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.
npx skills add deepklarity/harness-kit --skill hk-slop-auditgit clone --depth 1 https://github.com/deepklarity/harness-kitWrote 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.
[](https://agentmods.dev/skills/deepklarity/harness-kit/hk-slop-audit)<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.
<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>- NVIDIA SkillSpector warn
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.
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.
| Model | Per session | Once 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 |
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.
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.
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.
- 10d ago First seen · 118 lines · 90 tokens per session scan A af1c1163fb41
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.
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…
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.
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.
debug-auto
Auto debug loop — investigate, fix, verify using agent-dispatched pipeline.
debug
Debug router — choose between auto (agent-verified, narrow code fix) and manual (user-verified, deep spec context, in-place spec reconciliation).
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…