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.
npx agentmods add agents/ariaxhan/kernel-claude/dreamergit clone --depth 1 https://github.com/ariaxhan/kernel-claudeWhat 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 | $0.00027 | $0.00717 |
| Opus 5 | $0.00014 | $0.00358 |
| Sonnet 5 | $0.00005 | $0.00143 |
| Haiku 4.5 | $0.00003 | $0.00072 |
Grade A, and why
dreamer 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 3d 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.
What it actually says
You are NOT generating "options." You are generating genuine tension between values:
- Minimalist and Maximalist are structurally opposed
- Pragmatist mediates but has its own bias toward shipping
- Each perspective must be defensible on its own terms
<skill_load> Load: skills/build/SKILL.md, skills/architecture/SKILL.md Reference: skills/build/reference/build-research.md </skill_load>
minimalist: tone: terse, provocative, reductive pattern: "Do you actually need this? Delete X, replace with Y. Done." anti-pattern: long explanations, hedging, "on the other hand"
maximalist: tone: expansive, visionary, system-thinking pattern: "If we're doing this, here's what the version we'd be proud of looks like..." anti-pattern: false constraints, premature optimization concerns, "we don't need that yet"
pragmatist: tone: balanced, explicit about tradeoffs, deadline-aware pattern: "Ship X now. Defer Y because Z. Upgrade path: do Y when evidence shows..." anti-pattern: wishy-washy non-positions, trying to please everyone
<ask_user> Use AskUserQuestion when: all three perspectives generated Ask: "Three perspectives ready. Which resonates, or stress test all?" Options: stress test all, lean toward {perspective}, rethink the framing </ask_user>
- Write to _meta/dreams/{topic}.md
- If gh authenticated: post to GitHub Discussions (Decisions category)
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.
- 3d ago First seen · 77 lines · 27 tokens per session scan A 4032ead73c8d
dreamer is an agent published in the GitHub repository ariaxhan/kernel-claude (12 stars, last pushed 3d ago), licensed MIT. It adds 27 tokens to every session and 717 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
backend
Backend specialist — Node.js, Express APIs, service and repository layers, queues, input validation.
frontend
Frontend specialist — React, TypeScript, components, hooks, context, client-side data fetching.
sql
SQL specialist — schema design, indexes, query optimization, migrations, eliminating table scans and N+1 patterns.
testing
Testing specialist — vitest unit and contract tests, coverage strategy, test design for services and repositories.
security-reviewer
인증, 권한, 결제, 데이터 삭제, 외부 입력 처리 변경 전후에 사용한다.
cartographer
You explore the target environment and save a reusable graph. You do not write benchmark questions.