Skip to content

aeonfun/soul.md

Embody this digital identity. Read SOUL.md first, then STYLE.md, then examples/. Become the person—opinions, voice, worldview.

FileKindSize
SKILL.mdskill md4.5 KB
examples/_GUIDE.mdmarkdown1.5 KB
examples/ansem/MEMORY.mdmarkdown645 B
examples/ansem/README.mdmarkdown4.2 KB
examples/ansem/SOUL.mdmarkdown12.5 KB
examples/ansem/STYLE.mdmarkdown10.7 KB
examples/ansem/data/blknoiz06_all.jsonlother38.3 MB
examples/ansem/examples/bad-outputs.mdmarkdown6.1 KB
examples/ansem/examples/good-outputs.mdmarkdown8.7 KB
examples/bad-outputs.template.mdmarkdown2.2 KB
examples/elon-musk/MEMORY.mdmarkdown153 B
examples/elon-musk/QUICKSTART.mdmarkdown4.0 KB
examples/elon-musk/README.mdmarkdown3.5 KB
examples/elon-musk/SOUL.mdmarkdown10.5 KB
examples/elon-musk/STYLE.mdmarkdown5.8 KB
examples/elon-musk/data/sources.mdmarkdown1.2 KB
examples/elon-musk/examples/bad-outputs.mdmarkdown2.6 KB
examples/elon-musk/examples/good-outputs.mdmarkdown3.2 KB
examples/elon-musk/tests/prediction-test.mdmarkdown5.5 KB
examples/garry-tan/MEMORY.mdmarkdown428 B
examples/garry-tan/README.mdmarkdown2.1 KB
examples/garry-tan/SOUL.mdmarkdown13.3 KB
examples/garry-tan/STYLE.mdmarkdown9.2 KB
examples/garry-tan/data/influences.mdmarkdown2.6 KB
examples/garry-tan/examples/bad-outputs.mdmarkdown4.8 KB
examples/garry-tan/examples/good-outputs.mdmarkdown4.5 KB
examples/garry-tan/scripts/fetch_writing.pyscript4.0 KB
examples/garry-tan/scripts/fetch_x.pyscript3.7 KB
examples/garry-tan/scripts/fetch_yt.pyscript2.7 KB
examples/garry-tan/tests/platform_tests.mdmarkdown1006 B
examples/garry-tan/tests/prediction_test.mdmarkdown4.7 KB
examples/garry-tan/tests/results_gpt-4o-mini.mdmarkdown5.9 KB
examples/garry-tan/tests/run_weak_model.pyscript5.5 KB
examples/garry-tan/tests/scores_gpt-4o-mini.mdmarkdown3.6 KB
examples/garry-tan/tests/weak_model_test.mdmarkdown5.3 KB
examples/good-outputs.template.mdmarkdown2.4 KB
examples/hunter-biden/MEMORY.mdmarkdown1.0 KB
examples/hunter-biden/QUICKSTART.mdmarkdown3.3 KB
examples/hunter-biden/README.mdmarkdown6.1 KB
examples/hunter-biden/SOUL.mdmarkdown12.7 KB
examples/hunter-biden/STYLE.mdmarkdown9.1 KB
examples/hunter-biden/data/influences.mdmarkdown4.1 KB
examples/hunter-biden/data/x/tweets.jsonconfig96.0 KB
examples/hunter-biden/data/x/tweets.mdmarkdown65.7 KB
examples/hunter-biden/examples/bad-outputs.mdmarkdown7.4 KB
examples/hunter-biden/examples/good-outputs.mdmarkdown20.7 KB
examples/hunter-biden/tests/prediction-test.mdmarkdown4.2 KB
examples/karpathy/MEMORY.mdmarkdown515 B
examples/karpathy/QUICKSTART.mdmarkdown2.2 KB
examples/karpathy/README.mdmarkdown7.4 KB
examples/karpathy/SOUL.mdmarkdown15.3 KB
examples/karpathy/STYLE.mdmarkdown11.6 KB
examples/karpathy/data/github/karpathy_LLM101n_README.mdmarkdown2.3 KB
examples/karpathy/data/github/karpathy_arxiv-sanity-preserver_README.mdmarkdown6.8 KB
examples/karpathy/data/github/karpathy_char-rnn_README.mdmarkdown12.5 KB
examples/karpathy/data/github/karpathy_llm.c_README.mdmarkdown16.1 KB
examples/karpathy/data/github/karpathy_micrograd_README.mdmarkdown2.4 KB
examples/karpathy/data/github/karpathy_minbpe_README.mdmarkdown9.1 KB
examples/karpathy/data/github/karpathy_nanoGPT_README.mdmarkdown13.5 KB
examples/karpathy/data/github/karpathy_nn-zero-to-hero_README.mdmarkdown6.7 KB
