Agent skill

Routine Abstraction Improver

by bex-co in bex-co/beancount-io

Autonomous maintenance routine that flattens over-engineered abstractions in a monorepo package — interfaces with one implementation and no stated reason, passthrough wrappers, one-product…

MITAuto-check passedDevelopment

Install Routine Abstraction Improver

skills CLI
$ npx skills add bex-co/beancount-io --skill routine-abstraction-improver -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install bex-co/beancount-io routine-abstraction-improver --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/bex-co/beancount-io.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/routine-abstraction-improver .claude/skills/routine-abstraction-improver && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
routine-abstraction-improver
GitHub stars
295
Token cost
~810 tokens
SKILL.md length
336 words
Files
1
Skills in repo
27
Repo updated
First seen
Licence
MIT

At a glance

Autonomous maintenance routine that flattens over-engineered abstractions in a monorepo package — interfaces with one implementation and no stated reason, passthrough wrappers, one-product…

  • Works in 6 steps: Scope → Discover → Prove it → …
  • Explicitly invokes /routine-abstraction-improver
  • SKILL.md covers Contract, Workflow, What NOT to do and Arguments
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Routine Abstraction Improver is an agent skill from bex-co/beancount-io. Autonomous maintenance routine that flattens over-engineered abstractions in a monorepo package — interfaces with one implementation and no stated reason, passthrough wrappers, one-product factories, delegate-only manager layers — by inlining the single thing behind them and shipping via /ship. Use only when the user explicitly invokes /routine-abstraction-improver or asks to flatten needless indirection. SKIP for convoluted logic inside one unit (routine-logic-simplifier), imports crossing stated boundaries…

Its SKILL.md is about 810 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Monorepo tooling. The repository describes itself as: 💰 Double-entry bookkeeping made easy — plain-text accounting for humans and AI agents. Polished iOS & Android app built with React Native + Expo. The licence is MIT.

When your agent uses it

  • Explicitly invokes /routine-abstraction-improver
  • Asks to flatten needless indirection
  • Is remove indirection that has exactly one thing behind it

Example prompts

  • “remove indirection that has exactly one thing behind it”
  • “/routine-abstraction-improver”

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Scope
  2. Discover
  3. Prove it
  4. Fix
  5. Verify
  6. Ship

What it can do on your machine

Read from SKILL.md and the folder at commit 2103ca1. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Routine Abstraction Improver loads about 810 tokens when it runs. Until then it costs about 176 tokens; SKILL.md has 336 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~176
When it runs · the whole SKILL.md, loaded when a task matches
~810

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from bex-co/beancount-io at commit 2103ca1, republished under its MIT licence (© bex-co). 336 words, ~810 tokens.

Download SKILL.mdSave it as .claude/skills/routine-abstraction-improver/SKILL.md (or your agent's skills folder).
name
routine-abstraction-improver
description
Autonomous maintenance routine that flattens over-engineered abstractions in a monorepo package — interfaces with one implementation and no stated reason, passthrough wrappers, one-product factories, delegate-only manager layers — by inlining the single thing behind them and shipping via /ship. Use only when the user explicitly invokes /routine-abstraction-improver or asks to flatten needless indirection. SKIP for convoluted logic inside one unit (routine-logic-simplifier), imports crossing stated boundaries (routine-abstraction-police), and duplicated implementations (routine-dup-unifier). The core trigger is "remove indirection that has exactly one thing behind it".

Task: Flatten over-engineered abstractions

Usage: /routine-abstraction-improver [package-or-path]

Find a layer of indirection with exactly one thing behind it and no stated reason to exist, inline it, delete the layer, and ship via /ship.

Contract

Read .agents/skills/routine-shared/contract.md first — preconditions, scope resolution, verify gates, ship protocol, budget, universal STOPs. Floor even without it: never ship red; one finding per ship; anything in a DO_NOT_DO.md is a hard STOP.

Workflow

1. Scope

Resolve scope per the contract.

