creating-applications

creating-applications is a skill for Claude Code from chrisgagne/grounded-forge. It costs 131 tokens per session (6,110 once invoked), scanned A, original, MIT.

A workflow for creating an application from selected source material, a task description, and optional perspectives or specialist roles. It builds the needed folders, summaries, indexes, and configuration template.

In plain words
What is it for?
It is for creating task-specific applications from source collections, including their distilled references, runtime indexes, and CLAUDE.md template.
Why use it?
It gives the agent one process for turning a general information corpus into a package focused on a particular job. It also checks or creates the task description before assembling the package.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

Part of the grounded-forge plugin — 12 skills, 2 agents, 1 hook shipped together

Good fit It is for creating task-specific applications from source collections, including their distilled references, runtime indexes, and CLAUDE.md template.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/chrisgagne/grounded-forge/creating-applications
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 chrisgagne/grounded-forge --skill creating-applications
Clone the repo
git clone --depth 1 https://github.com/chrisgagne/grounded-forge

Made for: Claude Code.

Or install grounded-forge, the plugin that ships this one along with the rest of its 12 skills, 2 agents, 1 hook.

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 creating-applications

README.md
[![agentmods](https://agentmods.dev/badge/skills/chrisgagne/grounded-forge/creating-applications.svg)](https://agentmods.dev/skills/chrisgagne/grounded-forge/creating-applications)
Your own site
<a href="https://agentmods.dev/skills/chrisgagne/grounded-forge/creating-applications"><img src="https://agentmods.dev/badge/skills/chrisgagne/grounded-forge/creating-applications.svg" alt="Measured on agentmods" height="20"></a>
Per session 131 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,110 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 $0.00131 $0.06110
Opus 5 $0.00066 $0.03055
Sonnet 5 $0.00026 $0.01222
Haiku 4.5 $0.00013 $0.00611

Measured 7d ago against content hash 2e1757cb0a1a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

creating-applications 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 7d 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.

.claude/skills/creating-applications/SKILL.md · 250 lines

How it starts

The opening of the file, as written. The whole thing — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Creating Applications

An application is a compiled distribution: a corpus subset projected onto a task axis (optionally through a lens-set and a practitioner-role agent-set), bundled with a CLAUDE.md template and packaged at corpus.commons/{corpus}/apps/{profile}/. This skill scopes and assembles one application end-to-end.

The skill is the single user-facing entry point for creating an application. Internally it delegates to two sub-skills:

  1. Task-axis scoping. If no task spec exists at corpus.commons/{corpus}/tasks/{task-slug}.md, invoke the creating-tasks flow inline. The dialogue happens in this skill's conversation; the task spec drops at the right path; the skill continues onward without re-prompting the user. If a task spec already exists, skip.
  2. Per-distillation projection. For each source named in the task spec, call creating-distillations once. Pass G's applicability gate decides which distillations fire. Often dispatched as parallel sub-agents.

Between those two delegations, the skill does its own scaffolding work: distillation directory, distillation index (seeded from the task spec's practitioner questions and runtime listener grain), build profile in builds.yaml, package.json build script, build-profiles/{profile}.md CLAUDE.md template, and one agent file per agent declared in the task spec.

When to use

  • A user wants a new application: a new compiled distribution shipping a slice of the corpus for a specific job. Phrasing varies: "create an AAR facilitator app", "build me a coaching tool from this corpus", "I want a distribution for incident review". Route all such asks here.
  • A corpus reshape: the operator wants a new build profile that ships a different slice of the corpus to a different audience for a different task.
  • After ingesting new sources that warrant their own application rather than just extending existing axes: e.g. a corpus of AAR-specific sources where the operator wants the AAR-shaped distribution as a first-class profile.

Read the full file on GitHub · 250 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. 7d ago First seen · 250 lines · 0 tokens per session scan A 2e1757cb0a1a

Subscribe to this mod's changes

creating-applications is a skill published in the GitHub repository chrisgagne/grounded-forge (7 stars, last pushed 17d ago), licensed MIT. It adds 131 tokens to every session and 6,110 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.