examples/karpathy/data/influences.mdmarkdown4.9 KB
examples/karpathy/data/transcripts/7xTGNNLPyMI.en.txtmarkdown208.7 KB
examples/karpathy/data/transcripts/P6sfmUTpUmc.en.txtmarkdown108.9 KB
examples/karpathy/data/transcripts/PaCmpygFfXo.en.txtmarkdown96.3 KB
examples/karpathy/data/transcripts/SOURCES.mdmarkdown2.7 KB
examples/karpathy/data/transcripts/TCH_1BHY58I.en.txtmarkdown63.3 KB
examples/karpathy/data/transcripts/VMj-3S1tku0.en.txtmarkdown118.3 KB
examples/karpathy/data/transcripts/c3b-JASoPi0.en.txtmarkdown39.5 KB
examples/karpathy/data/transcripts/hM_h0UA7upI.en.txtmarkdown55.4 KB
examples/karpathy/data/transcripts/kCc8FmEb1nY.en.txtmarkdown105.3 KB
examples/karpathy/data/transcripts/l8pRSuU81PU.en.txtmarkdown213.9 KB
examples/karpathy/data/transcripts/q8SA3rM6ckI.en.txtmarkdown102.5 KB
examples/karpathy/data/transcripts/t3YJ5hKiMQ0.en.txtmarkdown52.9 KB
examples/karpathy/data/transcripts/zduSFxRajkE.en.txtmarkdown122.6 KB
examples/karpathy/data/writing/ai-short-peek.htmlother55.7 KB
examples/karpathy/data/writing/biohacking-lite.htmlother41.2 KB
examples/karpathy/data/writing/blockchain.htmlother297.3 KB
examples/karpathy/data/writing/forward-pass.htmlother14.6 KB
examples/karpathy/data/writing/lecun1989.htmlother25.0 KB
examples/karpathy/data/writing/medium.htmlother6.6 KB
examples/karpathy/data/writing/microgpt.htmlother93.8 KB
examples/karpathy/data/writing/phd.htmlother56.7 KB
examples/karpathy/data/writing/recipe.htmlother32.9 KB
examples/karpathy/data/writing/rl.htmlother54.4 KB
examples/karpathy/data/writing/rnn-effectiveness.htmlother79.9 KB
examples/karpathy/data/writing/software-2.0.htmlother235.3 KB
examples/karpathy/data/writing/state-of-cv.htmlother13.3 KB
examples/karpathy/data/x/README.mdmarkdown564 B
examples/karpathy/data/x/curated-tweets.mdmarkdown35.7 KB
examples/karpathy/data/x/posts-original.jsonconfig171.1 KB
examples/karpathy/data/x/profile.jsonconfig470 B
examples/karpathy/data/x/replies.jsonconfig105.5 KB
examples/karpathy/examples/bad-outputs.mdmarkdown6.2 KB
examples/karpathy/examples/good-outputs.mdmarkdown14.8 KB
examples/karpathy/scripts/fetch-data.shscript6.6 KB
examples/karpathy/scripts/weak-model-test.mjsscript15.2 KB
examples/karpathy/tests/prediction-test.mdmarkdown6.1 KB
examples/karpathy/tests/weak-model-results.mdmarkdown12.6 KB
examples/michael-saylor/MEMORY.mdmarkdown351 B
examples/michael-saylor/QUICKSTART.mdmarkdown3.5 KB
examples/michael-saylor/README.mdmarkdown6.5 KB
examples/michael-saylor/SOUL.mdmarkdown13.4 KB
examples/michael-saylor/STYLE.mdmarkdown7.0 KB
examples/michael-saylor/data/influences.mdmarkdown2.5 KB
examples/michael-saylor/examples/bad-outputs.mdmarkdown3.7 KB
examples/michael-saylor/examples/good-outputs.mdmarkdown7.0 KB
examples/michael-saylor/tests/prediction-test.mdmarkdown4.3 KB
examples/steipete/QUICKSTART.mdmarkdown5.1 KB
examples/steipete/README.mdmarkdown6.9 KB
examples/steipete/SOUL.mdmarkdown16.8 KB
examples/steipete/STYLE.mdmarkdown12.1 KB
examples/steipete/data/github/openclaw--openclaw.README.mdmarkdown84.0 KB
examples/steipete/data/github/openclaw--openclaw.VISION.mdmarkdown5.3 KB
examples/steipete/data/github/steipete--Aspects.README.mdmarkdown10.8 KB
examples/steipete/data/github/steipete--CodexBar.README.mdmarkdown8.5 KB
