hk-slop-audit

hk-slop-audit is a skill for Claude Code from deepklarity/harness-kit. It costs 90 tokens per session (1,205 once invoked), scanned A, original, MIT.

A codebase hygiene audit that looks for abandoned, misplaced, duplicated, insecure, or otherwise unnecessary project material. It produces findings ranked from P0, the most urgent, to P4, the least urgent.

In plain words
What is it for?
Use it to inspect a whole repository or a selected area for misplaced files, dead code, temporary files, security issues, dependency clutter, and Git-related clutter. It returns a prioritized report with suggested actions.
Why use it?
It helps uncover the clutter and structural problems that accumulate as a project changes. The audit also considers project instructions so deliberate unusual patterns are not mistaken for mistakes.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md; mentions subagents.

Good fit Use it to inspect a whole repository or a selected area for misplaced files, dead code, temporary files, security issues, dependency clutter, and Git-related clutter. It returns a prioritized report with suggested actions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/deepklarity/harness-kit/hk-slop-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 deepklarity/harness-kit --skill hk-slop-audit
Clone the repo
git clone --depth 1 https://github.com/deepklarity/harness-kit

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 hk-slop-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/deepklarity/harness-kit/hk-slop-audit/github.svg)](https://agentmods.dev/skills/deepklarity/harness-kit/hk-slop-audit)
Your own site
<a href="https://agentmods.dev/skills/deepklarity/harness-kit/hk-slop-audit"><img src="https://agentmods.dev/badge/skills/deepklarity/harness-kit/hk-slop-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 hk-slop-audit

Your own site · 80×15
<a href="https://agentmods.dev/skills/deepklarity/harness-kit/hk-slop-audit"><img src="https://agentmods.dev/badge/skills/deepklarity/harness-kit/hk-slop-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 90 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,205 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 warn 7 Sept 2026
SkillSpector: 2 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Privilege Escalation · line 38
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
  • medium Excessive Agency · line 48
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 $0.00090 $0.01205
Opus 5 $0.00045 $0.00602
Sonnet 5 $0.00018 $0.00241
Haiku 4.5 $0.00009 $0.00120

Measured 10d ago against content hash af1c1163fb41, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

hk-slop-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 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.

.claude/skills/hk-slop-audit/SKILL.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/hk-slop-audit — Codebase Hygiene Auditor

Systematically scan the codebase for slop — code that degrades quality through misplacement, abandonment, inconsistency, or negligence. Produce a prioritized, actionable report.

Scope

<audit_scope> $ARGUMENTS </audit_scope>

If a scope is provided, focus on that directory or category. Otherwise, audit the entire repository.

What is slop?

Slop is anything that makes a developer say "wait, why is this here?" or "is this still used?" It's the entropy that accumulates when people add things but never clean up.

Process

Step 1: Map the project structure

Use Glob and Bash (ls) to understand the directory layout, build systems, and language boundaries. Read the root CLAUDE.md and any project-level CLAUDE.md files to understand intentional patterns — things that look unusual but are deliberate are not slop.

Step 2: Scan each category

Work through each category using parallel subagents where possible. Each subagent scans one category and returns findings.

Category 1 — Misplaced Files: Files in the wrong directory. A Python script in a frontend dir. A test file in src. A config file at the wrong level.

Category 2 — Dead & Orphaned Code: Unused imports, functions nothing calls, commented-out code blocks, orphaned tests for deleted functionality, stale feature flags.

Category 3 — Temp & Scratch Files: Files named temp_, scratch_, debug_, old_, backup_*. One-off scripts (populate_data, fix_migration, quick_test). Log files or build artifacts committed to git.

Category 4 — Security & Config Slop: Hardcoded localhost URLs/ports/credentials. Committed .env files, API keys, tokens. Default passwords in non-example files. Overly permissive CORS/auth settings.

Category 5 — Structural Slop: Duplicate logic across files. Inconsistent naming conventions. God files (>500 lines doing multiple things). Circular imports. Docs describing behavior the code no longer has.

Category 6 — Dependency Slop: Unused dependencies. Pinned versions with known vulnerabilities. Multiple packages doing the same thing. Dev dependencies in production lists.

Read the full file on GitHub · 118 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 · 118 lines · 90 tokens per session scan A af1c1163fb41

Subscribe to this mod's changes

hk-slop-audit is a skill published in the GitHub repository deepklarity/harness-kit (97 stars, last pushed 1mo ago), licensed MIT. It adds 90 tokens to every session and 1,205 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.

Related

Other skills, from other repositories

neuron-debugger

Debug and monitor Neuron AI applications with Inspector APM, event observability, logging, and performance analysis. Use this skill whenever the user mentions debugging, monitoring, observability, performance analysis, tracing, Inspector, or needs to understand why an agent is behaving a certain way. Also trigger for…

neuron-core/neuron-ai · 90 tokens

diag-harness

Kernel-version skew check (ADR-027). Reports manifest surface + manifest kernel + installed kernel + verdict (match/patch-diff/minor-diff/major-diff). Exits 1 on minor/major skew with a copy-pasteable npm install @metaharness/[email protected] next step. Exits 2 if no .harness/manifest.json at path.

ruvnet/metaharness · 85 tokens

debug-manual

Manual debug loop with deep Belmont context and in-place spec reconciliation — user-verified fix + correct the specs that let the bug exist.

blake-simpson/belmont · 30 tokens

debug-auto

Auto debug loop — investigate, fix, verify using agent-dispatched pipeline.

blake-simpson/belmont · 17 tokens

debug

Debug router — choose between auto (agent-verified, narrow code fix) and manual (user-verified, deep spec context, in-place spec reconciliation).

blake-simpson/belmont · 33 tokens

neuron-debugger

Debug and monitor Neuron AI applications with Inspector APM, event observability, logging, and performance analysis. Use this skill whenever the user mentions debugging, monitoring, observability, performance analysis, tracing, Inspector, or needs to understand why an agent is behaving a certain way. Also trigger for…

neuron-core/neuron-laravel · 90 tokens