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 skills add DanialDaeHyunNam/omniscitus --skill blueprint-splitgit clone --depth 1 https://github.com/DanialDaeHyunNam/omniscitusWrote 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/skills/danialdaehyunnam/omniscitus/blueprint-split)<a href="https://agentmods.dev/skills/danialdaehyunnam/omniscitus/blueprint-split"><img src="https://agentmods.dev/badge/skills/danialdaehyunnam/omniscitus/blueprint-split/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/skills/danialdaehyunnam/omniscitus/blueprint-split"><img src="https://agentmods.dev/badge/skills/danialdaehyunnam/omniscitus/blueprint-split.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 | $0.00075 | $0.01515 |
| Opus 5 | $0.00037 | $0.00758 |
| Sonnet 5 | $0.00015 | $0.00303 |
| Haiku 4.5 | $0.00007 | $0.00152 |
Grade A, and why
blueprint-split 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 9d 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 — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Blueprint Split — Convert Flat Blueprint to Nested
A blueprint that holds 300+ entries (or mixes unrelated concerns) is
a hotspot for merge conflicts and cognitive overhead. RFC #10 defines
a nested split format where one large blueprints/{dir}.yaml is
broken into blueprints/{dir}/{group}.yaml files keyed by the
second path component.
This skill performs the conversion safely and reversibly.
When to Use
- User types
/blueprint-split {dir} - User says "split this blueprint", "이 블루프린트 쪼개", "분할"
- The session-start advisory recommends
/blueprint-splitfor a specific large blueprint
Usage
/blueprint-split src
/blueprint-split .claude
The argument is the top-level directory name as it appears in
the blueprint filename (without the .yaml extension and without
the _ prefix that hides dot-directories). Hidden directories like
.claude should be passed as .claude, not _claude — the skill
normalizes internally.
Instructions
Step 1: Validate Inputs
-
Check the user supplied a directory argument. If not, list the current top-level blueprints (
ls .omniscitus/blueprints/*.yaml) and ask which one to split. -
Verify the target blueprint file exists:
blueprints/{normalize(dir)}.yaml(where normalize = leading.becomes_)- If not, report the available blueprint files and stop.
-
Verify the target is not already split: check that
blueprints/{normalize(dir)}/directory doesn't exist. If it does, report that the blueprint is already nested and stop. The user can use/blueprint-merge {dir}to undo first.
Step 2: Read the Existing Blueprint
Read the entire blueprints/{normalize(dir)}.yaml file. Parse all
entries — paths, status, source, change_log, purpose, etc.
For each entry, compute its bucket by taking the second path component:
src/lib/auth.ts→ bucket =libsrc/index.ts→ bucket =_root(file is at the top ofsrc/).claude/skills/foo.md→ bucket =skills.claude/CLAUDE.md→ bucket =_root
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.
- 9d ago First seen · 182 lines · 75 tokens per session scan A fafa0c19d5d0
blueprint-split is a skill published in the GitHub repository DanialDaeHyunNam/omniscitus (5 stars, last pushed 1mo ago), licensed MIT. It adds 75 tokens to every session and 1,515 once invoked, about $0.0004 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
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…
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…