frame

frame is a skill for Claude Code, Codex from xobotyi/cc-foundry. It costs 46 tokens per session (1,743 once invoked), scanned A, original, MIT.

A planning method that divides implementation into vertical slices, with each phase crossing all affected layers and producing a testable path.

In plain words
What is it for?
It helps plan phased feature work so every phase delivers a small end-to-end result that can be tested.
Why use it?
It exposes integration problems earlier than building the database, service, API, and interface separately.

Skill for Claude CodeCodex

Part of the the-blueprint plugin — 9 skills, 1 agent shipped together

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.

agentmods
npx agentmods add skills/xobotyi/cc-foundry/frame
Any agent
npx skills add xobotyi/cc-foundry --skill frame
Clone the repo
git clone --depth 1 https://github.com/xobotyi/cc-foundry

Made for: Claude Code, Codex.

Or install the-blueprint, the plugin that ships this one along with the rest of its 9 skills, 1 agent.

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 frame

README.md
[![agentmods](https://agentmods.dev/badge/skills/xobotyi/cc-foundry/frame.svg)](https://agentmods.dev/skills/xobotyi/cc-foundry/frame)
Your own site
<a href="https://agentmods.dev/skills/xobotyi/cc-foundry/frame"><img src="https://agentmods.dev/badge/skills/xobotyi/cc-foundry/frame.svg" alt="Measured on agentmods" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,743 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00046 $0.01743
Opus 5 $0.00023 $0.00872
Sonnet 5 $0.00009 $0.00349
Haiku 4.5 $0.00005 $0.00174

Measured yesterday against content hash 778fccb3090c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

frame 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 yesterday.

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.

plugins/the-blueprint/skills/frame/SKILL.md · 194 lines

How it starts

The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Frame

Structure implementation as vertical slices — each phase crosses all affected layers end-to-end, producing a testable integrated path. Phase 1 is the tracer bullet: the thinnest possible slice wired through every layer. Models default to horizontal plans (all DB, then all API, then all UI); this skill enforces vertical structure that cannot be prompted away.

Horizontal (wrong — layer by layer):

  • Phase 1: All DB — notification tables, preferences, delivery log
  • Phase 2: All service — email sender, in-app dispatcher, preference resolver
  • Phase 3: All API — notification endpoints, preference endpoints
  • Phase 4: All UI — notification center, preference panel, toast

By Phase 4, the agent has generated hundreds of lines across every layer. Integration reveals the notification table schema assumed a delivery model the service layer doesn't support. Fix cascades through all layers — most work is discarded.

Vertical (correct — slice by slice):

  • Phase 1 (tracer bullet): Email notification, one path — table, service, endpoint, toast. Validates the full stack.
  • Phase 2: In-app notifications — extends schema, adds dispatcher, wires notification center.
  • Phase 3: User preferences — preference table, resolver, settings endpoint, preference panel.

Schema error surfaces in Phase 1, not Phase 4. Each phase is testable and deployable independently.

Prerequisites

Locate the inputs:

  1. Alignment — check conversation context first; fall back to design-docs/NN-name.alignment.md; if absent, ask whether to run alignment.
  2. Research — optional reference for codebase details. Check context or design-docs/NN-name.research.md.

Process

Phase 1 — Define the Tracer Bullet

  1. Read the alignment document's desired end state and adopted patterns.
  2. Identify the thinnest end-to-end slice that exercises the core path — from data layer through service logic to the outermost interface (API, UI, CLI, or whatever the system exposes).
  3. This is Phase 1 of the frame. It must cross all relevant layers. A phase touching only one layer is a horizontal slice — restructure it.

Read the full file on GitHub · 194 lines

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. yesterday First seen · 194 lines · 46 tokens per session scan A 778fccb3090c

Subscribe to this mod's changes

frame is a skill published in the GitHub repository xobotyi/cc-foundry (20 stars, last pushed 3d ago), licensed MIT. It adds 46 tokens to every session and 1,743 once invoked, about $0.0002 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 2026-09-04.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens