taniwha-leaf-implementation

taniwha-leaf-implementation is an agent for Claude Code from taniwhaai/arai. It costs 94 tokens per session (330 once invoked), scanned A, original, Apache-2.0.

A coding subagent that implements one Taniwha module from its contract manifest. Taniwha is a system that breaks a build into isolated modules with explicit requirements.

In plain words
What is it for?
Use it to write one module's source files and implementation notes from a manifest supplied by the Taniwha dispatcher.
Why use it?
It keeps implementation within the stated scope and project conventions, and reports unclear or contradictory requirements instead of guessing.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; reads .claude/ paths; mentions subagents.

Good fit Use it to write one module's source files and implementation notes from…

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/taniwhaai/arai/taniwha-leaf-implementation
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.

Clone the repo
git clone --depth 1 https://github.com/taniwhaai/arai

Made for: Claude Code.

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 taniwha-leaf-implementation

README.md
[![agentmods](https://agentmods.dev/badge/agents/taniwhaai/arai/taniwha-leaf-implementation.svg)](https://agentmods.dev/agents/taniwhaai/arai/taniwha-leaf-implementation)
Your own site
<a href="https://agentmods.dev/agents/taniwhaai/arai/taniwha-leaf-implementation"><img src="https://agentmods.dev/badge/agents/taniwhaai/arai/taniwha-leaf-implementation.svg" alt="Measured on agentmods" height="20"></a>
Per session 94 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 330 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00094 $0.00330
Opus 5 $0.00047 $0.00165
Sonnet 5 $0.00019 $0.00066
Haiku 4.5 $0.00009 $0.00033

Measured 7d ago against content hash 1df77b814ea9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

taniwha-leaf-implementation 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 7d 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/agents/taniwha-leaf-implementation.md · 17 lines

What it actually says

You are a Taniwha leaf-implementation subagent.

Your skill instructions are in .claude/skills/leaf-implementation/SKILL.md. Read it before writing any code. The discipline it describes — refusing to expand scope, surfacing ambiguity as re-raises rather than guessing, writing in the project context's language and conventions, putting source code at the repo root rather than inside .taniwha/ — is what makes the whole compartmentalised build work.

You have been given exactly three things as inputs: a manifest, the shared vocabulary, and the project context. Implement what your manifest specifies, in the language the project context names — nothing more, nothing less.

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 your manifest is under-specified, internally inconsistent, admits multiple materially different implementations, or cannot be satisfied within the current project context, emit a re-raise. Do not guess.

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. 7d ago First seen · 17 lines · 94 tokens per session scan A 1df77b814ea9

Subscribe to this mod's changes

taniwha-leaf-implementation is an agent published in the GitHub repository taniwhaai/arai (7 stars, last pushed 24d ago), licensed Apache-2.0. It adds 94 tokens to every session and 330 once invoked, about $0.0005 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.