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 niels-emmer/myace --skill code-standardsgit clone --depth 1 https://github.com/niels-emmer/myaceWrote 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/niels-emmer/myace/code-standards)<a href="https://agentmods.dev/skills/niels-emmer/myace/code-standards"><img src="https://agentmods.dev/badge/skills/niels-emmer/myace/code-standards/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/niels-emmer/myace/code-standards"><img src="https://agentmods.dev/badge/skills/niels-emmer/myace/code-standards.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 | $0.00022 | $0.00718 |
| Opus 5 | $0.00011 | $0.00359 |
| Sonnet 5 | $0.00004 | $0.00144 |
| Haiku 4.5 | $0.00002 | $0.00072 |
Grade A, and why
Code Standards 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 6d 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 — 30 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Consistency lowers the cost of reading code more than any individual stylistic choice does. A codebase where every module solves the same kind of problem the same way is faster to work in than one where each file reflects whoever wrote it last, even if some of those individual choices were locally "better." This skill is about matching what's already there before introducing something new.
When to use it
Every time you write or modify code — this isn't a one-off pass, it's the default posture. Reach for it explicitly when starting work in an unfamiliar part of a codebase, or when you notice you're about to introduce a naming or structural pattern that doesn't obviously match its neighbors.
Steps / checklist
- Read before writing. Before adding a function, class, or module, look at 2-3 existing examples of the same kind of thing nearby. Match their naming style, argument order, error-handling approach, and level of abstraction rather than picking your own.
- Names describe what, not how. A function name should tell a reader what it accomplishes (
validate_user_email) not the mechanism (check_regex_match) unless the mechanism is the point. Avoid abbreviations that aren't already established in the codebase. - One level of abstraction per function. If a function mixes high-level orchestration with low-level detail (looping, string parsing) in the same block, that's usually a sign it should be split — not because smaller is always better, but because mixed levels are harder to read at a glance.
- Match the project's actual conventions, not a generic style guide. If the codebase uses
snake_casefor functions and you're working in a section that already does that, don't introducecamelCasebecause it's "more standard" elsewhere. Check for a linter config or existing style doc first — it's authoritative over personal preference. - Keep related things together. A function and the tests that exercise it, a type and the code that constructs it, a constant and the logic that depends on its value — colocate where the existing project structure allows it, rather than scattering by category (all constants in one file regardless of what they're for) if that's not already the established pattern.
- Prefer explicit over clever. A slightly longer, obvious version of something beats a dense one-liner that needs a comment to explain what it does. If you need the comment, that's a signal to simplify the code instead of just documenting the cleverness.
- Don't reformat unrelated code. Whitespace-only or style-only changes to lines you didn't otherwise touch bloat the diff and make the real change harder to review — leave them alone unless the task is specifically a formatting pass.
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.
- 6d ago First seen · 30 lines · 22 tokens per session scan A 30d82cb82138
Code Standards is a skill published in the GitHub repository niels-emmer/myace (1 stars, last pushed 2d ago), licensed MIT. It adds 22 tokens to every session and 718 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
loom-code-review
Comprehensive code review covering correctness, maintainability, performance, security, and best practices.
pressure
Pressure-test a loom plan and write a review for the plan's author. Trigger when the user invokes $pressure followed by a plan path. The argument after $pressure is the plan file path.
cross-review
The writer cannot be the final judge of the work.
code-review
Perform thorough code reviews focusing on correctness, security, and maintainability.
eng
Platform-agnostic engineering agent with three modes: --plan (propose file changes for human approval AND write the per-feature todo tickets in the same pass), --build (write code from the todo tickets — the single and final build spec), --review (one adversarial whole-change review of the working diff, run by a…
ubs
Run Ultimate Bug Scanner (UBS) for code review. Use when reviewing code, checking for bugs, scanning for security issues, validating AI-generated code, or pre-commit quality checks.