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 Kevin-Liu-01/Agent-Machines --skill generate-interfacegit clone --depth 1 https://github.com/Kevin-Liu-01/Agent-MachinesWrote 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/kevin-liu-01/agent-machines/generate-interface)<a href="https://agentmods.dev/skills/kevin-liu-01/agent-machines/generate-interface"><img src="https://agentmods.dev/badge/skills/kevin-liu-01/agent-machines/generate-interface/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/kevin-liu-01/agent-machines/generate-interface"><img src="https://agentmods.dev/badge/skills/kevin-liu-01/agent-machines/generate-interface.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00075 | $0.02481 |
| Opus 5 | $0.00037 | $0.01241 |
| Sonnet 5 | $0.00015 | $0.00496 |
| Haiku 4.5 | $0.00007 | $0.00248 |
Grade A, and why
generate-interface 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.
How it starts
The opening of the file, as written. The whole thing — 427 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate Interface
Design interfaces the way durable systems do:
- one contract per real responsibility
- one authority per state field or operation
- explicit transports, not accidental ones
- README-first subsystem manuals
- docstrings that explain what part of the interface a module implements
- code that follows the contract instead of inventing side channels
The target is an interface that feels old in the best way:
- obvious
- narrow
- composable
- boring
- hard to misunderstand
Think Unix and Linux, not app-framework churn.
This skill is for interface hardening, not generic architecture prose.
Core rule
Reduce a subsystem until a reader can answer these questions quickly:
- What are the primary interfaces?
- Who calls each one?
- Who owns each write path?
- What is authoritative?
- What is compatibility-only or debug-only?
- What is explicitly out of scope?
If the answer requires reading five modules and guessing, the interface is not done.
If the behavior of the subsystem is mostly encoded in ad hoc helper functions and not in a small set of named interfaces, the design is not done.
Output shape
Prefer this hierarchy:
- subsystem
README.md - local module docstrings
- code
Do not create a new top-level taxonomy document unless the user explicitly wants one.
The default move is to consolidate interface definitions into the correct subsystem README.md files.
The user should be able to understand the subsystem by reading:
README.md- module docstrings
- code
and nothing else.
When to use
Use this skill when the user asks for things like:
- “make the interfaces solid”
- “reduce this architecture to a few APIs”
- “clean up the controlplane/runtime boundary”
- “document the subsystem so it reads cleanly”
- “collapse ad hoc functions into real interfaces”
- “make the README and docstrings the source of truth”
- “make this feel like a real subsystem manual”
- “make the API surface obvious”
Typical triggers:
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 · 427 lines · 75 tokens per session scan A 3fa54ad744cd
generate-interface is a skill published in the GitHub repository Kevin-Liu-01/Agent-Machines (26 stars, last pushed 8d ago), licensed MIT. It adds 75 tokens to every session and 2,481 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
add-backend
Guide for adding a backend (Rust or Python) to the agent-sec-core security middleware. Use when creating new backends, integrating Rust or Python code into the security middleware, or extending with new backend actions.
jentic
Use this skill whenever the user wants to work with a third-party or external API/tool through the Jentic platform — e.g. asks to "find the vessel-tracking API and add it", "get rows from this Google Sheet", connect Slack, import/search/discover an API, integrate or automate a SaaS, pull data from a service, or call…
unicli-explorer
Create new Uni-CLI adapters by exploring websites and APIs. Use when adding support for a new site, desktop app, or service that unicli doesn't cover yet.
contribute-spec-fix
Fix a broken OpenAPI spec in jentic-public-apis with an OpenAPI Overlay, validate it (spectral lint + idempotency check), and contribute it back via a PR to the community catalog. Falls back to applying the same overlay to the local Jentic registry if the user can't wait for maintainer approval, and closes the loop by…
inkbox-agent-self-signup
Use when guiding or implementing the Inkbox agent self-signup flow, including verification, resend-verification, signup restrictions, and optional signup fields like agent handles or mailbox local parts.
import-new-api
Import an API that is not yet in jentic-public-apis end to end — generate or find an OpenAPI spec from the vendor's docs, optionally import it into the local Jentic registry so the agent is unblocked immediately, publish it to the user's reusable public import-openapi-specs repo, and open the import issue that drives…