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 shennawardana23/skillme --skill coding-standardsgit clone --depth 1 https://github.com/shennawardana23/skillmeWrote 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/shennawardana23/skillme/coding-standards)<a href="https://agentmods.dev/skills/shennawardana23/skillme/coding-standards"><img src="https://agentmods.dev/badge/skills/shennawardana23/skillme/coding-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/shennawardana23/skillme/coding-standards"><img src="https://agentmods.dev/badge/skills/shennawardana23/skillme/coding-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 | $0.00106 | $0.01967 |
| Opus 5.5 | $0.00042 | $0.00787 |
| Sonnet 5.5 | $0.00021 | $0.00393 |
| Haiku 4.5 | $0.00011 | $0.00197 |
Grade A, and why
coding-standards scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
const response = await fetch(url) How it starts
The opening of the file, as written. The whole thing — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Coding Standards
This is the language-agnostic layer: decision heuristics that apply
whether the file is Go, TypeScript, or PHP. For a specific language or
framework's idioms, use the dedicated skill instead —
skills/go-service-idioms/, skills/api-design/,
skills/laravel-patterns/, skills/vue-nuxt-frontend-patterns/. This
skill only covers what's genuinely cross-cutting: it skips KISS/DRY/YAGNI
definitions and other things any competent reviewer already knows, and
focuses on the concrete thresholds and rationalizations that actually
distinguish a maintainable change from one that technically works.
When to use
Reviewing code for maintainability across languages; setting up lint rules; establishing conventions a mixed-language team will actually follow without a language-specific skill to lean on.
Function size and nesting
A function whose body exceeds ~50 lines is usually doing more than one thing — the fix is extracting named sub-steps, not shrinking whitespace:
// One function, three responsibilities hidden inside it
function processMarketData() { /* validate, transform, persist, ~100 lines */ }
// Three named steps, each independently testable
function processMarketData() {
const validated = validateData()
const transformed = transformData(validated)
return saveData(transformed)
}
Nesting past 3-4 levels is a comparable signal. Guard clauses (early returns) collapse a pyramid of conditions into a flat list of exits, which is easier to scan and to add a fifth condition to later:
// 5 levels deep
if (user) { if (user.isAdmin) { if (market) { if (market.isActive) { if (hasPermission) { /* ... */ } } } } }
// Flat
if (!user) return
if (!user.isAdmin) return
if (!market) return
if (!market.isActive) return
if (!hasPermission) return
// ...
Magic numbers and strings
An unexplained literal in a conditional or a timeout is a landmine for the
next reader, who has to guess whether 3 and 500 are related, arbitrary,
or load-bearing:
What ships with it
1 file 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.
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 · 206 lines · 106 tokens per session scan A 4e8012ddff60
coding-standards is a skill published in the GitHub repository shennawardana23/skillme (4 stars, last pushed 25d ago), licensed Apache-2.0. It adds 106 tokens to every session and 1,967 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
coding-standards compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| coding-standardsshennawardana23/skillme | Skill | 4 | 25d ago | Apache-2.0 | A | 106 | Claude Code |
| receiving-code-reviewobra/superpowers | Skill | 315k | 5d ago | MIT | A | 38 | Claude Code |
| requesting-code-reviewobra/superpowers | Skill | 315k | 5d ago | MIT | A | 22 | Claude Code |
| ego-lite-simplifycitrolabs/ego-lite | Skill | 22k | today | MIT | A | 68 | Codex |
| review-loopmthines/agent-skills | Skill | 20 | 5d ago | MIT | A | 124 | Claude Code |
| create-prmthines/agent-skills | Skill | 20 | 5d ago | MIT | A | 115 | Claude Code |
| implement-suggestionmthines/agent-skills | Skill | 20 | 5d ago | MIT | A | 87 | Claude Code |