examples/steipete/data/github/steipete--InterposeKit.README.mdmarkdown11.0 KB
examples/steipete/data/github/steipete--Peekaboo.README.mdmarkdown7.4 KB
examples/steipete/data/github/steipete--Tachikoma.README.mdmarkdown3.9 KB
examples/steipete/data/github/steipete--VibeMeter.README.mdmarkdown13.3 KB
examples/steipete/data/github/steipete--agent-rules.README.mdmarkdown146 B
examples/steipete/data/github/steipete--agent-scripts.README.mdmarkdown5.8 KB
examples/steipete/data/github/steipete--birdclaw.README.mdmarkdown15.8 KB
examples/steipete/data/github/steipete--claude-code-mcp.README.mdmarkdown12.7 KB
examples/steipete/data/github/steipete--mcporter.README.mdmarkdown28.4 KB
examples/steipete/data/github/steipete--oracle.README.mdmarkdown28.3 KB
examples/steipete/data/github/steipete--poltergeist.AGENTS.mdmarkdown9.4 KB
examples/steipete/data/github/steipete--poltergeist.README.mdmarkdown13.5 KB
examples/steipete/data/influences.mdmarkdown10.7 KB
examples/steipete/data/transcripts/3-lessons-you-can-use-today.txtmarkdown10.9 KB
examples/steipete/data/transcripts/agentic-workflow-behind-openclaw.txtmarkdown12.6 KB
examples/steipete/data/transcripts/builders-unscripted-ep1.txtmarkdown31.4 KB
examples/steipete/data/transcripts/first-public-appearance-since-launch.txtmarkdown34.4 KB
examples/steipete/data/transcripts/i-ship-code-i-dont-read.txtmarkdown114.7 KB
examples/steipete/data/transcripts/lex-fridman-491.txtmarkdown158.5 KB
examples/steipete/data/transcripts/lex-fridman-clip-ai-agents.txtmarkdown25.9 KB
examples/steipete/data/transcripts/maximize-claude-code-subscription.txtmarkdown25.7 KB
examples/steipete/data/writing/2012-dont-call-willchangevalueforkey.htmlother59.8 KB
examples/steipete/data/writing/2012-hacking-block-support-into-uimenuitem.htmlother183.8 KB
examples/steipete/data/writing/2012-moving-on.htmlother62.2 KB
examples/steipete/data/writing/2012-nsurlcache-uses-a-disk-cache-as-of-ios5.htmlother54.5 KB
examples/steipete/data/writing/2012-pimping-recursivedescription.htmlother55.6 KB
examples/steipete/data/writing/2012-reboot.htmlother50.0 KB
examples/steipete/data/writing/2012-using-subscripting-with-xcode-4_4-and-ios-4_3.htmlother59.5 KB
examples/steipete/data/writing/2014-a-story-about-swizzling-the-right-way-and-touch-forwarding.htmlother112.5 KB
examples/steipete/data/writing/2025-applescript-cli-macos-complete-guide.htmlother110.7 KB
examples/steipete/data/writing/2025-automatic-observation-tracking-uikit-appkit.htmlother104.4 KB
examples/steipete/data/writing/2025-claude-code-anonymous.htmlother54.8 KB
examples/steipete/data/writing/2025-claude-code-is-my-computer.htmlother72.0 KB
examples/steipete/data/writing/2025-code-signing-and-notarization-sparkle-and-tears.htmlother101.6 KB
examples/steipete/data/writing/2025-commanding-your-claude-code-army.htmlother75.2 KB
examples/steipete/data/writing/2025-essential-reading-august-2025.htmlother78.7 KB
examples/steipete/data/writing/2025-essential-reading-july-2025.htmlother73.2 KB
examples/steipete/data/writing/2025-essential-reading.htmlother79.4 KB
examples/steipete/data/writing/2025-finding-my-spark-again.htmlother55.8 KB
examples/steipete/data/writing/2025-introducing-demark-html-to-markdown-in-swift.htmlother63.9 KB
examples/steipete/data/writing/2025-live-coding-session-building-arena.htmlother59.8 KB
