Borrowing it
Nothing to install: this file belongs to saeedkolivand/ai-job-hunter-app. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/saeedkolivand/ai-job-hunter-app/main/.claude/skills/code-quality/SKILL.mdgit clone --depth 1 https://github.com/saeedkolivand/ai-job-hunter-appWrote 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/saeedkolivand/ai-job-hunter-app/code-quality)<a href="https://agentmods.dev/skills/saeedkolivand/ai-job-hunter-app/code-quality"><img src="https://agentmods.dev/badge/skills/saeedkolivand/ai-job-hunter-app/code-quality/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/saeedkolivand/ai-job-hunter-app/code-quality"><img src="https://agentmods.dev/badge/skills/saeedkolivand/ai-job-hunter-app/code-quality.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 | $0.00055 | $0.01048 |
| Opus 5 | $0.00028 | $0.00524 |
| Sonnet 5 | $0.00011 | $0.00210 |
| Haiku 4.5 | $0.00006 | $0.00105 |
Grade A, and why
code-quality 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Quality Standards
Standards for a pnpm/Turbo monorepo: React 19 + TypeScript frontend, Rust (Tauri 2) backend. The reviewer reports violations against this; the author fixes against it. Both apply the judgment below — these are heuristics, not a linter.
Severity
- High — bugs in waiting: real logic duplication that will drift; a function doing >1 job over shared mutable state;
any/unchecked casts hiding type holes;unwrap()/expect()/panic!on fallible paths in non-test Rust; swallowed errors. - Medium — friction: functions >~50 lines or nesting >3; unclear names; magic numbers/strings; prop drilling; repeated literals; dead params.
- Low — polish: comment-as-deodorant, inconsistent ordering, minor naming, anything the formatter already owns.
Principles — and where they backfire (do NOT over-apply)
- DRY: dedupe knowledge, not coincidental similarity. Two blocks that look alike but change for different reasons stay separate — a wrong abstraction costs more than duplication. Don't unify before the third occurrence, and only when the rule is truly the same.
- KISS / YAGNI: prefer the boring direct solution. Strip speculative generality — flags, params, hooks, and layers with one caller. Never add abstraction "for later."
- Single responsibility, not dogmatic SOLID. Split when there are two reasons to change, not to hit a line count.
- Net result must be simpler. A change that adds indirection, interfaces, or files without removing real complexity is a regression — record it as "considered, rejected," don't ship it.
Stack smells
React/TS:
- A component doing fetch + state + formatting + render → extract a hook / presentational split.
- State derivable from props or other state (compute, don't store); effects syncing state that should be derived.
- Over-memoization (
useMemo/useCallbackwith no measured need) as much as missing memo on a hot path. any,asassertions, stringly-typed unions → discriminated unions / generics. Enum where a union literal is simpler. Non-null!masking a real nullable;// @ts-ignore.- Prop drilling >2 levels → context or composition. Exported types/components with no consumer. Rust/Tauri:
unwrap/expect/panic!on I/O, parse, lock, or command paths →Result+?+ a real error enum (thiserror).- Clone-happy code where a borrow works;
Stringparams that should be&str. - Fat command handlers → push logic into testable fns; keep
#[tauri::command]thin.unsafewithout a justifying comment. Cross-cutting: duplicated literals/config → one const/module; magic numbers → named; deep nesting → guard clauses / early returns; a boolean param gating two behaviors → split the function.
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 · 50 lines · 55 tokens per session scan A b72edea3613f
code-quality is a skill published in the GitHub repository saeedkolivand/ai-job-hunter-app (54 stars, last pushed today), licensed Apache-2.0. It adds 55 tokens to every session and 1,048 once invoked, about $0.0003 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
anarlog
Query Anarlog meetings, notes, summaries, transcripts, participants, action items, and recurring history. Use when a user asks about their Anarlog meeting data or needs meeting context for another task.
ramble
Run a human-feedback loop through RambleDesk. Hard trigger: when the user invokes /ramble, $ramble, [$ramble], or says to use RambleDesk/ramble feedback, create a RambleDesk request before answering the substance unless they explicitly say not to send one. Also use when real human judgment, review, approval, or…
code-review-graph
Token-efficient code review using Tree-sitter AST graphs and MCP. Reduces AI assistant token usage by 6.8–49x by computing blast radius of changes instead of reading entire codebases. Uses SQLite graph database for structural analysis.
code-review-checklist
Expert guidelines, principles, and procedures for AI Assist Note.
code-review
Two-axis parallel code review comparing HEAD against a fixed point. Axis 1 (Standards) checks repo conventions and Fowler code smells. Axis 2 (Spec) checks line-by-line requirements coverage.
improve-codebase-architecture
Scans git commit hot spots for shallow modules, generates visual HTML reports with Mermaid diagrams, and drills into refactoring candidates.