Project Creator
aiskillstore/marketplace
Creates new projects in CCGG Business Operations with all required mechanisms automatically implemented.
Autonomous maintenance routine that finds imports crossing a stated architectural boundary the wrong way — cross-package imports, dashboard features reaching into each other, backend-v2 transport…
Install Routine Abstraction Police
$ npx skills add bex-co/beancount-io --skill routine-abstraction-police -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install bex-co/beancount-io routine-abstraction-police --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ 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-police .claude/skills/routine-abstraction-police && rm -rf skills-srcUse ~/.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/
Install the "routine-abstraction-police" agent skill from https://github.com/bex-co/beancount-io/tree/main/.agents/skills/routine-abstraction-police into .claude/skills/routine-abstraction-police/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "routine-abstraction-police", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/bex-co/beancount-io/tree/main/.agents/skills/routine-abstraction-policeType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add bex-co/beancount-io --skill routine-abstraction-police -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install bex-co/beancount-io routine-abstraction-police --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/bex-co/beancount-io.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/routine-abstraction-police .agents/skills/routine-abstraction-police && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "routine-abstraction-police" agent skill from https://github.com/bex-co/beancount-io/tree/main/.agents/skills/routine-abstraction-police into .agents/skills/routine-abstraction-police/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "routine-abstraction-police", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add bex-co/beancount-io --skill routine-abstraction-police -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install bex-co/beancount-io routine-abstraction-police --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/bex-co/beancount-io.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/routine-abstraction-police .cursor/skills/routine-abstraction-police && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "routine-abstraction-police" agent skill from https://github.com/bex-co/beancount-io/tree/main/.agents/skills/routine-abstraction-police into .cursor/skills/routine-abstraction-police/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "routine-abstraction-police", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/bex-co/beancount-io.git --path .agents/skills/routine-abstraction-police--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add bex-co/beancount-io --skill routine-abstraction-police -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install bex-co/beancount-io routine-abstraction-police --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/bex-co/beancount-io.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/routine-abstraction-police .gemini/skills/routine-abstraction-police && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "routine-abstraction-police" agent skill from https://github.com/bex-co/beancount-io/tree/main/.agents/skills/routine-abstraction-police into .gemini/skills/routine-abstraction-police/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "routine-abstraction-police", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install bex-co/beancount-io routine-abstraction-policeInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add bex-co/beancount-io --skill routine-abstraction-police -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/bex-co/beancount-io.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/routine-abstraction-police .github/skills/routine-abstraction-police && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "routine-abstraction-police" agent skill from https://github.com/bex-co/beancount-io/tree/main/.agents/skills/routine-abstraction-police into .github/skills/routine-abstraction-police/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "routine-abstraction-police", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add bex-co/beancount-io --skill routine-abstraction-police -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install bex-co/beancount-io routine-abstraction-police --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/bex-co/beancount-io.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/routine-abstraction-police .opencode/skills/routine-abstraction-police && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "routine-abstraction-police" agent skill from https://github.com/bex-co/beancount-io/tree/main/.agents/skills/routine-abstraction-police into .opencode/skills/routine-abstraction-police/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "routine-abstraction-police", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
routine-abstraction-police- GitHub stars
- 296
- Token cost
- ~1k tokens
- SKILL.md length
- 472 words
- Files
- 1
- Skills in repo
- 27
- Repo updated
- First seen
- Licence
- MIT
At a glance
Autonomous maintenance routine that finds imports crossing a stated architectural boundary the wrong way — cross-package imports, dashboard features reaching into each other, backend-v2 transport…
- Works in 6 steps: Scope → Discover — the stated rules and their… → Prove it → …
- Explicitly invokes /routine-abstraction-police
- SKILL.md covers Contract, The one proof rule, Workflow and What NOT to do, plus 1 more section
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Routine Abstraction Police is an agent skill from bex-co/beancount-io. Autonomous maintenance routine that finds imports crossing a stated architectural boundary the wrong way — cross-package imports, dashboard features reaching into each other, backend-v2 transport adapters touching models, mobile routes bypassing screens — and fixes each violation by moving code or inverting the dependency, shipping via /ship. Use only when the user explicitly invokes /routine-abstraction-police or asks to fix layering violations. Only rules stated in a AGENTS.md count; SKIP for too-many-layers…
Its SKILL.md is about 1k 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 Agent Workflows, covering Agent instruction files. 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-police
- Asks to fix layering violations
- Is this import points the wrong way across a stated boundary
Example prompts
- “this import points the wrong way across a stated boundary”
- “/routine-abstraction-police”
Workflow steps
6 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 2e520db. 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 Police loads about 1k tokens when it runs. Until then it costs about 175 tokens; SKILL.md has 472 words of instructions outside code blocks.
