ring:fixing-lint

ring:fixing-lint is a skill for Claude Code, Codex from LerianStudio/ring. It costs 96 tokens per session (1,241 once invoked), scanned A, original, Apache-2.0.

A workflow for finding and fixing multiple lint errors in a codebase. Linting is an automated check that reports likely code mistakes and style problems.

In plain words
What is it for?
Use it to run the appropriate linter, group errors by area, dispatch fixers for independent issue groups, and verify that no lint errors remain.
Why use it?
It organizes separate lint problems so they can be fixed independently, then repeats the check until the code is clean. It also assigns Go issues and other issues to the specified specialist types.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/lerianstudio/ring/fixing-lint
Any agent
npx skills add LerianStudio/ring --skill fixing-lint
Clone the repo
git clone --depth 1 https://github.com/LerianStudio/ring

Made for: Claude Code, Codex.

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 ring:fixing-lint

README.md
[![agentmods](https://agentmods.dev/badge/skills/lerianstudio/ring/fixing-lint.svg)](https://agentmods.dev/skills/lerianstudio/ring/fixing-lint)
Your own site
<a href="https://agentmods.dev/skills/lerianstudio/ring/fixing-lint"><img src="https://agentmods.dev/badge/skills/lerianstudio/ring/fixing-lint.svg" alt="Measured on agentmods" height="20"></a>
Per session 96 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,241 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00096 $0.01241
Opus 5 $0.00048 $0.00620
Sonnet 5 $0.00019 $0.00248
Haiku 4.5 $0.00010 $0.00124

Measured 6d ago against content hash af1a379e4c46, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

ring:fixing-lint 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.

default/skills/fixing-lint/SKILL.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Linting Codebase

When to use

  • User runs /ring:fixing-lint command
  • Codebase has lint issues that need fixing
  • Multiple lint errors across different files/components

Skip when

  • Single lint error → fix directly without agent dispatch
  • Lint already passes → nothing to do
  • User only wants to see lint output, not fix

Run lint checks, group issues into independent streams, dispatch parallel agents, iterate until clean.

⛔ Critical Constraints (communicate to ALL dispatched agents)

  • DO NOT create automated scripts to fix lint issues
  • DO NOT create documentation or README files
  • DO NOT add comments explaining the fixes
  • Fix each issue directly by editing source code
  • Minimal changes — only what's needed for lint

Phase 1: Run Lint

Detect command: make lintnpm run lintyarn lintpnpm lintgolangci-lint runcargo clippyruff check .eslint .

<lint_command> 2>&1 | tee /tmp/lint-output.txt; echo "EXIT_CODE: ${PIPESTATUS[0]}"

If EXIT_CODE is non-zero, lint failed. Report failure clearly before proceeding to grouping.

Parse: file path, line:column, error code/rule, message, severity.

Phase 2: Group into Streams

Issue Count Grouping Strategy
< 10 By file
10-50 By directory
50-100 By error type/rule
> 100 By component/module

A stream is independent if: files don't import each other, fixes won't conflict, agents can work without knowledge of other streams.

Phase 3: Parallel Agent Dispatch

⛔ STOP-CHECK BEFORE DISPATCH

Before emitting any Task call, count the agents you intend to launch in this turn.

  • Count MUST equal the number of independent streams you identified in Phase 2.
  • If your dispatch count diverges from your stream count → STOP and reconcile against the Phase 2 grouping.
  • One agent per stream. No substitutions, no omissions.

⛔ MUST NOT trickle-dispatch

All stream agents leave in the SAME TURN, before reading any agent output.

Read the full file on GitHub · 121 lines

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. 6d ago First seen · 121 lines · 96 tokens per session scan A af1a379e4c46

Subscribe to this mod's changes

ring:fixing-lint is a skill published in the GitHub repository LerianStudio/ring (211 stars, last pushed 16d ago), licensed Apache-2.0. It adds 96 tokens to every session and 1,241 once invoked, about $0.0005 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 2026-08-30.