2. Discover

The shapes worth suspecting:

  • Interfaces/abstract classes with exactly one implementation
  • Wrapper functions/modules that only re-export or forward arguments
  • Factories that can only ever produce one product
  • Generics never instantiated with a second type
  • "Manager"/"provider"/"service" layers that purely delegate
3. Prove it

A layer is a finding only when all hold:

  1. Grep confirms exactly one implementation and one usage pattern.
  2. No stated reason for it exists. Check the scoped AGENTS.md, docs/adrs/, and .pm boards. In particular: backend-v2 mandates an I<Name> interface beside every service/workflow class (backend-cluster/backend-v2/AGENTS.md, Dependency and layer rules) — those interfaces are a stated convention, never a finding. Same for seams that exist so tests can double them, when the tests actually do.
  3. No evidence of a planned second implementation.
4. Fix

Inline the single thing, delete the layer, call directly. If tests mocked the deleted layer, rewrite them against the concrete unit with real assertions — never leave them asserting a mock of something that no longer exists. Behavior identical.

5. Verify

Typecheck + full owning-package gate, and a grep confirming no dangling references to the deleted layer.

6. Ship

Compose /ship for this one flattening. Loop within budget.

What NOT to do

  • Never flatten an abstraction a AGENTS.md, ADR, or working test double justifies — a stated convention beats this routine's taste, every time.
  • Don't rewrite convoluted logic inside a unit (routine-logic-simplifier) or move code across layers (routine-abstraction-police).
  • Don't flatten two layers in one ship; each deletion stands alone.
  • Don't replace the deleted abstraction with a cleverer one — the fix is less structure, not different structure.

Arguments

$ARGUMENTS

© bex-co, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/routine-abstraction-improver of bex-co/beancount-io.

Open the folder on GitHubat commit 2103ca1

Compare with similar skills

Routine Abstraction Improver next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Routine Abstraction Improver compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Routine Abstraction Improver this skillbex-co/beancount-io295—~810Automated safety check: PassMIT
Sanity Radar Investigatesanity-io/sanity6.4k—~1.5kAutomated safety check: PassMIT
Nx Importnrwl/nx29k6 repos~3.5kAutomated safety check: PassMIT
Nx Workspacenomcopter/react-mosaic4.8k8 repos~1.9kAutomated safety check: PassCustom licence
Electron Multi-Process ArchitectureiOfficeAI/AionUi33k1 repos~1.8kAutomated safety check: PassApache-2.0
Nx Run Tasksnomcopter/react-mosaic4.8k8 repos~613Automated safety check: PassCustom licence

Similar skills

  • Sanity Radar Investigate

    sanity-io/sanity

    Official

    Investigate a suspected Studio performance regression surfaced by Studio Radar or the bench suite — confirm the signal against host calibration, narrow the commit range, confirm with an A/B…

    6.4k GitHub stars~1.5k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Nx Import

    nrwl/nx

    Import, merge, or combine repositories into an Nx workspace using nx import.

    29k GitHub starsUsed in 6 repos~3.5k tokens
    DevelopmentAuto-check passed
  • Nx Workspace

    nomcopter/react-mosaic

    Explore and understand Nx workspaces. An agent skill from nomcopter/react-mosaic.

    4.8k GitHub starsUsed in 8 repos~1.9k tokens
    DevelopmentAuto-check passed
  • Tells the agent where new code belongs in an Electron multi-process project and which APIs each process may use, with rules for new bridges, services, agents and workers.

    33k GitHub starsUsed in 1 repo~1.8k tokens
    DevelopmentAuto-check passed
  • Nx Run Tasks

    nomcopter/react-mosaic

    Helps with running tasks in an Nx workspace. An agent skill from nomcopter/react-mosaic.

    4.8k GitHub starsUsed in 8 repos~613 tokens
    DevelopmentAuto-check passed
  • Astro Developer

    withastro/astro

    Official

    Comprehensive guide for developing in the Astro monorepo. An agent skill from withastro/astro.

