What is write-evlog-content?

Writing guidance for creating, reviewing, and rewriting evlog documentation and project instructions, including README files, skills, and AGENTS.md files.

Use it when drafting or editing evlog docs, blog posts, package documentation, skills, or agent instruction files.

It helps keep related technical writing consistent and makes review separate from rewriting.

How HugoRCD/evlog configures Claude Code and Codex

About the project

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.

HugoRCD/evlog · 1,903 stars · on GitHub · evlog.dev

Reuse

Borrowing it

Nothing to install: this file belongs to HugoRCD/evlog. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/HugoRCD/evlog/main/.agents/skills/write-evlog-content/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/HugoRCD/evlog

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/hugorcd/evlog/write-evlog-content/github.svg)](https://agentmods.dev/skills/hugorcd/evlog/write-evlog-content)

Your own site

<a href="https://agentmods.dev/skills/hugorcd/evlog/write-evlog-content"><img src="https://agentmods.dev/badge/skills/hugorcd/evlog/write-evlog-content/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/hugorcd/evlog/write-evlog-content"><img src="https://agentmods.dev/badge/skills/hugorcd/evlog/write-evlog-content.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 121 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,436 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

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	$0.00121	$0.02436
Opus 5.5	$0.00048	$0.00974
Sonnet 5.5	$0.00024	$0.00487
Haiku 4.5	$0.00012	$0.00244

Measured 2mo ago against content hash 63e9e66a9252, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

write-evlog-content 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 2mo 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.

.agents/skills/write-evlog-content/SKILL.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Writing evlog content

Everything needed to draft or judge evlog prose. Two roles use this skill and they must not be merged.

Review produces findings and a verdict. It never rewrites, never softens, never proposes wording. Rewrite applies findings. It touches only what a finding names, and cites the rule or tell id for every change.

Splitting them is what keeps the loop honest. A reviewer that can rewrite talks itself into changes it cannot justify, and a rewriter that can re-judge its own output always passes.

Structure

references/
  voice.md        the voice and the five tests. Load first, always
  rules/          atomic rules, one file per surface group
    universal.md    every surface
    docs.md         apps/docs/content
    blog.md         blog posts
    landing.md      0.landing.md and other marketing surfaces
    machine.md      skills and AGENTS.md, the surfaces an agent acts on
  ai-tells.md     the tell corpus, each tell with its legitimate twin
  terminology.md  the names evlog gave its own parts (U-15)
  landscape/      what pino, winston, consola, and OpenTelemetry actually do (U-12)
  surfaces/       what each surface owes its reader
    docs.md  blog.md  landing.md  readme.md  skill.md  agents.md  changeset.md
  samples.md      evlog pages that read right, and why. What the tells must not flag
  corrections.md  accumulated lessons from rejected rewrites. Grows over time

Load voice.md first. Then the rule file for the surface, ai-tells.md when reviewing, and the matching surfaces/ file when drafting. Open terminology.md when a U-15 candidate is in play and the relevant landscape/ dossier before writing any sentence that names another logger. Do not load everything.

The corpus

Everything evlog ships as prose, on both sides of the line:

Read by	Surfaces	What decides quality
People	docs pages, the landing, blog posts, the package READMEs	Whether the reader can act, and whether they believe the page
Agents	`.agents/skills/`, `skills/`, the `AGENTS.md` files	Whether an agent does the right thing having read only this

Read the full file on GitHub · 136 lines

Files

What ships with it

22 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.

Changes

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.

2mo ago First seen · 136 lines · 121 tokens per session scan A 63e9e66a9252

Subscribe to this mod's changes

write-evlog-content is a skill published in the GitHub repository HugoRCD/evlog (1,903 stars, last pushed 12d ago), licensed MIT. It adds 121 tokens to every session and 2,436 once invoked, about $0.0005 per session on Opus 5.5. 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.

Writing and docs error-handling logging nuxt observability

write-evlog-content next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
write-evlog-contentHugoRCD/evlog	Skill	1.9k	12d ago	MIT	A	121	Claude Code, Codex
gh-issueapache/skywalking-banyandb	Skill	355	today	Apache-2.0	A	91	Claude Code
gh-pull-requestapache/skywalking-banyandb	Skill	355	today	Apache-2.0	A	37	Claude Code
vendor-updateapache/skywalking-banyandb	Skill	355	today	Apache-2.0	A	95	Claude Code
bydbqlapache/skywalking-banyandb	Skill	355	today	Apache-2.0	A	71	Claude Code
frontmcp-observabilityagentfront/frontmcp	Skill	148	yesterday	Apache-2.0	A	196	Claude Code, Codex
compilingapache/skywalking-banyandb	Skill	355	today	Apache-2.0	A	31	Claude Code

evlog: Skill for Claude Code