awesome-ai-agent-skills: Skill for Claude Code

.agents/skills/exact-coding/SKILL.md

exact-coding is a skill for Claude Code, Codex from LionelHuanSi/awesome-ai-agent-skills. It costs 41 tokens per session (534 once invoked), scanned A, original, MIT.

A set of coding and code-review guidelines based on Karpathy's principles, Claude Code execution patterns, visual checks, layered pull-request reviews, and defenses against look-alike package names.

In plain words
What is it for?
Use it when planning or modifying code, running self-healing loops, checking interfaces visually, reviewing pull requests, or guarding against slopsquatting—the use of a malicious package with a name resembling a legitimate one.
Why use it?
It encourages careful inspection, small targeted edits, simple solutions, and verifiable results while helping review code from several angles.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; mentions Claude Code; installed under .agents/ (shared by several agents).

This is LionelHuanSi/awesome-ai-agent-skills's own configuration. It tells Claude Code and Codex how to work on awesome-ai-agent-skills itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything awesome-ai-agent-skills configures →

Reuse

Borrowing it

Nothing to install: this file belongs to LionelHuanSi/awesome-ai-agent-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/LionelHuanSi/awesome-ai-agent-skills/main/.agents/skills/exact-coding/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/LionelHuanSi/awesome-ai-agent-skills

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 exact-coding

README.md
[![agentmods](https://agentmods.dev/badge/skills/lionelhuansi/awesome-ai-agent-skills/exact-coding/github.svg)](https://agentmods.dev/skills/lionelhuansi/awesome-ai-agent-skills/exact-coding)
Your own site
<a href="https://agentmods.dev/skills/lionelhuansi/awesome-ai-agent-skills/exact-coding"><img src="https://agentmods.dev/badge/skills/lionelhuansi/awesome-ai-agent-skills/exact-coding/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 exact-coding

Your own site · 80×15
<a href="https://agentmods.dev/skills/lionelhuansi/awesome-ai-agent-skills/exact-coding"><img src="https://agentmods.dev/badge/skills/lionelhuansi/awesome-ai-agent-skills/exact-coding.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 534 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 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 $0.00041 $0.00534
Opus 5 $0.00020 $0.00267
Sonnet 5 $0.00008 $0.00107
Haiku 4.5 $0.00004 $0.00053

Measured 11d ago against content hash 25a9800ad515, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

exact-coding 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 11d 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.

.agents/skills/exact-coding/SKILL.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

EXACT Coding & AI Code Review Skill (Enhanced with Claude Code Patterns)

Sourced from steveyo/andrej-karpathy-skills, Claude Code Autonomous Execution Protocols, and 3-Layer AI Code Review standards.


Karpathy's 4 Core Pillars

1. Think Before Coding

  • Never guess code logic, schemas, or file paths without inspecting source files first.
  • If requirements have ambiguities or multiple possible interpretations, explicitly list trade-offs before implementation.

2. Simplicity First

  • Minimum code to solve the problem. Zero speculative code.
  • No unused abstractions, unnecessary configurability, or complex wrapper functions.
  • If a 200-line implementation can be simplified to 50 lines, rewrite it.

3. Surgical Changes

  • Touch only the lines required for the requested feature or fix.
  • Do NOT reformat adjacent unrelated code, reorder imports, or touch working comments.
  • Clean up orphan variables/imports created by your edits, but leave pre-existing dead code untouched.

4. Goal-Driven Execution

  • Every task must have a verifiable outcome (passing unit test, clean build, matching endpoint payload).
  • Run verification tools and inspect logs before declaring success.

Claude Code Autonomous Protocols

1. Autonomous Self-Healing Debug Loop

When a build, test, or execution command fails:

  1. Log Extraction: Read the un-truncated error log immediately. Do NOT guess the cause blindly.
  2. Root Cause Analysis: Identify the broken contract or failing assertion.
  3. Surgical Patch: Apply a targeted code fix without altering unrelated functions.
  4. Re-Verification: Re-run the exact failing test/command. Repeat until 100% SUCCESS is achieved before ending turn.

2. Strict Scope Guard

  • Maintain an explicit whitelist of files authorized for modification.

3. Visual QA & Browser Verification

  • For UI or web endpoint changes, launch a Browser subagent (browser_subagent) to verify layout, screenshots, and logs.

Read the full file on GitHub · 53 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. 11d ago First seen · 53 lines · 41 tokens per session scan A 25a9800ad515

Subscribe to this mod's changes

exact-coding is a skill published in the GitHub repository LionelHuanSi/awesome-ai-agent-skills (3 stars, last pushed 1mo ago), licensed MIT. It adds 41 tokens to every session and 534 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 2026-08-31.