    63k GitHub starsUsed in 1 repo~1.5k tokens
    DevelopmentAuto-check passed

More from bex-co/beancount-io

All 27 skills in this repo
  • Beancount Close

    bex-co/beancount-io

    Close an accounting period in a Beancount ledger by reconciling each active account through beancount-reconcile, checking assertions and recurring gaps, reviewing flags, then proposing a commit with…

    295 GitHub stars~1.4k tokensUpdated yesterday
    Auto-check passed
  • Beancount Import

    bex-co/beancount-io

    Import a bank or card CSV, OFX/QFX, or QIF export into an existing Beancount ledger.

    295 GitHub stars~3k tokensUpdated yesterday
    Auto-check passed
  • Beancount Importer Author

    bex-co/beancount-io

    Write or repair a reusable Beangulp importer from a sample bank export, with reviewed golden files and a passing test harness.

    295 GitHub stars~2k tokensUpdated yesterday
    Auto-check passed
  • Beancount Init

    bex-co/beancount-io

    Scaffold a new Beancount ledger with bea init and validation, with optional Fava browser setup when requested.

    295 GitHub stars~1.2k tokensUpdated yesterday
    Auto-check: notes
  • Beancount Options

    bex-co/beancount-io

    Record a described options trade or lifecycle event as validated Beancount transactions through bea, after review and confirmation.

    295 GitHub stars~3.7k tokensUpdated yesterday
    Auto-check passed
  • Beancount Reconcile

    bex-co/beancount-io

    Reconcile one Beancount account against a CSV statement or pasted PDF text.

    295 GitHub stars~4.1k tokensUpdated yesterday
    Auto-check passed

Questions about Routine Abstraction Improver

What does Routine Abstraction Improver do?

Autonomous maintenance routine that flattens over-engineered abstractions in a monorepo package — interfaces with one implementation and no stated reason, passthrough wrappers, one-product…. Routine Abstraction Improver is an agent skill from bex-co/beancount-io. Autonomous maintenance routine that flattens over-engineered abstractions in a monorepo package — interfaces with one implementation and no stated reason, passthrough wrappers, one-product factories, delegate-only manager layers — by inlining the single thing behind them and shipping via /ship.

When should I use Routine Abstraction Improver?

Routine Abstraction Improver fits situations like: explicitly invokes /routine-abstraction-improver; asks to flatten needless indirection; is remove indirection that has exactly one thing behind it.

How do I install Routine Abstraction Improver in Claude Code?

Run `npx skills add bex-co/beancount-io --skill routine-abstraction-improver -a claude-code`. Or copy the skill folder (.agents/skills/routine-abstraction-improver in bex-co/beancount-io) into .claude/skills/routine-abstraction-improver in your project. Claude Code loads it when a task matches its description.

How do I install Routine Abstraction Improver in Codex?

Run `npx skills add bex-co/beancount-io --skill routine-abstraction-improver -a codex`. Or copy the skill folder (.agents/skills/routine-abstraction-improver in bex-co/beancount-io) into .agents/skills/routine-abstraction-improver in your project. Codex loads it when a task matches its description.

Can I use Routine Abstraction Improver in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add bex-co/beancount-io --skill routine-abstraction-improver -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/routine-abstraction-improver, .gemini/skills/routine-abstraction-improver, .github/skills/routine-abstraction-improver and .opencode/skills/routine-abstraction-improver in your project.

What does Routine Abstraction Improver need to run?

SKILL.md names no scripts, command-line tools or credentials: Routine Abstraction Improver is instructions for the agent only.

Does Routine Abstraction Improver access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Routine Abstraction Improver safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Routine Abstraction Improver use?

Routine Abstraction Improver is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Routine Abstraction Improver use?

About 810 tokens (SKILL.md is roughly 3.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Routine Abstraction Improver?

Skills that share tags, products or a category with Routine Abstraction Improver: Sanity Radar Investigate (sanity-io/sanity, 6.4k stars), Nx Import (nrwl/nx, 29k stars), Nx Workspace (nomcopter/react-mosaic, 4.8k stars) and Electron Multi-Process Architecture (iOfficeAI/AionUi, 33k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Routine Abstraction Improver?

bex-co (a GitHub organization) maintains it in bex-co/beancount-io, which has 295 GitHub stars. The repository holds 27 skills in this directory. The repository was last updated on October 7, 2026.

Source: bex-co/beancount-io on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.