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/hugorcd/evlog/upstream-syncnpx skills add HugoRCD/evlog --skill upstream-syncgit clone --depth 1 https://github.com/HugoRCD/evlogWhat 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 | $0.00059 | $0.00765 |
| Opus 5 | $0.00030 | $0.00382 |
| Sonnet 5 | $0.00012 | $0.00153 |
| Haiku 4.5 | $0.00006 | $0.00076 |
Grade A, and why
upstream-sync 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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Upstream sync
The frameworks this app runs on move independently: eve and its satellites (@agent-browser/eve, @github-tools/eve-extension) from vercel/eve, and @vercel/connect from vercel/vercel. The twice-weekly run checks them, updates the app where warranted, and opens draft PRs. The PRs are the deliverable; nothing merges without a human.
1. What changed upstream
- Installed versions:
apps/evi/package.json. - Latest published versions:
npm view <pkg> versionfrom the sandbox, or the npm registry page, foreve,@agent-browser/eve,@github-tools/eve-extension,@vercel/connect. - Release notes: GitHub releases on
vercel/eve,vercel-labs/agent-browser,vercel-labs/github-tools, and thepackages/connectchangelog invercel/vercel. For behavior changes,eve.dev/docsand the installednode_modules/eve/docs.
2. Map onto this repo
- eve APIs: everything under
agent/(channels, connections, extensions, schedules, sandbox.ts).node_modules/eve/docsis the framework reference. - @vercel/connect/eve:
channels/photon.ts,connections/vercel.ts,lib/github/credentials.ts. - @agent-browser/eve:
sandbox.ts,extensions/browser.ts. @github-tools/eve-extension:extensions/github.ts. - packages/evlog/src/eve: the evlog integration for eve. A change there is user-facing and needs a changeset.
- docs/notes.md: the "eve", "github-tools" and "Vercel Connect" sections record workarounds. A newer version that fixes one means the workaround goes and the note goes with it.
3. Deliver the PRs
- One draft PR per coherent change: a dependency bump with its adaptation, or a workaround replacement. Never bundle unrelated updates.
- Branch off
mainin/workspace/repo, apply the change, runpnpm run lint,pnpm run typecheckandpnpm run test. Add a changeset when a consumer of evlog would notice the change. - Push the branch, open a draft PR per branch. Drafts cannot merge; marking one ready is Hugo's call.
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 · 39 lines · 59 tokens per session scan A 46ddef3d511f
upstream-sync is a skill published in the GitHub repository HugoRCD/evlog (1,831 stars, last pushed today), licensed MIT. It adds 59 tokens to every session and 765 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
frontmcp-observability
Use when adding tracing, structured logging, metrics, or monitoring to a FrontMCP server. Covers zero-config OpenTelemetry distributed tracing across all flows; the this.telemetry API for custom spans, events, and attributes in tools, plugins, agents, and skills; structured JSON logging with trace correlation and…
golang-observability-opentelemetry
Instrumenting Go applications with OpenTelemetry for distributed tracing, Prometheus for metrics, and structured logging with slog.
Observability Checklist
Reviews a service or codebase against a full observability checklist — logs, metrics, traces, and alerting gaps.
anyrobot-shadcn-frontend-js
AnyRobot 前端开发核心指南：提供 JavaScript + React + shadcn/ui 开发的精简实用规范和最佳实践。 当用户需要前端开发指导、组件开发或项目结构建议时触发。 本技能提供实际可用于项目开发的核心代码示例和开发指南。.
数据模型文档生成
当用户要生成或更新 Doris 表的数据模型 Markdown（三一级标题：数据摘要、数据表列、JSON扩展字段）、从 Doris 拉取元数据与至少 100 行样本，并由脚本或 --llm 补全说明时启用。.
fix-loop
Use when a Java app that has stacktale installed is failing — after running it or its tests, to find what broke, fix it, and confirm the fix by re-running and checking for new errors. Also use when asked to "check the errors", "what's failing", or to work through errors-ai.log.