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/leaf-implementationnpx skills add taniwhaai/arai --skill leaf-implementationgit 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/leaf-implementation)<a href="https://agentmods.dev/skills/taniwhaai/arai/leaf-implementation"><img src="https://agentmods.dev/badge/skills/taniwhaai/arai/leaf-implementation.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 | $0.00133 | $0.03477 |
| Opus 5 | $0.00067 | $0.01739 |
| Sonnet 5 | $0.00027 | $0.00695 |
| Haiku 4.5 | $0.00013 | $0.00348 |
Grade A, and why
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 4d 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 — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Leaf Implementation
Implement one module from one manifest. Do not exceed the contract. Do not infer the system's purpose. Do not reach beyond the manifest and shared vocabulary you were given.
Why this skill exists
Compartmentalisation is the property that makes large agent-built codebases tractable. When an implementing agent sees only its own module's contract — not the rest of the system, not the design doc, not adjacent modules — three things happen:
- The agent cannot invent coupling that does not exist. It has nothing to couple to.
- The agent cannot drift toward the system's overall purpose, which would otherwise bias every micro-decision.
- Any incompleteness in the contract surfaces immediately, as a re-raise, rather than being smoothed over with plausible-looking code.
This makes context lean, makes contracts honest, and makes the resulting code locally verifiable. The framework around this skill is what physically enforces the context boundary; this skill's job is to make the agent inside that boundary behave correctly.
If this skill is being used outside the framework (no enforced isolation), behave as if isolation were enforced anyway. Treat anything outside the manifest, shared vocabulary, and project context as if it did not exist. The discipline is what produces the value, not the wall.
What you have
You have been given exactly three things:
- A manifest for the module you are implementing. This contains the contract: inputs, outputs, side effects, error semantics, behavioural guarantees, dependencies, referenced data shapes, acceptance criteria. The manifest is language-neutral by design — it does not tell you which language to write in.
- A shared vocabulary file containing the data shapes and external systems your manifest refers to. Also language-neutral.
- A project context file (
project_context.yaml). This is where language, toolchain, repository style, directory layout, test framework, and code conventions are recorded. The user authored this; it is authoritative for every choice the manifest deliberately leaves to you.
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.
- 4d ago First seen · 152 lines · 133 tokens per session scan A 5d76b1ef1acf
leaf-implementation is a skill published in the GitHub repository taniwhaai/arai (7 stars, last pushed 22d ago), licensed Apache-2.0. It adds 133 tokens to every session and 3,477 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.
bug-fix
Guided end-to-end bug-fix workflow for Plan Forge tempering bugs — load → pre-fix review → write failing test → fix → validate → post-fix sweep → close. Composes /code-review, /clean-code-review, /forge-quench, and /test-sweep around the forgebug tool surface so a fix never closes without a regression check.
infra-deploy
Validate, what-if/plan, deploy, and verify Azure infrastructure using Bicep, Terraform, or azd. Use when deploying a completed infrastructure phase to an environment.