clean

clean is a skill for Claude Code from flavien-ia/hypervibe-harness. It costs 75 tokens per session (7,488 once invoked), scanned A, original, Apache-2.0.

A project-hygiene audit looks for files, code, dependencies, environment variables, database tables, and migrations that no longer appear to be used.

In plain words
What is it for?
It audits unused project material, reports its findings, and applies validated deletions on a separate Git branch for review.
Why use it?
It helps reduce clutter and identify old project parts that may be safe to remove, while recording how certain and risky each finding is.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_SKILL_DIR} variable. Also seen: mentions Claude Code; mentions Codex.

Part of the hypervibe plugin — 86 skills, 1 hook, 1 MCP server shipped together

Good fit It audits unused project material, reports its findings, and applies validated deletions on a separate Git branch for review.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/flavien-ia/hypervibe-harness/clean
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 flavien-ia/hypervibe-harness --skill clean
Clone the repo
git clone --depth 1 https://github.com/flavien-ia/hypervibe-harness

Made for: Claude Code.

Or install hypervibe, the plugin that ships this one along with the rest of its 86 skills, 1 hook, 1 MCP server.

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 clean

README.md
[![agentmods](https://agentmods.dev/badge/skills/flavien-ia/hypervibe-harness/clean/github.svg)](https://agentmods.dev/skills/flavien-ia/hypervibe-harness/clean)
Your own site
<a href="https://agentmods.dev/skills/flavien-ia/hypervibe-harness/clean"><img src="https://agentmods.dev/badge/skills/flavien-ia/hypervibe-harness/clean/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 clean

Your own site · 80×15
<a href="https://agentmods.dev/skills/flavien-ia/hypervibe-harness/clean"><img src="https://agentmods.dev/badge/skills/flavien-ia/hypervibe-harness/clean.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,488 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: 9 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 47
    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.
  • high Tool Misuse · line 435
    Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
    Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
  • high Privilege Escalation · line 81
    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.
  • high Privilege Escalation · line 143
    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.
  • high Privilege Escalation · line 144
    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.
  • high Privilege Escalation · line 145
    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.
  • high Privilege Escalation · line 306
    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 43
    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.
  • medium Excessive Agency · line 50
    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 $0.00075 $0.07488
Opus 5 $0.00037 $0.03744
Sonnet 5 $0.00015 $0.01498
Haiku 4.5 $0.00007 $0.00749

Measured 5d ago against content hash 1b644a087d8c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

clean 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 5d 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/clean/SKILL.md · 450 lines

How it starts

The opening of the file, as written. The whole thing — 450 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Clean - Project hygiene audit

Communication

  • Detect the user's language from the conversation (the user's own messages, anywhere in the session - not just this invocation: a bare slash command like /bootstrap carries no language signal by itself). If nothing in the conversation gives a signal, fall back to the OS locale (node -e "console.log(Intl.DateTimeFormat().resolvedOptions().locale)") before defaulting to English. ALWAYS reply in that language for every user-facing message: questions, progress, confirmations, summaries, errors - including any example text quoted in this skill, which is illustrative and must be translated, never sent verbatim.
  • Use plain, non-technical business language. Never expose internal script names (*.mjs) or jargon; describe actions in human terms.
  • When generating user-facing content for the scaffolded project (UI labels, emails, copy), write it in the user's language too.
  • Show progress as a short natural-language checklist (in-progress and done states).

You audit the project to find what is no longer used, then you propose deletions on a separate branch so the user can verify before merging.

Disclaimer to display at the start of the audit:

⚠️ This report is a diagnostic. Some findings are false positives: your code may use elements in a way that static analysis cannot detect (dynamic imports, references in the database, an env var read by a transitive dependency, external links to pages, and so on). Nothing will be deleted without your explicit approval, and the deletions will be made on a separate branch that you test before merging.


Educational rule (important)

The report must be readable by someone who is not a developer. You may be dealing with a user who knows what they want, but not all the technical jargon.

Concrete rules:

  • When you use a technical term, explain it immediately in parentheses the first time it appears. Example: "An unused export (a function or component exposed by a file, but that no other file picks up)".
  • When you can, prefer a common rephrasing and put the technical term in parentheses. Example: "This file contains bits of code that are saved but never called (dead code)".
  • Use everyday analogies for abstract concepts: a .bak file = "a forgotten photocopy", an unused dependency = "a tool in the toolbox that no one uses", a DB table with no caller = "a storage room that no one has the key to".
  • For the checks the user has to do, explain what verifying it is for - not just the action to take. Example of a bad phrasing: "Check grep -r 'Foo'". Example of a good phrasing: "Open a terminal and type grep -r 'Foo' src/ - you should only see the file that defines Foo. If you see other files, that means Foo is used somewhere, and you must not delete it."
  • Never be condescending. The user is intelligent, they just do not know this domain.

Read the full file on GitHub · 450 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 5d ago First seen · 450 lines · 75 tokens per session scan A 1b644a087d8c

Subscribe to this mod's changes

clean is a skill published in the GitHub repository flavien-ia/hypervibe-harness (37 stars, last pushed yesterday), licensed Apache-2.0. It adds 75 tokens to every session and 7,488 once invoked, about $0.0004 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 2026-09-04.

Related

Other skills, from other repositories

git-advanced-workflows

Master advanced Git workflows including rebasing, cherry-picking, bisect, worktrees, and reflog to maintain clean history and recover from any situation. Use when managing complex Git histories, collaborating on feature branches, or troubleshooting repository issues.

wshobson/agents · 54 tokens

gsd-audit-fix

Autonomous audit-to-fix pipeline — find issues, classify, fix, test, commit.

open-gsd/gsd-core · 25 tokens

git-worktree-precommit-hook-flutter-failure

Fix git pre-commit hook failures in Flutter projects when using git worktrees. Use when: (1) Pre-commit hook with flutter analyze fails during git commit but passes when run manually, (2) Hook output shows "Resolving dependencies..." then immediately fails with no actual analysis errors, (3) Working in a git worktree…

divinevideo/divine-mobile · 153 tokens

git-mastery

Advanced Git: rebase, bisect, reflog, cherry-pick, worktrees, LFS. Triggers: rebase, bisect, cherry-pick, reflog, force push, merge conflict, worktree.

softspark/ai-toolkit · 51 tokens

magpie-setup-upstream-fix

Turn a framework bug or quirk the agent hit while running a Magpie skill or tool into a fix PR against apache/magpie — one PR per issue. First confirms the problem is a framework defect (not a local misconfiguration or a stale snapshot), then searches apache/magpie for an existing issue or PR that already covers it…

apache/magpie · 110 tokens

stage-payload-reverts

Create TRT JIRA bugs, open revert PRs, and trigger payload jobs for high-confidence revert candidates.

openshift-eng/ai-helpers · 26 tokens