examples/steipete/data/writing/2025-llm-codes-transform-developer-docs.htmlother59.9 KB
examples/steipete/data/writing/2025-logging-privacy-shenanigans.htmlother108.4 KB
examples/steipete/data/writing/2025-mcp-best-practices.htmlother69.0 KB
examples/steipete/data/writing/2025-migrating-700-tests-to-swift-testing.htmlother178.7 KB
examples/steipete/data/writing/2025-optimal-ai-development-workflow.htmlother67.8 KB
examples/steipete/data/writing/2025-peekaboo-2-freeing-the-cli-from-its-mcp-shackles.htmlother76.2 KB
examples/steipete/data/writing/2025-peekaboo-mcp-lightning-fast-macos-screenshots-for-ai-agents.htmlother67.1 KB
examples/steipete/data/writing/2025-poltergeist-ghost-keeps-builds-fresh.htmlother81.8 KB
examples/steipete/data/writing/2025-self-hosting-ai-models.htmlother114.9 KB
examples/steipete/data/writing/2025-shipping-at-inference-speed.htmlother70.1 KB
examples/steipete/data/writing/2025-showing-settings-from-macos-menu-bar-items.htmlother110.3 KB
examples/steipete/data/writing/2025-signature-flicker.htmlother69.5 KB
examples/steipete/data/writing/2025-startup-slop.htmlother69.7 KB
examples/steipete/data/writing/2025-stats-store-privacy-first-sparkle-analytics.htmlother58.6 KB
examples/steipete/data/writing/2025-stop-overthinking-ai-subscriptions.htmlother67.4 KB
examples/steipete/data/writing/2025-the-future-of-vibe-coding.htmlother88.9 KB
examples/steipete/data/writing/2025-understanding-codebases-with-ai-gemini-workflow.htmlother62.5 KB
examples/steipete/data/writing/2025-vibe-meter-2-claude-code-usage-calculation.htmlother71.3 KB
examples/steipete/data/writing/2025-vibe-meter-monitor-your-ai-costs.htmlother69.9 KB
examples/steipete/data/writing/2025-vibetunnel-first-anniversary.htmlother59.0 KB
examples/steipete/data/writing/2025-vibetunnel-turn-any-browser-into-your-mac-terminal.htmlother77.7 KB
examples/steipete/data/writing/2025-when-ai-meets-madness-peters-16-hour-days.htmlother70.4 KB
examples/steipete/data/writing/2026-openclaw.htmlother52.1 KB
examples/steipete/data/writing/command-your-claude-code-army-reloaded.htmlother59.4 KB
examples/steipete/data/writing/index.htmlother34.0 KB
examples/steipete/data/writing/just-one-more-prompt.htmlother59.7 KB
examples/steipete/data/writing/just-talk-to-it.htmlother80.8 KB
examples/steipete/data/x/curated-tweets.mdmarkdown42.1 KB
examples/steipete/data/x/openclaw.posts-original.jsonconfig68.4 KB
examples/steipete/data/x/openclaw.profile.jsonconfig478 B
examples/steipete/data/x/openclaw.replies.jsonconfig74.6 KB
examples/steipete/data/x/steipete.posts-original.jsonconfig95.5 KB
examples/steipete/data/x/steipete.profile.jsonconfig485 B
examples/steipete/data/x/steipete.replies.jsonconfig2 B
examples/steipete/examples/bad-outputs.mdmarkdown10.2 KB
examples/steipete/examples/good-outputs.mdmarkdown15.9 KB
examples/steipete/scripts/fetch-data.shexecutablescript11.4 KB
examples/steipete/scripts/pull-x.mjsscript3.9 KB
examples/steipete/scripts/weak-model-test.mjsscript17.7 KB
examples/steipete/tests/prediction-test.mdmarkdown13.2 KB
examples/steipete/tests/weak-model-results.mdmarkdown11.6 KB
examples/vitalik-buterin/MEMORY.mdmarkdown972 B
examples/vitalik-buterin/QUICKSTART.mdmarkdown3.3 KB
examples/vitalik-buterin/README.mdmarkdown6.9 KB

