drift: Skill for Claude Code

.github/skills/simplify-and-harden/SKILL.md

simplify-and-harden is a skill for Claude Code from mick-gsk/drift. It costs 92 tokens per session (1,918 once invoked), scanned A, original, MIT.

A post-completion review process for coding agents that checks changed code for simplification, safety, and small documentation improvements. It applies only after a substantial coding change.

In plain words
What is it for?
It is for reviewing non-trivial changes, especially code involving authentication, validation, data access, file paths, network requests, or concurrency.
Why use it?
It catches unnecessary complexity, safety problems, and missing explanations before the work is handed over. Its scope is limited to code changed in the current task.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions CLAUDE.md; mentions AGENTS.md; built for openclaw.

This is mick-gsk/drift's own configuration. It tells Claude Code how to work on drift itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything drift configures →

Part of the drift plugin — 31 skills, 17 agents shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to mick-gsk/drift. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/mick-gsk/drift/main/.github/skills/simplify-and-harden/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/mick-gsk/drift

Made for: Claude Code.

Or install drift, the plugin that ships this one along with the rest of its 31 skills, 17 agents.

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 simplify-and-harden

README.md
[![agentmods](https://agentmods.dev/badge/skills/mick-gsk/drift/simplify-and-harden/github.svg)](https://agentmods.dev/skills/mick-gsk/drift/simplify-and-harden)
Your own site
<a href="https://agentmods.dev/skills/mick-gsk/drift/simplify-and-harden"><img src="https://agentmods.dev/badge/skills/mick-gsk/drift/simplify-and-harden/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 simplify-and-harden

Your own site · 80×15
<a href="https://agentmods.dev/skills/mick-gsk/drift/simplify-and-harden"><img src="https://agentmods.dev/badge/skills/mick-gsk/drift/simplify-and-harden.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 92 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,918 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 $0.00092 $0.01918
Opus 5 $0.00046 $0.00959
Sonnet 5 $0.00018 $0.00384
Haiku 4.5 $0.00009 $0.00192

Measured 10d ago against content hash e5ffed1f4b6b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

simplify-and-harden 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.

.github/skills/simplify-and-harden/SKILL.md · 190 lines

How it starts

The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Skill: Simplify & Harden

Post-completion self-review: clean, harden, and document your work before moving on.

Source: https://clawhub.ai/pskoett/simplify-and-harden (v1.0.1, MIT-0, VirusTotal: Benign, OpenClaw: Benign HIGH CONFIDENCE)

Trigger Conditions

Activate automatically when ALL of the following are true:

  1. The agent has completed its primary coding task
  2. The diff contains a non-trivial code change:
    • Touches at least one executable source file (*.py, *.ts, *.js, *.go, *.rs, etc.)
    • AND includes either ≥10 changed non-comment/non-whitespace lines OR at least one high-impact logic change (auth/authz, input validation, data access, external commands, file paths, network requests, concurrency)
  3. The skill has not already run on this task (no re-entry loops)

Does NOT activate when:

  • The change is docs-only, config-only, comments-only, formatting-only, generated artifacts only, or tests-only
  • The agent failed or was interrupted
  • User explicitly skips via --no-review

Scope Constraints

Hard rule: Only touch code modified in this task.

  • Do NOT refactor adjacent code that was not modified
  • Do NOT introduce new dependencies or architectural changes
  • Flag out-of-scope concerns in the summary output rather than acting on them

Budget limits:

  • Maximum additional changes: 20% of the original diff size (lines changed)
  • Maximum execution time: 60 seconds
  • If either limit is hit, stop and output what you have with a budget_exceeded flag

Pass 1: Simplify

Objective: Reduce unnecessary complexity introduced during implementation.

Default posture: Simplify, don't restructure. Bias heavily toward cosmetic fixes. Refactoring is the exception.

Fresh-eyes start (mandatory): Before any edits, re-read all code added or modified with fresh eyes. Actively look for obvious bugs, confusing logic, brittle assumptions, and naming issues.

Review Checklist

  • Dead code — debug logs, commented-out attempts, unused imports, temp variables
  • Naming clarity — function/variable names that made sense mid-implementation but read poorly after
  • Control flow — nested conditionals that can be flattened, deep nesting replaceable by early returns
  • API surface — exposed more than necessary? Can public methods become private?
  • Over-abstraction — classes or wrappers not justified by current scope
  • Consolidation — logic spread across functions/files when it could live in one place

Read the full file on GitHub · 190 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 · 190 lines · 92 tokens per session scan A e5ffed1f4b6b

Subscribe to this mod's changes

simplify-and-harden is a skill published in the GitHub repository mick-gsk/drift (15 stars, last pushed 1mo ago), licensed MIT. It adds 92 tokens to every session and 1,918 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

umbra-trust-review

Verify AI-generated code before shipping. Run Umbra's Trust Score scan before committing or finishing any coding task, treat findings as blocking issues, and re-scan until clean. Use when finishing a task, before a commit, or when reviewing code written by an agent.

elberacasa/umbra · 60 tokens

ai-debt-audit

Scan a repository for AI-generated technical, cognitive, and intent debt. Use when the user asks to audit a codebase for AI/vibe-coding risk, check for issues an AI coding assistant may have introduced (disabled RLS, hardcoded secrets, missing auth checks, SSTI, debug mode left on), assess technical debt after heavy…

aniruddhavasudev/ai-debt-audit · 108 tokens

rework-rate

Measure and interpret PR rework rate — the emerging 5th DORA metric.

bradygaster/squad · 20 tokens

truecourse-analyze

Run TrueCourse architecture analysis on this repository.

truecourse-ai/truecourse · 13 tokens

argot-setup

Set argot up for a repository end to end — audit its history, decide what should shape its voice, fit, verify the fit actually catches things, tune the rules its own history says are noisy, and wire the places it runs (pre-write hook, pre-commit, MCP, CI). One sitting, one decision at a time, each proposed with the…

get-tmonier/argot · 129 tokens

argot-check

Score your working changes with argot — flag code foreign to this repo's own patterns (unfamiliar dependencies, APIs, constructs), functions the repo already has, code filed in the wrong place, imports that break the repo's layering, and tests weakened, disabled, or deleted alongside a production change — before…

get-tmonier/argot · 110 tokens