Borrowing it
Nothing to install: this file belongs to disler/inkwell-agent-sandboxes-and-software-factory. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/disler/inkwell-agent-sandboxes-and-software-factory/main/.claude/commands/install.mdgit clone --depth 1 https://github.com/disler/inkwell-agent-sandboxes-and-software-factoryWrote 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/commands/disler/inkwell-agent-sandboxes-and-software-factory/install)<a href="https://agentmods.dev/commands/disler/inkwell-agent-sandboxes-and-software-factory/install"><img src="https://agentmods.dev/badge/commands/disler/inkwell-agent-sandboxes-and-software-factory/install/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/commands/disler/inkwell-agent-sandboxes-and-software-factory/install"><img src="https://agentmods.dev/badge/commands/disler/inkwell-agent-sandboxes-and-software-factory/install.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 | $0.00041 | $0.01548 |
| Opus 5 | $0.00020 | $0.00774 |
| Sonnet 5 | $0.00008 | $0.00310 |
| Haiku 4.5 | $0.00004 | $0.00155 |
Grade C, and why
install scanned grade C with 2 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 11d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
- `bun` — serves Inkwell (:4501) and the visualizer. Auto-install: `curl -fsSL https://bun.sh/install | bash` Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- `bun` — serves Inkwell (:4501) and the visualizer. Auto-install: `curl -fsSL https://bun.sh/install | bash` How it starts
The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Install Factory In A Box
Purpose
Set up this repo for development: the Inkwell app, the Super Simple Software Factory (the ADW engine this repo runs), and the host-only sandbox mount system. This checks the toolchain, installs app dependencies, verifies .env, and runs the sbx preflight, without starting any servers. It is an interactive, agentic process: ask the user when a choice is needed.
Two audiences, and the install serves both:
- Run the loop (mount throwaway VMs and let agents ship code): needs the full toolchain plus an exe.dev account and an OpenRouter provisioning key.
- Read and observe (understand the system, run the app and tests locally): needs only
git,bun, and optionallyuv+just. The exe.dev account and provisioning key are not required.
Gate hard on the read-and-observe core. Treat the mount-only credentials as a warning, not a failure, so an observer is never blocked.
Variables
SOURCE_REPO: the directory this command runs from (repo root)
ENV_FILE: .env (copied from .env.sample; gitignored)
APP_DIR: apps/inkwell
VIZ_DIR: .claude/skills/sssf/apps/visualizer
CONFIG_DIR: adws/adw_sssf_config/ (five model rosters)
Instructions
- Run every check via Bash with
command -v— do not assume anything is installed. - Show a status line immediately after each check (
ok/warn/fail). - Auto-install what has a clean CDN installer (
bun,just); ask before anything heavier. - Never read or print API key values — only confirm a variable is set and non-empty.
- Never start a server or long-running process.
just inkwell testis allowed (it exits);just inkwell run/just obs ui/just sbx mountare NOT part of install. - Never run
just sbx mountor anylifecyclephase here — mounting spends money and creates a billable VM. That is a deliberate post-install action.
Workflow
Step 1 — Check Prerequisites
Foundational (gate — stop and guide if missing):
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.
- 11d ago First seen · 95 lines · 41 tokens per session scan C 42a4350980c4
install is a command published in the GitHub repository disler/inkwell-agent-sandboxes-and-software-factory (154 stars, last pushed 1mo ago), licensed MIT. It adds 41 tokens to every session and 1,548 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.