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.
npx agentmods add skills/taniwhaai/arai/compositionnpx skills add taniwhaai/arai --skill compositiongit clone --depth 1 https://github.com/taniwhaai/araiWrote 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.
[](https://agentmods.dev/skills/taniwhaai/arai/composition)<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>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.
| Model | Per session | Once 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 |
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.
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:
- The parent contract — the manifest the composition must satisfy.
- Child A's contract — the manifest of the first child module.
- Child B's contract — the manifest of the second child module.
- The shared vocabulary — every data shape and external system the contracts refer to.
- 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 iscurrentand 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. - The project context — language, repo style, directory layout, code conventions. The composition must be written in this language using these conventions.
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.
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.
- 5d ago First seen · 160 lines · 136 tokens per session scan A ee693f6e6542
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.
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…
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…
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.
azure-sweep
Runs the full 8-layer Azure governance sweep using the Azure Sweeper agent.
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.
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.