-logs, build-audit-logs, review-logging-patterns). - What to check: every API name, option, default, or adapter the skill shows.
An
evlog.Xoption must exist under that name; a function signature must be the real one (a curried call shown where the API is two-arg is a bug); a framework must export what the skill claims it does or does not. - Bar: a skill that describes old behavior is worse than no skill (
AGENTS.md). When a code change fixed a skill in this repo, that fix is the evidence the skill used to drift.
Docs quality
The published docs are the contract, so a wrong page costs real users.
- Pages that are unclear, stale, or inconsistent with each other. A page that contradicts a sibling page about the same API is a finding even when both are wrong the same way.
- A feature that shipped without a docs page, or an option documented with the wrong default.
- A table (adapters, env vars, exports, flags) that lists sources the code does not read, or omits ones it does. Cross-check against source, not against an older page.
- Anything
source-researchcould not answer because no page covers it.
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.
- 12d ago First seen · 129 lines · 102 tokens per session scan A 4c255c560a22
repo-health-sweep is a skill published in the GitHub repository HugoRCD/evlog (1,841 stars, last pushed 6d ago), licensed MIT. It adds 102 tokens to every session and 1,459 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 2026-08-30.
Other skills, from other repositories
Logging and Observability Guard
Ensure code changes keep logs/metrics/traces useful for debugging failures and regressions.
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…
monitoring-observability
Monitoring and observability patterns for Prometheus metrics, Grafana dashboards, Langfuse v4 LLM tracing (astype, scorecurrentspan, shouldexportspan, LangfuseMedia), and drift detection. Use when adding logging, metrics, distributed tracing, LLM cost tracking, or quality drift monitoring.
bydbql
Generate, validate, and optionally execute read-only BanyanDB BydbQL for STREAM, MEASURE, TRACE, and PROPERTY resources. Use when the user asks to query BanyanDB, translate natural language to BydbQL, inspect BanyanDB schema or data, validate BydbQL, or fetch raw BanyanDB records.