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/create-framework-integrationnpx skills add HugoRCD/evlog --skill create-framework-integrationgit 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 | $0.00077 | $0.04887 |
| Opus 5 | $0.00039 | $0.02443 |
| Sonnet 5 | $0.00015 | $0.00977 |
| Haiku 4.5 | $0.00008 | $0.00489 |
Grade A, and why
create-evlog-framework-integration 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 yesterday.
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 — 374 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create evlog Framework Integration
Add a new framework integration to evlog. The recommended path is the manifest mode built on defineFrameworkIntegration from evlog/toolkit, for any framework with a request/response middleware shape. For frameworks with a fundamentally different lifecycle you'll fall back to the lower-level createMiddlewareLogger.
Two paths
- Manifest mode (preferred, ~30–80 lines of glue). Call
defineFrameworkIntegration({ name, extractRequest, attachLogger, storage? })once at module level, then write a tiny middleware that callsintegration.start(ctx, options)and runs the framework'snext()insiderunWith. Reference implementations: all ofpackages/evlog/src/{hono,express,fastify,elysia,nestjs,orpc,react-router,sveltekit,workers}/index.tsuse it. - Custom mode: use
createMiddlewareLoggerdirectly when the framework's lifecycle doesn't fit a standard middleware. Current custom-mode integrations: Next.js (src/next/), Nitro v2/v3 (src/nitro/,src/nitro-v3/), Eve (src/eve/).
Manifest mode now covers all classic HTTP frameworks. Use custom mode only when you can't extract a request synchronously at the start of the lifecycle (server actions, module-level hooks, agent turns).
Required API surface (from AGENTS.md)
Every framework integration must expose:
evlog()middleware/plugin accepting the fullBaseEvlogOptions(drain,enrich,keep,include,exclude,routes,plugins)useLogger()(ALS-backed). Workers is the one sanctioned exception (ALS needs a compat flag there;defineWorkerFetchattaches the logger instead)log.fork()support (automatic whenstorageis provided to the manifest)- The framework-native accessor (
c.get('log'),req.log,event.locals.log, …)
PR Title
feat({framework}): add {Framework} middleware integration
Scope timing caveat: the semantic PR check reads its scope list from the base branch, so a brand-new scope can't validate the very PR that introduces it. Either register the scope in a small preceding PR, or use an unscoped title (feat: add {Framework} middleware integration) on the introducing PR.
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.
- yesterday First seen · 374 lines · 77 tokens per session scan A acc3ee2a4db4
create-evlog-framework-integration is a skill published in the GitHub repository HugoRCD/evlog (1,826 stars, last pushed 2d ago), licensed MIT. It adds 77 tokens to every session and 4,887 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 2026-08-30.
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…
migrate-better-result-3
Migrate a TypeScript codebase from better-result 2.x to 3.0. Use when upgrading better-result across the TaggedError syntax, removed Result serialization helpers, recovery inference, matching, or retry APIs.
audit-better-result-dependents
Audit better-result changes or PRs against known Prisma and Better T Stack downstream dependents. Use when working on better-result API/type/runtime changes and the user asks whether a change breaks Prisma dependents, Better T Stack dependents, npm dependents, or PR compatibility.
dd-code-generation
Use pup CLI for immediate Datadog operations or generate code for integration into applications.
adopt-better-result
Adopt better-result in an existing TypeScript codebase. Use for a repository-wide error-handling audit and proposal, or for implementing a named vertical slice with TaggedError and Result.
agent-inspect
Local evidence debugger and trajectory-test toolkit for TypeScript AI agents. Use when capturing framework-faithful traces, asserting TraceContract/TraceFacts, packaging Evidence v2, or inspecting local runs over read-only MCP (gettracefacts).