New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Backend Conventions

by Inebrio in Inebrio/Routerly

Rules for service, CLI, shared types and infrastructure code in this repository.

AGPL-3.0Auto-check passed

Install Backend Conventions

skills CLI
$ npx skills add Inebrio/Routerly --skill backend-conventions -a claude-code

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

GitHub CLI
$ gh skill install Inebrio/Routerly backend-conventions --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/Inebrio/Routerly.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/backend-conventions .claude/skills/backend-conventions && 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
backend-conventions
GitHub stars
101
Token cost
~786 tokens
SKILL.md length
465 words
Files
1
Skills in repo
17
Repo updated
First seen
Licence
AGPL-3.0

At a glance

Rules for service, CLI, shared types and infrastructure code in this repository.

  • Implementing anything behind the interface
  • SKILL.md covers Everywhere, Service, CLI and Scripts against live external…, plus 1 more section
  • Calls bash, gh and npm

What it does

Backend Conventions is an agent skill from Inebrio/Routerly. Rules for service, CLI, shared types and infrastructure code in this repository. Use when implementing anything behind the interface.

Its SKILL.md is about 790 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: Self-hosted LLM gateway that routes requests across AI providers (OpenAI, Anthropic, Gemini, Mistral, Ollama) using intelligent multi-policy scoring — including an LLM-native… The licence is AGPL-3.0.

When your agent uses it

  • Implementing anything behind the interface

Example prompts

  • “Use the backend-conventions skill to rule for service, CLI, shared types and infrastructure code in this repository”
  • “/backend-conventions”

Requirements

  • Node.js

What it can do on your machine

Read from SKILL.md and the folder at commit bcf58f1. 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

    Shell commands in SKILL.md call:

    • bash
    • gh
    • npm
    • git

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

  • Network

    No URLs in SKILL.md. Its commands use gh, npm and git, which can reach the network depending on how they are called.

    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

Backend Conventions loads about 786 tokens when it runs. Until then it costs about 38 tokens; SKILL.md has 465 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~38
When it runs · the whole SKILL.md, loaded when a task matches
~786

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 Inebrio/Routerly at commit bcf58f1, republished under its AGPL-3.0 licence (© Inebrio). 465 words, ~786 tokens.

Download SKILL.mdSave it as .claude/skills/backend-conventions/SKILL.md (or your agent's skills folder).
name
backend-conventions
description
Rules for service, CLI, shared types and infrastructure code in this repository. Use when implementing anything behind the interface.

Backend conventions

Binding detail lives in .Codex/rules/service.md and .Codex/rules/cli.md. Read the one covering what you touch. This is the short list you must not get wrong.

Everywhere

  • TypeScript ESM. Relative imports carry the .js extension, Node builtins carry the node: prefix.
  • Types come from the shared package. Never redeclare one locally.
  • Tests are *.test.ts beside the source they cover.

Service

  • Config writes go through writeConfig(). Never fs.writeFile on config.
  • A new management endpoint needs all four: Zod body validation, permission check, the route itself, and a fastify.inject() test proving allowed → 200 and forbidden → 403.
  • Bearer tokens are stored as SHA-256. Passwords are bcrypt, 12 rounds. Never log either, never return either.
  • Runtime state is JSON under ROUTERLY_HOME. There is no database.

CLI

  • HTTP goes through api.ts. Never fetch directly.
  • The service URL comes from the active account's serverUrl in store.ts. Never hardcode it.
  • Refresh the token silently before every call when expiresAt has passed.
  • Errors to stderr with exit code 1. Success to stdout with exit code 0.
  • --json where piping makes sense, and its output must always parse.
  • Register new commands in index.ts, or they do not exist.

Scripts against live external services

A script that creates a disposable GitHub repo, hits a real API, or runs a live release tool is expensive to redo: minutes of wall-clock, a fresh external resource, and a full agent turn budget, every time it fails on something you could have caught for free.

  • Sanity-check before the first live run. bash -n the script. Re-read it for shell portability this machine actually has — grep -P/-Pq silently misbehaves here because this is BSD grep, not GNU; prefer gh api --jq or POSIX-safe patterns. Check whether an early step (npm install, a build) leaves the tree dirty in a way a later git checkout in the same script will collide with. A live run that fails on a bug like this bought no evidence and cost a real repo.
  • Wait for it with one blocking call, not a loop of turns. For a script that logs many lines over minutes, do not stream it with Monitor line-by-line and then fill turns with idle placeholder commands between notifications — each notification and each placeholder is a paid turn, and a chatty script can burn the whole budget before you ever reach the step that writes your report. Prefer a single foreground Bash call with a timeout that covers the expected wall-clock, or run_in_background plus one wait for the process to actually exit. Read the resulting log file once it is done, rather than watching it happen.
Show full SKILL.md (36 more words)Show less

Before you report done

  • The package builds and its tests pass.
  • The command you claim works has been run, and you have its output.
  • Anything you could not verify is stated as unverified, not as done.

© Inebrio, AGPL-3.0. 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/backend-conventions of Inebrio/Routerly.

Open the folder on GitHubat commit bcf58f1

Compare with similar skills

Backend Conventions 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.

