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 mikestangdevs/craft-skills --skill everywhere-elsegit clone --depth 1 https://github.com/mikestangdevs/craft-skillsWrote 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/mikestangdevs/craft-skills/everywhere-else)<a href="https://agentmods.dev/skills/mikestangdevs/craft-skills/everywhere-else"><img src="https://agentmods.dev/badge/skills/mikestangdevs/craft-skills/everywhere-else/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/mikestangdevs/craft-skills/everywhere-else"><img src="https://agentmods.dev/badge/skills/mikestangdevs/craft-skills/everywhere-else.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00134 | $0.01208 |
| Opus 5 | $0.00067 | $0.00604 |
| Sonnet 5 | $0.00027 | $0.00242 |
| Haiku 4.5 | $0.00013 | $0.00121 |
Grade A, and why
everywhere-else 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 8d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Everywhere Else
The failure mode this fixes
A bug gets found in one scenario, one endpoint, one template — and fixed there. The report says "fixed," the test goes green, everyone moves on. But the codebase has nineteen siblings built by the same hand, from the same copy-paste, with the same defect — and the fix just made instance #7 correct while #1–6 and #8–20 still lie. The user discovers this one sibling at a time, each discovery costing a full debugging session that ends in "oh, it's the same bug again."
Agents are biased toward the point fix: the task said "fix the chart in scenario 12," so scenario 12 gets fixed and the task is "done." Nobody asked the question that turns a point fix into a real fix: is this defect a member of a population?
When to Use This Skill
- You just fixed a defect in one instance of anything that has siblings — handlers, templates, scenarios, components, parsers, fixtures, migrations, configs
- The fix corrected a pattern (wrong field semantics, missing null check, stale API shape) rather than a one-off typo
- The codebase contains parallel surfaces that must stay consistent (every page that renders X, every job that emits Y)
- A report is about to say "fixed" and the diff touches one file in a directory of twenty look-alikes
- The user asks "did you do that anywhere else?" — if they have to ask, the skill fired too late
Don't use when: the defect is genuinely unique to its site (a typo in one string), or the "siblings" only superficially resemble each other and share no logic or origin. Don't let the sweep balloon into a refactor of every file it visits — the sweep checks for this defect, not all defects.
Instructions
1. Classify the fix: typo or pattern?
After any fix, ask what kind of wrong it was. A one-off mistake stays a point fix. But if the defect came from a misunderstanding (wrong unit, wrong field meaning, wrong API contract), a copy-paste lineage, or a convention everyone followed — the same wrongness exists wherever that understanding was applied.
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.
- 8d ago First seen · 70 lines · 134 tokens per session scan A b9d0fa1c2f24
everywhere-else is a skill published in the GitHub repository mikestangdevs/craft-skills (4 stars, last pushed 3mo ago), licensed MIT. It adds 134 tokens to every session and 1,208 once invoked, about $0.0007 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 2026-08-31.
Other skills, from other repositories
plumb-line-audit
Use when auditing a diff or repository against the plumb-line principles — finds laundered uncertainty, boundary leaks, hardcoded priors, overstated maturity, outputs lacking recorded lineage, and baseline drift with no explanation. Read-only: it reports, never auto-fixes.
Tech Debt Auditor
Identifies and prioritizes technical debt in a codebase with an effort/impact matrix.
craft-audit
The front door to the craft skills — a whole-project production-readiness orchestrator that drives the ten per-domain craft skills (ux, frontend, backend, db, security, infra, observability, testing, lint, ai) instead of auditing one surface at a time. It discovers the project's shape, plans an audit per surface, and…
craft-backend
The Craftsman standard for building and reviewing backend code — API routes, request validation, the authentication boundary, service/business logic, error handling, route rate-limit middleware, third-party integrations, and background jobs. Use this WHENEVER the work touches the server side: adding or reviewing a…
code-consolidation
This skill should be used when the user asks to "find duplicated code", "map responsibilities", "consolidate code", "find code sprawl", "analyze duplication", "create consolidation plan", or mentions "código duplicado", "responsabilidades espalhadas", "consolidar". Analyzes codebases to identify scattered…
recipe-front-review
Reviews completed frontend implementation for governing-source compliance, scope economy, repository quality, and security, then applies user-approved React corrections.