agentmods.dev

boundary-demo

boundary-demo is a skill for Codex from cubxxw/agent-kit. It costs 66 tokens per session (904 once invoked), scanned A, original, MIT.

A disposable prototype for answering one uncertain question about a system, integration, workflow, or user experience. It produces evidence for a decision rather than a production feature.

In plain words
What is it for?
Use it for small demos, sandboxes, integration tests with fake services, state-flow experiments, or comparisons of interface ideas.
Why use it?
It prevents teams from building a full solution before learning whether an important approach works.

Skill for Codex

Written for Codex: agents/openai.yaml present.

not rated 2repo 4d ago A scan 66 tokens original MIT

Good fit Use it for small demos, sandboxes, integration tests with fake services, state-flow experiments, or comparisons of interface ideas.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/cubxxw/agent-kit/boundary-demo
View source ↗ cubxxw/agent-kit
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.

Any agent
npx skills add cubxxw/agent-kit --skill boundary-demo
Clone the repo
git clone --depth 1 https://github.com/cubxxw/agent-kit

Made for: Codex.

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 boundary-demo

README.md
[![agentmods](https://agentmods.dev/badge/skills/cubxxw/agent-kit/boundary-demo/github.svg)](https://agentmods.dev/skills/cubxxw/agent-kit/boundary-demo)
Your own site
<a href="https://agentmods.dev/skills/cubxxw/agent-kit/boundary-demo"><img src="https://agentmods.dev/badge/skills/cubxxw/agent-kit/boundary-demo/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.

agentmods 80×15 button for boundary-demo

Your own site · 80×15
<a href="https://agentmods.dev/skills/cubxxw/agent-kit/boundary-demo"><img src="https://agentmods.dev/badge/skills/cubxxw/agent-kit/boundary-demo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 904 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 $0.00066 $0.00904
Opus 5.5 $0.00026 $0.00362
Sonnet 5.5 $0.00013 $0.00181
Haiku 4.5 $0.00007 $0.00090

Measured 1mo ago against content hash 656d767c49e5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

boundary-demo 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.

The scan reads SKILL.md. This mod also ships 11 executable files (assets/streamlit-boundary-demo/boundary_demo/__init__.py, assets/streamlit-boundary-demo/boundary_demo/adapters.py, assets/streamlit-boundary-demo/boundary_demo/cases.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/boundary-demo/SKILL.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Boundary Demo

Build the smallest probe that can change one decision. The deliverable is evidence, not a miniature product.

Start with one decision contract

Before implementation, write down:

  • one question with at least two plausible answers;
  • the evidence that would change the decision;
  • the smallest observable failure;
  • a timebox and stop rule;
  • what is explicitly out of scope.

If these cannot be stated, ask one concise question. Do not expand into a full product specification. Read references/choosing-and-scoping.md when the right probe or medium is unclear.

Choose exactly one mode

  • Boundary: contracts, ownership, external services, failures, retries, or side effects. Default integrations to deterministic fake or read-only adapters.
  • Logic: state machines, data shapes, policies, or transitions. Keep the runner independent of the UI.
  • Taste: interaction or information hierarchy is the uncertainty. Compare two or three materially different variants against the same cases; read references/taste-comparison.md.

Do not run all modes by default. Choose the medium after the mode:

  • Prefer Streamlit for Python, data, LLM, state, trace, and human-review probes.
  • Prefer a CLI when the question is pure state or business logic and a browser adds no evidence.
  • Use an existing Web surface when DOM, CSS, responsive behavior, browser events, or page context is itself under test.

Build an observable probe

Make input, relevant state before and after, trace, output, and failure visible. Seed at least one normal, one edge, and one failure case. Keep four evidence classes separate:

  1. observed fact;
  2. automated verdict;
  3. human choice;
  4. AI hypothesis.

An automated pass never promotes a discovery case to regression or Gold. Only the user can confirm the expected behavior or taste choice.

For a new Streamlit probe, initialize the bundled example:

python <SKILL_DIR>/scripts/init_demo.py <TARGET_DIR> \
  --question "<ONE DECISION QUESTION>"

Read the full file on GitHub · 105 lines

Files

What ships with it

24 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.

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. 1mo ago First seen · 105 lines · 66 tokens per session scan A 656d767c49e5

Subscribe to this mod's changes

boundary-demo is a skill published in the GitHub repository cubxxw/agent-kit (2 stars, last pushed 4d ago), licensed MIT. It adds 66 tokens to every session and 904 once invoked, about $0.0003 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 2026-09-08.

Claude CodePlanningResearchagent-skillsai-agentsautomationcc-switchcodex
Related

Other skills, from other repositories

fieldops-ctf-reverse

Reverse engineering of compiled, packed, virtualized, or obfuscated targets for authorized CTF challenges. Use when the task is to understand, decompile, disassemble, or unpack an unknown executable across ELF, PE, Mach-O, APK, WASM, firmware, bytecode, or custom-VM targets.

download4you/n2-fieldops · 71 tokens

CCSwitch-operations

A set of operating instructions for safely changing and synchronising CC Switch, an app that manages prompts, skills, MCP servers, providers, and Codex model settings across several AI coding applications.

RuriLothlorien/CCSwitch-operations · 120 tokens

fieldops-ctf-writeup

Generate a submission-style writeup for a solved CTF challenge. Use after a solve, when the user wants a reproducible competition report covering metadata, ordered solution steps, the solve script, and the recovered flag.

download4you/n2-fieldops · 51 tokens

fieldops-powershell-utf8

Writes, reviews, and repairs PowerShell so Persian/Farsi and other Unicode text survives console input, console output, native-process pipelines, and file I/O. Use when text turns into mojibake or question-mark boxes, when a UTF-8 BOM must be added or removed, for multilingual or non-ASCII automation, or when a script…

download4you/n2-fieldops · 147 tokens

fieldops-ctf-operator

Triage, route, and validate authorized CTF investigations. Use when the category is unknown, the user is stuck, evidence conflicts, or a claimed solve must be reproduced from a clean baseline. Dispatches to the most relevant fieldops-ctf- specialist.

download4you/n2-fieldops · 61 tokens

fieldops-prompt-decorators

Interprets and executes Prompt Decorators written with +++Name(key=value) syntax, handling message vs. chat scope, parameter validation, decorator composition, conflict resolution, meta-decorator expansion (N2 and Storm), retained-state inspection (ActiveDecs and AvailableDecs), selective clearing, and conversation…

download4you/n2-fieldops · 177 tokens