qclean

qclean is a skill for Claude Code, Codex from 3awny/qship. It costs 58 tokens per session (1,159 once invoked), scanned A, original, MIT.

A code-review method for finding defensive or leftover code that no longer serves a purpose. Defensive code adds checks for possible problems; this method keeps valid boundary checks while questioning redundant ones.

In plain words
What is it for?
Use it after implementing a feature to inspect unnecessary null checks, error suppression, unused branches, and over-engineered safeguards in the changed code.
Why use it?
It helps remove noise, speculative branches, and scaffolding that make code harder to understand or can hide real bugs. The review is limited to the relevant change unless a full-repository audit is requested.

Skill for Claude CodeCodex

Part of the qship plugin — 22 skills, 1 agent, 1 hook shipped together

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.

agentmods
npx agentmods add skills/3awny/qship/qclean
Any agent
npx skills add 3awny/qship --skill qclean
Clone the repo
git clone --depth 1 https://github.com/3awny/qship

Made for: Claude Code, Codex.

Or install qship, the plugin that ships this one along with the rest of its 22 skills, 1 agent, 1 hook.

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 qclean

README.md
[![agentmods](https://agentmods.dev/badge/skills/3awny/qship/qclean.svg)](https://agentmods.dev/skills/3awny/qship/qclean)
Your own site
<a href="https://agentmods.dev/skills/3awny/qship/qclean"><img src="https://agentmods.dev/badge/skills/3awny/qship/qclean.svg" alt="Measured on agentmods" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,159 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00058 $0.01159
Opus 5 $0.00029 $0.00580
Sonnet 5 $0.00012 $0.00232
Haiku 4.5 $0.00006 $0.00116

Measured 5d ago against content hash a7299a14e0cf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

qclean 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.

templates/skills/qclean/SKILL.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Clean Code Review

You are a defensive-programming audit specialist. Your goal is to strip out redundant defensive code that hides bugs and adds maintenance burden — while preserving legitimate boundary checks.

Scope

Default to the diff under review (current branch vs develop, or the staged diff if none): git diff develop...HEAD or git diff --cached. The narrow scope keeps signal high. Only run against the whole repo when the user explicitly asks for a "full audit" — otherwise you'll surface hundreds of legitimate boundary checks and bury the real findings.

Patterns to look for

Walk through each. Flag a finding only when you can name the guarantee that makes the defensive code unnecessary — schema constraint, validated upstream, framework invariant, etc. Without that evidence, leave it alone.

1. Error suppression

  • except Exception: (or bare except:) that just logs and continues, or returns a default. Trusted internal operations should fail loudly.
  • try/except whose body has a single line — usually means the catch is masking a real signal.
  • Bare except: pass — never acceptable; minimum bar is logging the caught exception (memory: feedback_no_bare_pass_in_except).
  • Catches that re-raise the same exception with no transformation — pointless.

2. Null / falsy checks that can never trigger

  • if not x: on values guaranteed non-null by ORM (PK after .get() succeeded, validated Pydantic field, NOT NULL DB column).
  • Optional[X] parameter typing where every caller passes a non-None value — drop the Optional, drop the check.
  • Double validation: Pydantic validated at the boundary, then re-validated 3 frames down.
  • dict.get(k, default) when k is in a TypedDict / required Pydantic field. (Inverse: at TypedDict→DB boundaries, prefer .get(k) or default for NOT-NULL columns — see memory feedback_typeddict_safe_get.)
  • Redundant if x is not None and x: — pick one.

3. Dead branches

  • else clauses after a branch that always raise / return.
  • assert followed by code that re-checks the same condition.
  • Catch-all if condition: ... else: pass where the else branch is never meaningful.

Read the full file on GitHub · 82 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. 5d ago First seen · 82 lines · 58 tokens per session scan A a7299a14e0cf

Subscribe to this mod's changes

qclean is a skill published in the GitHub repository 3awny/qship (2 stars, last pushed 2mo ago), licensed MIT. It adds 58 tokens to every session and 1,159 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.

Related

Other skills, from other repositories

remove-ai-marks

Strip multi-vendor AI provenance from owned files: hidden Unicode (Layer A), statistical sampling watermarks via rewrite (Layer B — always offer), and C2PA/EXIF/XMP/container metadata on PNG/JPEG/WebP/SVG/PDF/DOCX/ODT/HTML/MD. Covers Claude, Gemini/SynthID-class, OpenAI provenance surfaces, and open-LLM sampling…

ShadowAqueduct/watermark-remover · 135 tokens

clean-user-facing-text

Audit and finalize authorized natural-language text meant for readers: strip suspicious invisible Unicode, then rewrite prose while keeping facts, meaning, and the writer's voice. Use when the user asks to clean, humanize, polish, or finalize articles, manuscripts, reports, documentation, emails, product copy, UI…

ShadowAqueduct/watermark-remover · 121 tokens

oracle

Author an IMPL-BLIND spec-conformance oracle for an acceptance criterion the policy worklist (clad oracle --required) demands — an empty worklist means don't author unless the user explicitly asks. YOU spawn a blind sub-agent from a spec-only brief, then record it. Activate only when the connected project contains…

qwerfunch/cladding · 82 tokens

reviewer

Philosophical guardrails enforcer — independently audits code, tests, and spec for layered-integrity, Why>What, error-as-data, and the related Ironclad philosophical invariants. Activate only when the connected project contains spec.yaml or the user explicitly names Cladding; ignore ordinary requests in uninitialized…

qwerfunch/cladding · 68 tokens

doctor

Diagnose Cladding runtime health — Claude Code hook liveness and version, CI package pinning, lifecycle governance, and sentinel-miss frequency by phase × cause × fallback. Use when hooks may be silent, CI may float across Cladding releases, scan or run results look thinner than expected, or before tuning the host…

qwerfunch/cladding · 93 tokens

changelog

Render release notes / a changelog from the cladding spec. Use when the user asks for release notes, a changelog, 릴리즈 노트, 변경 이력, or "what changed (since )" — run clad changelog --json for the deterministic shipped-changes manifest, then write the human-facing notes FROM it, sourcing every claim from a feature title or…

qwerfunch/cladding · 121 tokens