Agent skill

Interface Contracts

by Inebrio in Inebrio/Routerly

How to freeze and arbitrate the interface between parallel implementers.

AGPL-3.0Auto-check passedLegal & Compliance

Install Interface Contracts

skills CLI
$ npx skills add Inebrio/Routerly --skill interface-contracts -a claude-code

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

GitHub CLI
$ gh skill install Inebrio/Routerly interface-contracts --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/interface-contracts .claude/skills/interface-contracts && 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
interface-contracts
GitHub stars
100
Token cost
~572 tokens
SKILL.md length
353 words
Files
1
Skills in repo
17
Repo updated
First seen
Licence
AGPL-3.0

At a glance

How to freeze and arbitrate the interface between parallel implementers.

  • Works in 3 steps: The frozen contract wins. Neither side… → If the contract is genuinely wrong,… → Prefer the change that keeps the…
  • Coordinating backend and frontend work on the same story
  • SKILL.md covers What a contact point is, Freezing one, Sequencing and Arbitration, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Interface Contracts is an agent skill from Inebrio/Routerly. How to freeze and arbitrate the interface between parallel implementers. Use when coordinating backend and frontend work on the same story.

Its SKILL.md is about 570 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 Legal & Compliance. 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

  • Coordinating backend and frontend work on the same story

Example prompts

  • “/interface-contracts”

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. The frozen contract wins. Neither side changes it unilaterally.
  2. If the contract is genuinely wrong, decide the new shape, write it down,
  3. Prefer the change that keeps the consumer honest: an optional field is

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

    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

Interface Contracts loads about 572 tokens when it runs. Until then it costs about 40 tokens; SKILL.md has 353 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~40
When it runs · the whole SKILL.md, loaded when a task matches
~572

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). 353 words, ~572 tokens.

Download SKILL.mdSave it as .claude/skills/interface-contracts/SKILL.md (or your agent's skills folder).
name
interface-contracts
description
How to freeze and arbitrate the interface between parallel implementers. Use when coordinating backend and frontend work on the same story.

Interface contracts

Two implementers working at once fail in exactly one way: each assumes a different shape at the line where their work meets. Freezing that line before either starts is the whole job.

What a contact point is

Anywhere data crosses between the people working in parallel: an HTTP endpoint, a shared type, a config key, a file format, an event, an exit code, an error string a caller matches on.

Freezing one

A contract is frozen when both sides could implement against it without asking a question. That means, for an endpoint:

  • method and path, exactly as it will ship
  • request shape, with field names and types
  • response shape for success, with field names and types
  • status codes, including the failure ones
  • error body shape
  • permission or auth required
  • pagination, ordering, and what an empty result looks like

Vague is worse than wrong. returns the list of items is not a contract: one side ships {items: []}, the other reads [], and nobody finds out until integration.

Shared types are the cheapest contract in a typed monorepo: define the type once in the shared package, have both sides import it, and the compiler enforces what a document cannot.

Show full SKILL.md (155 more words)Show less

Sequencing

Give the type or interface definition to one side as its first task and let the other consume it. When both must start now, write the contract into the blueprint and hold both to it verbatim.

Arbitration

When the two sides disagree mid-flight:

  1. The frozen contract wins. Neither side changes it unilaterally.
  2. If the contract is genuinely wrong, decide the new shape, write it down, and tell both sides in the same message. Never let two versions coexist.
  3. Prefer the change that keeps the consumer honest: an optional field is cheaper than a renamed one, a new endpoint is cheaper than a repurposed one.

What is not yours to decide

  • A gap in the plan goes back to whoever wrote the plan.
  • A conflict with another story in flight goes up to whoever owns the dependency graph.
  • A change to what the story asks for is not negotiable at this level.

© 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/interface-contracts of Inebrio/Routerly.

Open the folder on GitHubat commit bcf58f1

Compare with similar skills

Interface Contracts 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.

