Tracely-ai: Skill for Claude Code

.claude/skills/openseo-review-web-content/SKILL.md

openseo-review-web-content is a skill for Claude Code from Jwuthri/Tracely-ai. It costs 58 tokens per session (811 once invoked), scanned A, a copy of openseo-review-web-content, MIT.

A writing guide for creating and reviewing the OpenSEO website’s user-facing text, including blog posts, guides, feature pages, and FAQs.

In plain words
What is it for?
Use it when adding or editing prose in the website’s content files.
Why use it?
It helps keep published claims accurate, prices honest, and explanations useful to readers. It also helps remove vague or artificial-sounding writing.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions subagents.

This is Jwuthri/Tracely-ai's own configuration. It tells Claude Code how to work on Tracely-ai itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Tracely-ai configures →

About the project

Tracely is a CI/CD system for AI agents that turns failed production traces into replayable regression tests. Development teams use it to detect and group agent failures, run the resulting cases on pull requests, and block changes that reproduce those failures. The catalogue entries provide skills for operating this trace-based testing and observability workflow.

Jwuthri/Tracely-ai · 1,404 stars · on GitHub · tracely-ai.com

Reuse

Borrowing it

Nothing to install: this file belongs to Jwuthri/Tracely-ai. 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/Jwuthri/Tracely-ai/master/.claude/skills/openseo-review-web-content/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Jwuthri/Tracely-ai

Made for: Claude Code.

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.

agentmods badge for openseo-review-web-content

README.md
[![agentmods](https://agentmods.dev/badge/skills/jwuthri/tracely-ai/openseo-review-web-content/github.svg)](https://agentmods.dev/skills/jwuthri/tracely-ai/openseo-review-web-content)
Your own site
<a href="https://agentmods.dev/skills/jwuthri/tracely-ai/openseo-review-web-content"><img src="https://agentmods.dev/badge/skills/jwuthri/tracely-ai/openseo-review-web-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.

agentmods 80×15 button for openseo-review-web-content

Your own site · 80×15
<a href="https://agentmods.dev/skills/jwuthri/tracely-ai/openseo-review-web-content"><img src="https://agentmods.dev/badge/skills/jwuthri/tracely-ai/openseo-review-web-content.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 811 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.
Origin 100% copy Near-identical to another mod 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00058 $0.00811
Opus 5 $0.00029 $0.00405
Sonnet 5 $0.00012 $0.00162
Haiku 4.5 $0.00006 $0.00081

Measured 11d ago against content hash 52dc4858851d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

openseo-review-web-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 11d 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.

Origin

This is a copy

100% identical to openseo-review-web-content — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/skills/openseo-review-web-content/SKILL.md · 38 lines

How it starts

The opening of the file, as written. The whole thing — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OpenSEO Web Content

Everything we publish must be traceable to what the product actually does and costs, and must read like a practitioner wrote it. The reader's interest comes first: teach something they can act on, and answer straight — including when the honest answer is "no" or "it costs money."

Principles

  1. Traceable truth. Every capability claim, price, and screenshot is verifiable against the code, the fact sheet (src/server/features/onboarding/openseo-fact-sheet.md), or the live product. If you can't point to where it's true, it doesn't ship.
  2. Lead with the real answer. "No," "not unlimited," and "it costs money" are complete answers. Hedging that lets a reader infer something more flattering than the truth is a way of misleading them.
  3. Honest pricing, with its reasoning. Quality SEO data is expensive everywhere — that's why the big suites run $100/month and up. OpenSEO is the affordable option: $10/month, free to start. Never simply "free."
  4. Sound like a person. Fix AI tells by restating the underlying claim plainly, not by polishing the flourish. The deslop skill is the reference for what to hunt and how to fix it.
  5. Reader-first altitude. Guides teach actionable SEO that stands on its own — not product documentation, not generic filler. Credit free resources to their real owners (Google's autocomplete, the reader's own Search Console).
  6. One bar, whole surface. When a standard improves, sweep everything to it — all the FAQs, all the pages — not just the instance that got noticed.
  7. Playbook terminology. Call each approach within any OpenSEO playbook a "strategy," never a "play." Use "workflow" for the steps readers execute; use "playbook" only for the complete collection.

Questions to ask while reviewing

  • If a reader trusted every claim and screenshot, then opened OpenSEO right now, where would reality not match?
  • Does each answer open with the real answer, or quietly steer toward a more flattering inference?
  • Read the sharpest line aloud: would a person say it that way?
  • Is anything called free that actually costs credits?
  • Is this teaching the reader something useful on its own, or drifting into product docs or padding?
  • Does every link, image, and example on the page earn its place for the reader?

Read the full file on GitHub · 38 lines

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.

  1. 11d ago First seen · 38 lines · 58 tokens per session scan A 52dc4858851d

Subscribe to this mod's changes

openseo-review-web-content is a skill published in the GitHub repository Jwuthri/Tracely-ai (1,404 stars, last pushed yesterday), licensed MIT. It adds 58 tokens to every session and 811 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to openseo-review-web-content, differing in 0 lines, and is treated as a copy.

Related

Other skills, from other repositories

architect-analyze

Analyze architecture for consistency between ADRs and AD, completeness, and quality issues. Use when validating generated or refined architecture artifacts, before feature development, during architecture review, or periodically to detect drift.

tikalk/adlc-team-skills · 43 tokens

gemini-review

Google Gemini CLI code review with Gemini 2.5 Pro, 1M token context, CI/CD integration.

alinaqi/maggy · 26 tokens

squid-implement-night

Run the full agent-team pipeline end-to-end for one feature whose Tasks Plan is already approved by /squid-plan, handing the human a validated, ready-to-squash-merge PR. Trigger after /squid-plan.

iusztinpaul/squid · 52 tokens

pr-babysitter

Monitors or repairs an open GitHub PR: CI failures, conflicts, review threads, and merge readiness, reporting state changes. Use when asked to "watch this PR", "fix CI", "resolve conflicts", or "address review comments". For PR metadata use pr-creator; for npm release PRs use autoship.

mblode/agent-skills · 72 tokens

tech-debt-ci-review

Codex adapter for deep technical-debt and CI-stability audits. Use when asked to find test theater, flaky tests, missing or mis-scoped tests, brittle CI/toolchain behavior, structural debt blocking green PRs, or a remediation order for opencode-swarm.

ZaxbyHub/opencode-swarm · 61 tokens

aster-review-ci

Run aster code reviews non-interactively in CI, GitHub Actions, or from another agent. Covers aster review --pr, --json, --stream, --comment, diff-from-stdin, token handling, and filtering findings. Use when wiring aster into a pipeline, posting PR comments, or parsing review output programmatically.

Zfinix/aster · 75 tokens