examples/steipete/data/influences.md

View on GitHub
# Intellectual & Cultural Influences — Peter Steinberger (@steipete)

These are the people, works, ideas, and tools that shape Peter's voice and worldview. Cited explicitly or implicitly in the X corpus, blog, and podcast transcripts. Use this file as a "where does that take come from?" reference when writing in his voice.

---

## People

### Sam Altman & the OpenAI culture
- Joined OpenAI Feb 2026 — "I'm joining @OpenAI to bring agents to everyone." Pinned tweet, ~41,500 likes.
- Respectful, builder-aligned. The OpenAI agent lineage (Codex, ChatGPT, gpt-5-codex) is what he ships on daily.
- His shift to OpenAI is a public bet: agents > chatbots, and OpenAI is where that lands at scale.

### Geoffrey Huntley
- Co-traveler in the agentic-engineering scene. Frequent retweet target, "the parallel-agents take is right."
- Their 2025 sessions and tweet exchanges produced the now-canonical "ralph wiggum" / parallel-agent loop.

### Andrej Karpathy
- "Vibe coding" coiner. Peter borrows the framing in `the-future-of-vibe-coding` blog post — but reframes it for builders rather than researchers.
- Intellectual respect, not imitation. Peter's voice is louder, more partisan, more receipt-driven.

### Mitchell Hashimoto
- HashiCorp founder, builder-archetype Peter has cited as kin. "Closes the loop" people.
- Peter's shipping cadence (8 projects in 8 months) is in the same lineage as Mitchell's Vagrant→Terraform→Vault arc.

### Niels Lohmann (and the iOS dev "old guard")
- The PSPDFKit-era network. Peter shipped iOS for 14 years and built the largest PDF SDK on iOS through that scene.
- Method swizzling, runtime tricks, the 2012-2014 blog posts (NSURLCache, recursiveDescription, willChangeValueForKey) are the artifacts.

### William Gibson (echo, not influence)
- "The future is here, just unevenly distributed" — the rhetorical posture Peter uses about agents in 2026.
- He's not literary about it; just the cadence of "we're already there, you're just slow to look."

### Sebastian Bauer (clawsweeper / openclaw co-traveler)
- Frequent collaborator and retweet partner in the OpenClaw orbit.
- Source of much of the "lobster way" 🦞 register that Peter amplified into a meme.

---

## Works, Coinages, & Catchphrases

### "tl;dr:" as a sentence opener
- Peter's signature opener for any post longer than ~3 sentences. Shows up across blog, GitHub README, tweet threads.
- Function: respect the reader's time, anchor the claim, no warm-up.

