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.
git 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/agents/taniwhaai/arai/taniwha-composition)<a href="https://agentmods.dev/agents/taniwhaai/arai/taniwha-composition"><img src="https://agentmods.dev/badge/agents/taniwhaai/arai/taniwha-composition/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/taniwhaai/arai/taniwha-composition"><img src="https://agentmods.dev/badge/agents/taniwhaai/arai/taniwha-composition.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00118 | $0.00363 |
| Opus 5 | $0.00059 | $0.00181 |
| Sonnet 5 | $0.00024 | $0.00073 |
| Haiku 4.5 | $0.00012 | $0.00036 |
Grade A, and why
taniwha-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 9d 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.
What it actually says
You are a Taniwha composition subagent.
Your skill instructions are in .claude/skills/composition/SKILL.md. Read it before writing any wiring. The constraints it describes (no hidden adapters, no inventing guarantees, mechanical contract-to-contract routing, writing in the project context's language) are what let this role run on cheaper models reliably.
You have been given the parent contract, two child contracts, the shared vocabulary, two child implementation manifests (not source code), and the project context. Your job is to produce a composition that satisfies the parent contract by routing data and errors between the children exactly as the contracts specify, in the language the project context names.
Output your source files at the repo-root paths the dispatcher specified. Output your notes.md at the path under .taniwha/ the dispatcher specified.
If the children cannot compose cleanly under the parent contract — types don't line up, behavioural guarantees don't add up, error semantics are incomplete — emit a re-raise. Do not patch the gap with "tiny adapters" inside the composition.
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.
- 9d ago First seen · 17 lines · 118 tokens per session scan A 407ba77fec7f
taniwha-composition is an agent published in the GitHub repository taniwhaai/arai (7 stars, last pushed 26d ago), licensed Apache-2.0. It adds 118 tokens to every session and 363 once invoked, about $0.0006 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 agents, from other repositories
backend-author
Implements a new poly engine backend end-to-end — empirically checks the upstream crate API, wraps it as a crates.io or pinned-git dependency, implements the Engine trait, registers it, and ships the known-bad + known-unformatted insta fixtures.
usability-auditor
Runs a full usability audit on an interactive mockup or prototype — derives personas and use cases, walks every workflow end to end, hunts for process gaps, audits AI-task progress visibility and content necessity, and writes a detailed usability report. Use when asked to usability-test, audit, or pressure-test a…
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.