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 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/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/skills/taniwhaai/arai/leaf-implementation"><img src="https://agentmods.dev/badge/skills/taniwhaai/arai/leaf-implementation.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 | $0.00133 | $0.03477 |
| Opus 5.5 | $0.00053 | $0.01391 |
| Sonnet 5.5 | $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 1mo 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.
- 1mo 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 7d ago), licensed Apache-2.0. It adds 133 tokens to every session and 3,477 once invoked, about $0.0005 per session on Opus 5.5. 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
umbra-trust-review
Verify AI-generated code before shipping. Run Umbra's Trust Score scan before committing or finishing any coding task, treat findings as blocking issues, and re-scan until clean. Use when finishing a task, before a commit, or when reviewing code written by an agent.
michel-run-local-dev-stack
The canonical recipe for starting, checking, and stopping the Packmind local dev stack with Docker Compose — the single source of truth other skills and the Michel agent defer to. Covers bringing the full stack (PostgreSQL, Redis, NestJS API, React/Vite frontend on :4200, MCP server, nginx) up in the background, the…
hexagonal-architecture
Describes the hexagonal architecture (ports and adapters) used across the Packmind monorepo. This skill should be used when creating new domain packages, use cases, services, repositories, domain error classes, or any architectural component to follow established patterns, including how a failure raised in a use case…
michel-create-packmind-dataset
Seed a local Packmind instance with a realistic dataset — one organization populated with standards, commands, and skills — so an autonomous agent can exercise its own changes against lifelike data instead of an empty app. Use this whenever you need populated Packmind data to verify a change end-to-end: reproducing a…
blotato
Blotato social-media publishing and scheduling platform — REST API + MCP server. Publish and schedule posts across X/Twitter, TikTok, Instagram, LinkedIn, YouTube, Facebook, Threads, Pinterest, and more from a single integration. Use this skill whenever the user wants to schedule, publish, queue, or batch-post content…
ralphctl-test-driven-development
Execute-phase skill — drive changes with the red-green-refactor loop; write the failing test before the code that makes it pass; for bug fixes, this is the reproduction test itself. Use for any logic change, bug fix, or behavioural modification; for the full root-cause triage pipeline around an unexpected failure, see…