Interface Contracts compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Interface Contracts this skillInebrio/Routerly100—~572Automated safety check: PassAGPL-3.0
Paper to Chinese Patent DrafterYuan1z0825/nature-skills46k1 repos~1.1kAutomated safety check: PassApache-2.0
C15tc15t/c15t1.9k1 repos~1.6kAutomated safety check: PassApache-2.0
Contract Reviewevolsb/claude-legal-skill4621 repos~3.6kAutomated safety check: PassMIT
Legal Clinic Client Intakeanthropics/claude-for-legal9.6k3 repos~3.2kAutomated safety check: PassApache-2.0
Paper To Cn Patentsnipp-zha/Paper-to-patent-Skill1051 repos~959Automated safety check: PassNone

Similar skills

  • Paper to Chinese Patent Drafter

    Yuan1z0825/nature-skills

    Drafts Chinese invention patent applications and technical disclosures from research papers or inventor materials, tying each claim feature to source evidence.

    46k GitHub starsUsed in 1 repo~1.1k tokens
    Legal & ComplianceAuto-check passed
  • C15t

    c15t/c15t

    Work with c15t consent management docs, APIs, and integrations for Next.js, React, and JavaScript.

    1.9k GitHub starsUsed in 1 repo~1.6k tokens
    Legal & ComplianceAuto-check passed
  • Contract Review

    evolsb/claude-legal-skill

    Review legal contracts, NDAs, employment agreements, SaaS terms, and M&A documents.

    462 GitHub starsUsed in 1 repo~3.6k tokens
    Legal & ComplianceAuto-check passed
  • Legal Clinic Client Intake

    anthropics/claude-for-legal

    Official

    Structures a legal clinic client intake interview and produces a case summary with cross-area issue spotting, conflict flags and triage classification.

    9.6k GitHub starsUsed in 3 repos~3.2k tokens
    Legal & ComplianceAuto-check passed
  • Paper To Cn Patent

    snipp-zha/Paper-to-patent-Skill

    Convert scientific papers, theses, technical reports, source code, figures, or research manuscripts into evidence-grounded Chinese invention patent drafts.

    105 GitHub starsUsed in 1 repo~959 tokens
    Legal & ComplianceAuto-check passed
  • Employment Contract Templates

    ynulihao/AgentSkillOS

    Create employment contracts, offer letters, and HR policy documents following legal best practices.

    617 GitHub starsUsed in 12 repos~4.1k tokens
    Legal & ComplianceAuto-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.

    100 GitHub stars~624 tokensUpdated yesterday
    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.

    100 GitHub stars~3k tokensUpdated yesterday
    Auto-check passed
  • Story Lifecycle

    Inebrio/Routerly

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

    100 GitHub stars~905 tokensUpdated yesterday
    Auto-check passed
  • Test Conventions

    Inebrio/Routerly

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

    100 GitHub stars~467 tokensUpdated yesterday
    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.

    100 GitHub stars~628 tokensUpdated yesterday
    Auto-check passed
  • Analysis Format

    Inebrio/Routerly

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

    100 GitHub stars~472 tokensUpdated yesterday
    Auto-check passed

Questions about Interface Contracts

What does Interface Contracts do?

How to freeze and arbitrate the interface between parallel implementers. Interface Contracts is an agent skill from Inebrio/Routerly. How to freeze and arbitrate the interface between parallel implementers.

When should I use Interface Contracts?

Interface Contracts fits situations like: coordinating backend and frontend work on the same story.

How do I install Interface Contracts in Claude Code?

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

How do I install Interface Contracts in Codex?

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

Can I use Interface Contracts 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 interface-contracts -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/interface-contracts, .gemini/skills/interface-contracts, .github/skills/interface-contracts and .opencode/skills/interface-contracts in your project.

What does Interface Contracts need to run?

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

Does Interface Contracts 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 Interface Contracts 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 Interface Contracts use?

Interface Contracts 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 Interface Contracts use?

About 572 tokens (SKILL.md is roughly 2.3k 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 Interface Contracts?

Skills that share tags, products or a category with Interface Contracts: Paper to Chinese Patent Drafter (Yuan1z0825/nature-skills, 46k stars), C15t (c15t/c15t, 1.9k stars), Contract Review (evolsb/claude-legal-skill, 462 stars) and Legal Clinic Client Intake (anthropics/claude-for-legal, 9.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Interface Contracts?

Inebrio (a GitHub organization) maintains it in Inebrio/Routerly, which has 100 GitHub stars. The repository holds 17 skills in this directory. The repository was last updated on October 6, 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.