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 2e520db, republished under its MIT licence (© bex-co). 472 words, ~1,035 tokens.
Download SKILL.mdSave it as
.claude/skills/routine-abstraction-police/SKILL.md (or your agent's skills folder).- name
- routine-abstraction-police
- description
- Autonomous maintenance routine that finds imports crossing a stated architectural boundary the wrong way — cross-package imports, dashboard features reaching into each other, backend-v2 transport adapters touching models, mobile routes bypassing screens — and fixes each violation by moving code or inverting the dependency, shipping via /ship. Use only when the user explicitly invokes /routine-abstraction-police or asks to fix layering violations. Only rules stated in a AGENTS.md count; SKIP for too-many-layers (routine-abstraction-improver) and duplicated logic (routine-dup-unifier). The core trigger is "this import points the wrong way across a stated boundary".
Task: Fix imports that cross a stated boundary the wrong way
Usage: /routine-abstraction-police [package-or-path]
Find an import that violates a boundary this repo has written down, fix it by
moving code to the right layer or inverting the dependency, 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.
The one proof rule
A violation exists only against a rule stated in a AGENTS.md (root or
scoped) or an ADR. Your own taste in layering is not a rule. Before fixing,
quote the rule; re-read the scoped AGENTS.md of the target package for rules
beyond the seed list below. No stated rule → no finding.
Workflow
1. Scope
Resolve scope per the contract.
2. Discover — the stated rules and their greps
- Repo-wide (root
AGENTS.md): no cross-package imports — grep for relative imports escaping the package root and cross-package path aliases. - dashboard (
dashboard/AGENTS.md): one feature must not import another feature's private component/utility (cross-feature infrastructure belongs insrc/common/); route files undersrc/routes/stay thin and import the feature page — grepsrc/features/*for imports from sibling features. - backend-v2 (
backend-cluster/backend-v2/AGENTS.md, Dependency and layer rules): resolvers/REST handlers delegate — they do not access models or orchestrate several services; workflows must not import GraphQL DTOs fromapi/; services stay transport-agnostic; models hold persistence only. - mobile (
mobile/AGENTS.md):app/route files mount screens fromsrc/screens/— screen logic does not live inapp/;src/generated-graphql/is codegen output nothing hand-edits.
3. Prove it
Read the violating import in context and quote the stated rule it breaks. Confirm the violation is real usage, not a type-only import a rule permits.
Show full SKILL.md (189 more words)Show less
4. Fix
Pick the smallest correct repair:
- Move the code to the layer both sides may depend on (
src/common/, a service,src/shared/). - Invert the dependency — pass the value/callback in as a parameter or prop instead of importing downward.
- Duplicate a tiny helper (≤10 lines, with a comment naming the twin) when
sharing would demand a worse structure — explicitly not a
routine-dup-unifierfinding at that size.
For a cross-package violation, the fix lives entirely on the violating side (duplicate or restructure locally); touching the other package is a separate concern and usually a universal STOP.
5. Verify
Full owning-package gate, plus re-grep to show the violating pattern is gone and no new one was introduced.
6. Ship
Compose /ship for this one violation. Loop within budget.
What NOT to do
- Never invent a boundary. If the structure feels wrong but no rule says so, propose the rule in the summary — don't enforce it.
- Don't remove layers (
routine-abstraction-improver) or unify duplicates (routine-dup-unifier). - Never "fix" a violation by weakening the rule's
AGENTS.mdwording. - Never hand-edit codegen output to satisfy a boundary — regenerate or restructure the source instead.
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-police of bex-co/beancount-io.
Open the folder on GitHubat commit 2e520db
Compare with similar skills
Routine Abstraction Police 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Routine Abstraction Police this skillbex-co/beancount-io | 296 | — | ~1k | Automated safety check: Pass | MIT | |
| Project Creatoraiskillstore/marketplace | 433 | — | ~5.9k | Automated safety check: Pass | None | |
| Docs Gardeningmhmzdev/the-holy-quran-app | 888 | — | ~1.1k | Automated safety check: Pass | MIT | |
| Improve Idea Critiqueassafkip/kipi-system | 112 | — | ~729 | Automated safety check: Pass | MIT | |
| Mine HistoryZoneMinder/zmNinjaNg | 112 | — | ~1k | Automated safety check: Pass | Apache-2.0 | |
| Happier Profile And Optimizehappier-dev/happier | 1.9k | — | ~3.2k | Automated safety check: Pass | MIT |
Similar skills
Docs Gardening
mhmzdev/the-holy-quran-app
Audit and maintain The Holy Qur'an app's knowledge base (AGENTS.md, .agents/rules/, docs/ OKF bundle) for staleness, broken cross-links, drift from code, and OKF structural issues.
