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 saeedkolivand/ai-job-hunter-app --skill code-qualitygit 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 5.5 | $0.00022 | $0.00419 |
| Sonnet 5.5 | $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 1mo 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.
- 1mo 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 (62 stars, last pushed today), licensed Apache-2.0. It adds 55 tokens to every session and 1,048 once invoked, about $0.0002 per session on Opus 5.5. 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, or import a local recording. Use when a user asks about their Anarlog meeting data or needs meeting context for another task.
code-review-checklist
Systematic code review audit engine and master rubric across logic, security hardening, performance, clean-code adherence, and test coverage.
improve-codebase-architecture
Scans git commit hot spots for shallow modules, generates visual HTML reports with Mermaid diagrams, and drills into refactoring candidates.
code-review
Two-axis parallel code review comparing HEAD against a fixed point. Axis 1 (Standards) audits repo conventions and Fowler smells; Axis 2 (Spec) verifies line-by-line requirements coverage.
code-review-graph
Token-efficient code review using Tree-sitter AST graphs and MCP. Reduces AI assistant token usage by up to 49x by computing blast radius instead of reading entire folders.
adg-governance
Active Documentation Guard (ADG v2) protocol, machine-maintained witness manifests, AST symbol blast radius analysis, and parity guard compliance.