Backend Conventions compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Backend Conventions this skillInebrio/Routerly101—~786Automated safety check: PassAGPL-3.0
Rust Path Typesopeninterpreter/openinterpreter69k2 repos~605Automated safety check: PassApache-2.0
Python Type Safetywshobson/agents40k—~1.4kAutomated safety check: PassMIT
Pyrefly Type Coveragepytorch/pytorch104k—~3kAutomated safety check: PassCustom licence
Ecc Conventionsaffaan-m/ECC276k—~2.8kAutomated safety check: PassMIT
Typescript Advanced Typesrolling-scopes/rsschool-app10k25 repos~4.2kAutomated safety check: PassMPL-2.0

Similar skills

  • Rust Path Types

    openinterpreter/openinterpreter

    Rules for choosing Rust types for filesystem paths in new Codex code, covering protocol types, internal use and model tool arguments.

    69k GitHub starsUsed in 2 repos~605 tokens
    DevelopmentAuto-check passed

  • Python Type Safety

    wshobson/agents

    Python type safety with type hints, generics, protocols, and strict type checking.

    40k GitHub stars~1.4k tokensUpdated 4 days ago
    DevelopmentAuto-check passed

  • Pyrefly Type Coverage

    pytorch/pytorch

    Migrate a file to use stricter Pyrefly type checking with annotations required for all functions, classes, and attributes.

    104k GitHub stars~3k tokensUpdated today
    DevelopmentAuto-check passed

  • Ecc Conventions

    affaan-m/ECC

    Development conventions and patterns for ECC. An agent skill from affaan-m/ECC.

    276k GitHub stars~2.8k tokensUpdated 4 days ago
    DevelopmentAuto-check passed

  • Typescript Advanced Types

    rolling-scopes/rsschool-app

    Master TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility types for building type-safe applications.

    10k GitHub starsUsed in 25 repos~4.2k tokens
    DevelopmentAuto-check passed

  • API Types

    supabase/supabase

    Official

    Maintain Supabase API types. An agent skill from supabase/supabase.

    111k GitHub stars~557 tokensUpdated today
    Backend & APIsAuto-check passed

More from Inebrio/Routerly

All 17 skills in this repo

  • Docs Conventions

    Inebrio/Routerly

    Where documentation lives in this repository, how a page is structured, and what a change owes the docs.

    101 GitHub stars~624 tokensUpdated today
    Auto-check passed

  • Feature Lifecycle

    Inebrio/Routerly

    Run a Tier 1 or Tier 2 feature end to end — feature level, story level, parallelism, integration, and retrospective.

    101 GitHub stars~3k tokensUpdated today
    Auto-check passed

  • Story Lifecycle

    Inebrio/Routerly

    Run one user story end to end in its own worktree, from claim to merge.

    101 GitHub stars~905 tokensUpdated today
    Auto-check passed

  • Test Conventions

    Inebrio/Routerly

    Where tests live in this repository, how to run them, and what a story owes in coverage.

    101 GitHub stars~467 tokensUpdated today
    Auto-check passed

  • Validation Protocol

    Inebrio/Routerly

    How to validate a story against its criteria and write the report, including what counts as evidence and what counts as blocking.

    101 GitHub stars~628 tokensUpdated today
    Auto-check passed

  • Analysis Format

    Inebrio/Routerly

    Shape of a feature analysis document (00-analysis.md). An agent skill from Inebrio/Routerly.

    101 GitHub stars~472 tokensUpdated today
    Auto-check passed

Questions about Backend Conventions

What does Backend Conventions do?

Rules for service, CLI, shared types and infrastructure code in this repository. Backend Conventions is an agent skill from Inebrio/Routerly. Rules for service, CLI, shared types and infrastructure code in this repository.

When should I use Backend Conventions?

Backend Conventions fits situations like: implementing anything behind the interface.

How do I install Backend Conventions in Claude Code?

Run `npx skills add Inebrio/Routerly --skill backend-conventions -a claude-code`. Or copy the skill folder (.agents/skills/backend-conventions in Inebrio/Routerly) into .claude/skills/backend-conventions in your project. Claude Code loads it when a task matches its description.

How do I install Backend Conventions in Codex?

Run `npx skills add Inebrio/Routerly --skill backend-conventions -a codex`. Or copy the skill folder (.agents/skills/backend-conventions in Inebrio/Routerly) into .agents/skills/backend-conventions in your project. Codex loads it when a task matches its description.

Can I use Backend Conventions 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 Inebrio/Routerly --skill backend-conventions -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/backend-conventions, .gemini/skills/backend-conventions, .github/skills/backend-conventions and .opencode/skills/backend-conventions in your project.

What does Backend Conventions need to run?

Going by SKILL.md and its folder, Backend Conventions needs the command-line tools its instructions call (bash, gh, npm and git). Our summary lists: Node.js.

Does Backend Conventions access the network?

SKILL.md contains no URLs. Its commands use gh, npm and git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Backend Conventions 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 Backend Conventions use?

Backend Conventions is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Backend Conventions use?

About 786 tokens (SKILL.md is roughly 3.1k 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 Backend Conventions?

Skills that share tags, products or a category with Backend Conventions: Rust Path Types (openinterpreter/openinterpreter, 69k stars), Python Type Safety (wshobson/agents, 40k stars), Pyrefly Type Coverage (pytorch/pytorch, 104k stars) and Ecc Conventions (affaan-m/ECC, 276k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Backend Conventions?

Inebrio (a GitHub organization) maintains it in Inebrio/Routerly, which has 101 GitHub stars. The repository holds 17 skills in this directory. The repository was last updated on October 8, 2026.

Source: Inebrio/Routerly on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.