Improve Idea Critique
assafkip/kipi-system
Judges a pasted tip, post or video summary against what the kipi system already has, and returns adopt, skip or already-built with the files that back the verdict.
Mine History
ZoneMinder/zmNinjaNg
A skill your agent uses when asked to mine the commit history for lessons the agent instruction files have not captured, to audit whether domain-context and contracts reflect what actually broke, or…
Happier Profile And Optimize
happier-dev/happier
The method for profiling and optimizing anything whose success is a measured cost — frame the phase and metric, choose an instrument that can actually see the cost, label the waste, falsify the…
User Onboarding Sop
IgorWarzocha/Opencode-Workflows
Generate AGENTS.md for end-user assistance. An agent skill from IgorWarzocha/Opencode-Workflows.
More from bex-co/beancount-io
All 27 skills in this repoBeancount 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…
Beancount Import
bex-co/beancount-io
Import a bank or card CSV, OFX/QFX, or QIF export into an existing Beancount ledger.
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.
Beancount Init
bex-co/beancount-io
Scaffold a new Beancount ledger with bea init and validation, with optional Fava browser setup when requested.
Beancount Options
bex-co/beancount-io
Record a described options trade or lifecycle event as validated Beancount transactions through bea, after review and confirmation.
Beancount Reconcile
bex-co/beancount-io
Reconcile one Beancount account against a CSV statement or pasted PDF text.
Related
Questions about Routine Abstraction Police
What does Routine Abstraction Police do?
Autonomous maintenance routine that finds imports crossing a stated architectural boundary the wrong way — cross-package imports, dashboard features reaching into each other, backend-v2 transport…. Routine Abstraction Police is an agent skill from bex-co/beancount-io. Autonomous maintenance routine that finds imports crossing a stated architectural boundary the wrong way — cross-package imports, dashboard features reaching into each other, backend-v2 transport adapters touching models, mobile routes bypassing screens — and fixes each violation by moving code or inverting the dependency, shipping via /ship.
When should I use Routine Abstraction Police?
Routine Abstraction Police fits situations like: explicitly invokes /routine-abstraction-police; asks to fix layering violations; is this import points the wrong way across a stated boundary.
How do I install Routine Abstraction Police in Claude Code?
Run `npx skills add bex-co/beancount-io --skill routine-abstraction-police -a claude-code`. Or copy the skill folder (.agents/skills/routine-abstraction-police in bex-co/beancount-io) into .claude/skills/routine-abstraction-police in your project. Claude Code loads it when a task matches its description.
How do I install Routine Abstraction Police in Codex?
Run `npx skills add bex-co/beancount-io --skill routine-abstraction-police -a codex`. Or copy the skill folder (.agents/skills/routine-abstraction-police in bex-co/beancount-io) into .agents/skills/routine-abstraction-police in your project. Codex loads it when a task matches its description.
Can I use Routine Abstraction Police 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-police -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-police, .gemini/skills/routine-abstraction-police, .github/skills/routine-abstraction-police and .opencode/skills/routine-abstraction-police in your project.
What does Routine Abstraction Police need to run?
SKILL.md names no scripts, command-line tools or credentials: Routine Abstraction Police is instructions for the agent only.
Does Routine Abstraction Police 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 Police 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 Police use?
Routine Abstraction Police 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 Police use?
About 1k tokens (SKILL.md is roughly 4.1k 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 Police?
Skills that share tags, products or a category with Routine Abstraction Police: Project Creator (aiskillstore/marketplace, 433 stars), Docs Gardening (mhmzdev/the-holy-quran-app, 888 stars), Improve Idea Critique (assafkip/kipi-system, 112 stars) and Mine History (ZoneMinder/zmNinjaNg, 112 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Routine Abstraction Police?
bex-co (a GitHub organization) maintains it in bex-co/beancount-io, which has 296 GitHub stars. The repository holds 27 skills in this directory. The repository was last updated on October 10, 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.