taste-lints

taste-lints is a skill for Claude Code from rjmurillo/ai-agents. It costs 47 tokens per session (972 once invoked), scanned A, original, MIT.

A custom code checker that looks for project rules such as file-size limits, naming patterns, structured logs, and code complexity. Its error messages include suggested fixes for an AI coding agent.

In plain words
What is it for?
Use it while editing files, before opening a pull request, or when reviewing staged changes. It can check all rules, a single rule, or produce a machine-readable report.
Why use it?
It catches project-specific style and quality problems before review and explains how to correct them. This reduces repeated manual feedback about conventions and oversized files.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths.

Part of the project-toolkit plugin — 95 skills, 26 commands, 33 agents, 4 hooks shipped together

Good fit Use it while editing files, before opening a pull request, or when reviewing staged changes. It can check all rules, a single rule, or produce a machine-readable report.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rjmurillo/ai-agents/taste-lints
Install

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.

Any agent
npx skills add rjmurillo/ai-agents --skill taste-lints
Clone the repo
git clone --depth 1 https://github.com/rjmurillo/ai-agents

Made for: Claude Code.

Or install project-toolkit, the plugin that ships this one along with the rest of its 95 skills, 26 commands, 33 agents, 4 hooks.

Wrote 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.

agentmods badge for taste-lints

README.md
[![agentmods](https://agentmods.dev/badge/skills/rjmurillo/ai-agents/taste-lints/github.svg)](https://agentmods.dev/skills/rjmurillo/ai-agents/taste-lints)
Your own site
<a href="https://agentmods.dev/skills/rjmurillo/ai-agents/taste-lints"><img src="https://agentmods.dev/badge/skills/rjmurillo/ai-agents/taste-lints/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.

agentmods 80×15 button for taste-lints

Your own site · 80×15
<a href="https://agentmods.dev/skills/rjmurillo/ai-agents/taste-lints"><img src="https://agentmods.dev/badge/skills/rjmurillo/ai-agents/taste-lints.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 972 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00047 $0.00972
Opus 5 $0.00023 $0.00486
Sonnet 5 $0.00009 $0.00194
Haiku 4.5 $0.00005 $0.00097

Measured 4d ago against content hash 0c46db6851ed, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

taste-lints 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 4d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/taste_lints.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.claude/skills/taste-lints/SKILL.md · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Taste Lints

Custom lints where error messages become agent-readable remediation instructions.

Inspired by OpenAI Harness Engineering:

"We statically enforce structured logging, naming conventions for schemas and types, file size limits, and platform-specific reliability requirements with custom lints. Because the lints are custom, we write the error messages to inject remediation instructions into agent context."

Triggers

Trigger Phrase Operation
run taste lints taste_lints.py on staged or specified files
check file size taste_lints.py with file-size rule only
check naming conventions taste_lints.py with naming rule only
lint taste invariants taste_lints.py full scan
taste lint report taste_lints.py with JSON output

When to Use

Use this skill when:

  • Writing or editing source files (catch taste violations early)
  • Preparing code for PR submission
  • Reviewing code for style and convention compliance
  • Adding new files to the project

Taste Invariants

1. File Size Limits

Files exceeding line thresholds indicate poor cohesion.

Threshold Lines Severity
Warning 301-500 warning
Error 501+ error

2. Naming Conventions

Pattern Rule Applies To
snake_case Python files, functions, variables *.py
kebab-case Skill directories, YAML files .claude/skills/, *.yml
PascalCase PowerShell functions, classes *.ps1, *.psm1
UPPER_CASE Constants, environment variables All languages
invoke_ prefix Hook scripts .claude/hooks/

3. Function Complexity

Functions exceeding cyclomatic complexity 10 need decomposition.

4. Skill Prompt Size

Skills exceeding 500 lines need progressive disclosure refactoring.

Process

  1. Run python3 .claude/skills/taste-lints/scripts/taste_lints.py with target files
  2. Review AGENT_REMEDIATION blocks in output
  3. Apply suggested fixes
  4. Re-run to confirm compliance

Read the full file on GitHub · 126 lines

Files

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.

Changes

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.

  1. 4d ago First seen · 126 lines · 47 tokens per session scan A 0c46db6851ed

Subscribe to this mod's changes

taste-lints is a skill published in the GitHub repository rjmurillo/ai-agents (45 stars, last pushed yesterday), licensed MIT. It adds 47 tokens to every session and 972 once invoked, about $0.0002 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.