correct

correct is a skill for Claude Code from kwaa/skills. It costs 68 tokens per session (544 once invoked), scanned A, a copy of correct, MIT.

A process for finding recurring mistakes in a repository and changing the codebase so they become harder to repeat. It prefers architecture and type checks, then linters or tests, with documentation as a later step.

In plain words
What is it for?
Use it to turn recurring review feedback, workarounds, and agent errors into enforced design rules, type errors, lint checks, or tests.
Why use it?
It addresses repeated corrections that otherwise have to be made again for each contributor or coding agent. Checks are tied to mistakes that have actually happened in the project.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: installed under .agents/ (shared by several agents).

Good fit Use it to turn recurring review feedback, workarounds, and agent errors into enforced design rules, type errors, lint checks, or tests.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kwaa/skills/correct
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 kwaa/skills --skill correct
Clone the repo
git clone --depth 1 https://github.com/kwaa/skills

Made for: Claude Code.

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 correct

README.md
[![agentmods](https://agentmods.dev/badge/skills/kwaa/skills/correct/github.svg)](https://agentmods.dev/skills/kwaa/skills/correct)
Your own site
<a href="https://agentmods.dev/skills/kwaa/skills/correct"><img src="https://agentmods.dev/badge/skills/kwaa/skills/correct/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 correct

Your own site · 80×15
<a href="https://agentmods.dev/skills/kwaa/skills/correct"><img src="https://agentmods.dev/badge/skills/kwaa/skills/correct.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 544 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.
Origin 91% copy Near-identical to another mod 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 $0.00068 $0.00544
Opus 5.5 $0.00027 $0.00218
Sonnet 5.5 $0.00014 $0.00109
Haiku 4.5 $0.00007 $0.00054

Measured 10d ago against content hash e347045d00c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

correct 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 10d 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.

Origin

This is a copy

91% identical to correct — 1 line differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.agents/skills/correct/SKILL.md · 33 lines

How it starts

The opening of the file, as written. The whole thing — 33 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Correct

The operator keeps correcting agents in this repo for the same mistakes. Change the repo so the next agent can't make them.

Assume every contributor is an agent that sees only the files it opened, copies the nearest example, and takes the shortest path that compiles. Design the repo so a change that looks right from one file is right for the whole repo.

Find the mistake classes

First, read recent commits, reverts, review comments, agent instruction files, and comments that explain workarounds. Group the mistakes into classes. A class counts once it has happened twice.

Fix each class at the highest level that works

  1. Eliminate it with architecture. Give each piece of state one owner and each task one supported way. Hide internals so the wrong import fails. Replace hand-synced lists with one source of truth. Delete old ways and dead code an agent would copy.
  2. Enforce it with types so the bad state can't be written. If bad code still compiles, add a lint or CI check whose error names the file, type, or function to use instead. If the pattern is already common, fail only when a change adds more.
  3. Test the behavior. Fix or delete any test that still passes when the behavior it checks breaks, or that fails when only the internals change.
  4. Write docs or agent rules last, only for judgment calls. Nothing fails when an agent skips them.

Fix and prove

Then fix the most frequent classes now, one commit each. Prove each new check fails on a real past mistake. Run the same command locally and in CI. Exceptions go on the offending line with a reason, an expiry date, and a human's approval.

Keep the rule table

Last, keep a table in the agent instruction file that pairs each rule with what enforces it. When the operator corrects you, fix the mistake and add the rule. If the rule was already there and nothing enforces it, that's a repeat, so fix it at the highest level in the same change. Drop a rule once its mistake can't happen.

Read the full file on GitHub · 33 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. 10d ago First seen · 33 lines · 68 tokens per session scan A e347045d00c9

Subscribe to this mod's changes

correct is a skill published in the GitHub repository kwaa/skills (2 stars, last pushed 11d ago), licensed MIT. It adds 68 tokens to every session and 544 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 91% identical to correct, differing in 1 line, and is treated as a copy.

Related

correct compared with skills from other repositories

correct next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
correctkwaa/skillsSkill211d agoMITA68Claude Code
agent-watchdogBuilderIO/skillsSkill4.6k5d agoMITA115Claude Code, Codex
comet-verifyrpamis/cometSkill3.3kyesterdayMITA32Claude Code, Codex
agent-teams-simplify-and-hardenLeoYeAI/openclaw-master-skillsSkill2.2k6d agoMITA115Claude Code, Codex
no-commentsbacknotprop/pstackSkill3.8kyesterdayMITA20Claude Code, Cursor
graphify-dotnetmanagedcode/dotnet-skillsSkill509todayMITA125Claude Code, Codex
pr-description-writermohitagw15856/pm-claude-skillsSkill1.5kyesterdayMITA80Claude Code, Codex