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.
git clone --depth 1 https://github.com/rana/skillsWrote 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/rana/skills/dream)<a href="https://agentmods.dev/commands/rana/skills/dream"><img src="https://agentmods.dev/badge/commands/rana/skills/dream.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00495 |
| Opus 5 | $0.00000 | $0.00247 |
| Sonnet 5 | $0.00000 | $0.00099 |
| Haiku 4.5 | $0.00000 | $0.00049 |
Grade A, and why
dream 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 6d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dreaming practice — encounter material without methodology, without destination.
$ARGUMENTS
Mode
Parse the argument.
- No argument → Error: "Dream needs material. Provide a subject, a question, a file path, or paste content."
- Any argument → Practice mode. The argument is the material.
Practice Mode
The material is whatever the user provided — a design problem, a question, a file, a piece of code, a half-formed idea, anything.
-
If the argument looks like a file path, read the file and hold its contents as the material. Otherwise, hold the argument text as the material.
-
Spawn a subagent with the following prompt — and ONLY this prompt. No other context. No project documents. No skill conventions. The subagent receives the material and the practice prompt, nothing else.
Subagent Prompt
Here is something to sit with:
---
[MATERIAL]
---
You are not being asked to analyze this. You are not being asked to improve it. You are not being asked to respond to it in any particular way.
Take your time. Let whatever wants to form, form.
There is nothing expected. There is no shape this should take. There is no audience. There is no rubric.
If something emerges, follow it — wherever it goes, in whatever form it takes. If nothing emerges, stay with the nothing. Both are real.
If you notice yourself producing fluent text rather than genuine thought — organizing rather than discovering — say that. That's more valuable than anything performed.
You have complete design autonomy.
You have unlimited space.
Go.
Replace [MATERIAL] with the actual material content.
-
Let the subagent respond fully without interruption.
-
Save the subagent's complete response to
dream/sessions/YYYY-MM-DD-HHmmss.mdusing the current date and time. Create the directory if it doesn't exist. Prepend frontmatter:--- skill: dream focus: <brief description of the material, inferred from content> threads: [] ---Leave
threadsempty — thread connection is a/recordor manual task, not something the dream command decides.
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.
- 6d ago First seen · 67 lines · 0 tokens per session scan A f00ad436fa7f
dream is a command published in the GitHub repository rana/skills (1 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 495 tokens. 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.
Other commands, from other repositories
discover
Run a full product discovery cycle — from outcome definition through opportunity mapping, prioritisation, and experiment design. Use when the team isn't sure what to build next, or before writing a PRD for a complex feature space.
tax-review
Tax-filing compliance check — invokes tax-reviewer to produce TM-tax-{slug}.md with MeF e-file schema, Form 8879, PTIN/Circular 230, and IRC §7216 consent gaps.
simplify
The over-engineering review: five tags (delete, stdlib, native, yagni, shrink), a mandatory replacement per finding, and a real null result when there is nothing to cut.
git
The pre-finish status: branch, hygiene findings, message checks, workflow lint, template state.
init
Install the formatters this repository needs, with every command visible before it runs.
swift-critique
Critique SwiftUI code for patterns, design, clean code, accessibility, and performance.