composition

composition is a skill for Claude Code, Codex from taniwhaai/arai. It costs 136 tokens per session (3,489 once invoked), scanned A, original, Apache-2.0.

A guide for connecting two completed modules so they satisfy a parent contract. A contract describes the inputs, outputs, behaviour, and errors that a module must provide.

In plain words
What is it for?
Use it when two implemented modules and their manifests must be wired together under a shared parent contract.
Why use it?
It keeps integration focused on routing existing behaviour and makes genuine mismatches explicit instead of hiding them with new code.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/taniwhaai/arai/composition
Any agent
npx skills add taniwhaai/arai --skill composition
Clone the repo
git clone --depth 1 https://github.com/taniwhaai/arai

Made for: Claude Code, Codex.

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 composition

README.md
[![agentmods](https://agentmods.dev/badge/skills/taniwhaai/arai/composition.svg)](https://agentmods.dev/skills/taniwhaai/arai/composition)
Your own site
<a href="https://agentmods.dev/skills/taniwhaai/arai/composition"><img src="https://agentmods.dev/badge/skills/taniwhaai/arai/composition.svg" alt="Measured on agentmods" height="20"></a>
Per session 136 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,489 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00136 $0.03489
Opus 5 $0.00068 $0.01744
Sonnet 5 $0.00027 $0.00698
Haiku 4.5 $0.00014 $0.00349

Measured 5d ago against content hash ee693f6e6542, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

composition 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 5d 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.

.claude/skills/composition/SKILL.md · 160 lines

How it starts

The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Composition

Wire two child modules together to satisfy a parent contract. You are not implementing new behaviour. You are routing data from the parent's inputs through the children's contracts to the parent's outputs, exactly as the parent contract specifies.

Why this skill exists

In a compartmentalised system, every node in the build tree either implements a leaf module (one contract, no children) or composes two child contracts under a parent contract. This skill handles the second case. It is structurally simpler than leaf implementation — the children already exist and are trusted; the parent contract already exists and is the target. The composition's job is only to wire one to the other faithfully.

Because the work is constrained, this skill is the right place to use cheaper, smaller models. The rules below are deliberately tight to make that practical: most decisions are forced by the contracts involved, so there is little room for creative drift.

When a genuine mismatch exists — child contracts that cannot be reconciled, a parent contract that cannot be satisfied by the children chosen for it — this skill does not try to solve the mismatch. It surfaces a precise re-raise back up the tree, where an agent with the authority and context can resolve it.

What you have

You have been given exactly six things:

  1. The parent contract — the manifest the composition must satisfy.
  2. Child A's contract — the manifest of the first child module.
  3. Child B's contract — the manifest of the second child module.
  4. The shared vocabulary — every data shape and external system the contracts refer to.
  5. Child A's implementation manifest — the manifest under .taniwha/kupu/implementations/<A>/v<N>/manifest.yaml (or compositions/ if A is itself a composition). This tells you the source paths and confirms the implementation is current and verified. You do not get child A's source code as input. You can read the source paths from disk if and only if you genuinely need to (e.g. to discover an exported function name in a language where the contract didn't specify one) — and that need itself is a sign the contract may be incomplete.
  6. The project context — language, repo style, directory layout, code conventions. The composition must be written in this language using these conventions.

Read the full file on GitHub · 160 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 5d ago First seen · 160 lines · 136 tokens per session scan A ee693f6e6542

Subscribe to this mod's changes

composition is a skill published in the GitHub repository taniwhaai/arai (7 stars, last pushed 23d ago), licensed Apache-2.0. It adds 136 tokens to every session and 3,489 once invoked, about $0.0007 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 2026-08-31.

Related

Other skills, from other repositories

clean-code-review

Run a comprehensive Clean Code audit against the codebase — module size, function complexity, long parameter lists, TODO/FIXME markers, commented-out code, duplication (DRY), Boy Scout delta, dead exports, test smells, shell-parity (PS/Bash twins), dep boundaries (cross-package imports), frozen-arrays drift…

srnichols/plan-forge · 92 tokens

code-review

Plan-Forge-tuned comprehensive code review — runs public-surface diff, forge analysis, architecture / security / testing / patterns checks, plus Plan-Forge-specific gates (ACI compliance, dual-shell parity, branch model). Use before merging features or at the end of a phase. With --quorum, dispatches multi-model…

srnichols/plan-forge · 70 tokens

stakeholder-briefing

Generate a per-organisation stakeholder briefing for Plan Forge from the canonical template, optionally drafting the prospect-specific sections from a source directory of customer materials. Use when an internal champion needs to walk a colleague or VP through the decision to adopt Plan Forge.

srnichols/plan-forge · 55 tokens

azure-sweep

Runs the full 8-layer Azure governance sweep using the Azure Sweeper agent.

srnichols/plan-forge · 0 tokens

forge-quench

Systematically reduce .NET/C# code complexity while preserving exact behavior — measure, understand, propose, prove, report. Use after a feature is complete and tests pass, when code works but is harder to maintain than it should be.

srnichols/plan-forge · 51 tokens

ui-scaffold

Scaffold a new Blazor page with proper layering — service interface, page component (markup + code-behind split), DTO, validation, error handling, and bUnit test. Enforces architecture-principles + blazor-fluent-ui conventions. Use when adding any new UI surface to a Blazor Server app.

srnichols/plan-forge · 68 tokens