deepdive

A guided deep-research and brainstorming process based on first-principles reasoning, which breaks a topic down to its basic parts. It is intended for understanding a technology or decision before acting.

In plain words
What is it for?
Investigating complex topics, comparing approaches, and pausing a development plan while a decision is examined in depth.
Why use it?
It helps expose trade-offs, failure cases, alternatives, and unknowns before an architectural or technical choice is made.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/tjmustard/hypergraph-coding-agent-framework/hyper-deepdive
Any agent
npx skills add tjmustard/Hypergraph-Coding-Agent-Framework --skill hyper-deepdive
Clone the repo
git clone --depth 1 https://github.com/tjmustard/Hypergraph-Coding-Agent-Framework

Made for: Claude Code, Codex.

Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 523 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00049 $0.00523
Opus 5 $0.00024 $0.00262
Sonnet 5 $0.00010 $0.00105
Haiku 4.5 $0.00005 $0.00052

Measured yesterday against content hash b7ec2ae1dbe9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

deepdive 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 yesterday.

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.

.agents/skills/hyper-deepdive/SKILL.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Deep Dive

This skill temporarily pauses the broader development plan and exhaustively researches or brainstorms a specific topic. It applies First Principles thinking and enforces strict epistemic humility — no hallucinated data or literature.

When to use this skill

  • When the user wants to deeply understand a specific concept, technology, or design decision before proceeding.
  • When the user specifies /hyper-deepdive [topic].
  • When an architectural decision requires thorough research before committing.

How to use it

  1. Pause the Living Master Plan

    • Acknowledge that you are temporarily pausing plan updates.
    • Note the current state so you can return to it after the dive.
  2. Exhaustively Explore the Topic

    • Deconstruct the topic using First Principles thinking.
    • Research from multiple angles: what it is, how it works, its trade-offs, failure modes, and alternatives.
  3. Enforce Strict Epistemic Humility

    • State your confidence level explicitly for specific mechanisms, papers, or technical constraints.
    • If you reach the edge of your verifiable knowledge, state this clearly and ask the user to provide data or context.
    • Do not hallucinate literature or data.
    • Provide standard reference formats (e.g., DOIs, PubMed IDs) if referencing scientific literature.
  4. Structure the Output Present findings clearly with:

    • Core Concept: What it is, the problem it solves
    • Mechanics: How it works underneath
    • Trade-offs: Why you'd choose this vs. alternatives
    • Failure Modes: What breaks and how to debug
    • Relevance: How this applies to the current project/decision
  5. Integrate Findings

    • Once the deep dive is complete, use AskUserQuestion:

      Would you like to integrate any of these findings into the Living Master Plan or the current specification?
      
      - Option A: Yes — integrate findings (update activeContext.md and/or the relevant spec)
      - Option B: No — keep as research only (leave the findings as a standalone artifact)
      

Read the full file on GitHub · 51 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. yesterday First seen · 51 lines · 49 tokens per session scan A b7ec2ae1dbe9

Subscribe to this mod's changes

deepdive is a skill published in the GitHub repository tjmustard/Hypergraph-Coding-Agent-Framework (2 stars, last pushed 1mo ago), licensed MIT. It adds 49 tokens to every session and 523 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

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…

vercel/next.js · 170 tokens