hone:intent-clarity-audit

hone:intent-clarity-audit is a skill for Claude Code from ckorhonen/hone-skills. It costs 69 tokens per session (1,588 once invoked), scanned A, original, MIT.

A code review that finds places where the code’s purpose is hard to understand, especially in recently changed files.

In plain words
What is it for?
Use it to review recent changes or run a regular check for clarity problems. It reports the file, line, code, problem category, and a short explanation.
Why use it?
It highlights unclear names, deeply nested conditional expressions, unexplained true or false arguments, overly dense one-line expressions, and comments that merely repeat the code.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the hone-skills plugin — 8 skills shipped together

Good fit Use it to review recent changes or run a regular check for clarity problems. It reports the file, line, code, problem category, and a short explanation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ckorhonen/hone-skills/intent-clarity-audit
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 ckorhonen/hone-skills --skill intent-clarity-audit
Clone the repo
git clone --depth 1 https://github.com/ckorhonen/hone-skills

Made for: Claude Code.

Or install hone-skills, the plugin that ships this one along with the rest of its 8 skills.

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 hone:intent-clarity-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/ckorhonen/hone-skills/intent-clarity-audit/github.svg)](https://agentmods.dev/skills/ckorhonen/hone-skills/intent-clarity-audit)
Your own site
<a href="https://agentmods.dev/skills/ckorhonen/hone-skills/intent-clarity-audit"><img src="https://agentmods.dev/badge/skills/ckorhonen/hone-skills/intent-clarity-audit/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 hone:intent-clarity-audit

Your own site · 80×15
<a href="https://agentmods.dev/skills/ckorhonen/hone-skills/intent-clarity-audit"><img src="https://agentmods.dev/badge/skills/ckorhonen/hone-skills/intent-clarity-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,588 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 $0.00069 $0.01588
Opus 5 $0.00034 $0.00794
Sonnet 5 $0.00014 $0.00318
Haiku 4.5 $0.00007 $0.00159

Measured 12d ago against content hash 208ac6af9079, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

hone:intent-clarity-audit 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 12d 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.

skills/intent-clarity-audit/SKILL.md · 160 lines

How it starts

The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Intent Clarity Audit

What This Skill Does

Audits source code for patterns that make it harder to understand what the code is doing and why. Focuses on five categories of intent obscurity:

  1. Unclear names: Single-letter variables outside tiny loops, generic names (data, temp, result, val, info, item) in non-trivial scopes, abbreviated names that sacrifice readability.
  2. Nested ternaries: Ternary or conditional expressions nested two or more levels deep.
  3. Unnamed boolean parameters: Function calls passing bare true/false literals without a named parameter, comment, or object wrapper to explain the meaning.
  4. Overly clever one-liners: Dense expressions that chain multiple operations, bitwise tricks used for non-bitwise purposes, regex used inline without explanation, or reduce/fold with complex accumulators.
  5. Restating comments: Comments that describe what the next line does rather than why (e.g., // increment counter before counter++).

Reports findings with file:line, the offending snippet, the category, and a brief explanation of why it harms clarity.

When To Use

  • On a weekly schedule to audit recently changed files.
  • After a large feature branch merges.
  • When reviewing code written by unfamiliar contributors.
  • When the user asks to "find unclear code" or "audit code clarity".

Do Not Use

  • For method length — use hone:method-brevity-audit instead.
  • For duplicated code — use hone:duplication-hunt instead.
  • For test naming — use hone:test-naming-audit instead.
  • For naming specificity (Manager, Handler, Utils) — use hone:naming-specificity-audit instead.
  • To rewrite code. This skill reports findings only.

Inputs To Confirm

  1. Scope: Which directories or file patterns to scan (default: files changed in the last 14 days per git log, falling back to entire repo if no git history).
  2. Recency window: Number of days to look back for changed files (default: 14).
  3. Categories: Which of the five categories to check (default: all).
  4. Exclusions: Glob patterns for files or directories to skip.
  5. Top-N: Maximum findings to report (default: 25).

Read the full file on GitHub · 160 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. 12d ago First seen · 160 lines · 69 tokens per session scan A 208ac6af9079

Subscribe to this mod's changes

hone:intent-clarity-audit is a skill published in the GitHub repository ckorhonen/hone-skills (0 stars, last pushed 4mo ago), licensed MIT. It adds 69 tokens to every session and 1,588 once invoked, about $0.0003 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.