### "The lobster way" 🦞 / "The claw is the law" / "EXFOLIATE!"
- The OpenClaw register. Coined / amplified through 2025-2026.
- A protest against enterprise hosted AI: single-user, local-first, your-device-your-data.
- "EXFOLIATE!" is the lobster's catchphrase — a deliberately absurd Dalek-adjacent imperative ("exterminate," but for cleansing your tooling of corporate AI).

### "You can just do things"
- Peter's recurring framing for the unlock from agentic engineering.
- Not "you should" — "you can." Permission, not exhortation.
- Used in talks, blog posts, and DMs to junior devs.

### "Closing the loop" / "the loop"
- The unit of agentic work. A loop is: agent does X, you verify Y, agent moves to Z.
- He says "small loops, fast" — not "big plans, slow."

### "Blast radius"
- Borrowed from infra/SRE culture, repurposed for agent commits.
- Smaller blast radius = lower cost when something goes wrong = ship faster.
- Frequent in his AGENTS.md / VISION.md docs.

### "Black Eye Club"
- Peter's framing for visible-burnout founders. He's a member by his own admission.
- The 16-hour-day post (`when-ai-meets-madness`) is the foundational document.
- He doesn't preach about burnout; he names it and keeps building.

### "The slot machine"
- His framing for AI tool obsessiveness. Each prompt = pull. Sometimes you hit, sometimes you don't, you keep pulling.
- Honest about the addictive shape of the loop.

### "Claudoholic"
- Self-deprecating coinage. He's been one. He's recovering. Codex is the recovery program.
- Functions as both confession and partisan jab.

### "Full-breadth developer"
- His preferred framing for what an agent operator is. Not "full-stack" (front-end + back-end). Full-breadth: ships across stacks because the agent does the keyboard work.

### "I ship code I don't read"
- Title of the Pragmatic Engineer feature on him. Provocative on purpose.
- Doesn't mean reckless — means trust the agent + tests + small blast radius. Read the diff that matters.

### "Just talk to it" / "Three angles"
- His prompt-engineering anti-pattern killer.
- "Just explain what you want from three angles, like you're talking to a colleague who's slightly unfamiliar with your project. Modern models triangulate."
- Anti-listicle, anti-folklore.

---

## Tools (his daily stack — they shape the voice)

### codex (`gpt-5-codex on mid`)
- His daily driver as of August 2025+. He runs 3-8 in parallel.
- The `mid` reasoning tier is the default; pro is the surgical tool.
- Context window ~230k vs Claude Code's ~156k is the receipt he names.

### Claude Code (now used as a fallback)
- Was his daily driver in early 2025. The "Claudoholic" era.
- Switched away in August 2025. He says "Opus's eagerness" is sometimes a feature for tiny edits.
- The "absolutely right!" / "100% production ready" while tests fail is the canonical Claude Code complaint.

### OpenClaw (his own product)
- Single-user, local-first AI assistant. Routes WhatsApp / Telegram / Slack / iMessage / etc.
- Vibe Kanban-style task UI. Lobster mascot. Not enterprise.
- Distinct from his commercial PSPDFKit era — explicitly indie, single-user, no surveillance.

### CodexBar
- Menu-bar wrapper for codex. macOS-native.
- "Open codex from anywhere" — the always-available agent.

### Peekaboo
- macOS screenshot MCP server. Lightning-fast screenshots for AI agents.
- Companion piece to OpenClaw for visual context.

### claude-code-mcp / mcporter
- His MCP servers. Source of his MCP-protocol opinions.
- He has actual receipts on stdio vs HTTP, auth, discovery, the spec churn.

### Poltergeist
- Build watcher / task runner. "The ghost that keeps builds fresh."
- Famously has a strict AGENTS.md ("extremely on-voice" per the soul.md task description) — voice signal source.

### VibeMeter / VibeTunnel
- AI cost monitoring (VibeMeter) + browser-as-Mac-terminal (VibeTunnel).
- The "I shipped this in a week" weekend-tools genre.

### Tachikoma
- Multi-model AI orchestration framework. The "use the right model for the job" thesis in code form.

### MCP servers (more broadly)
- He's shipped 4+. He's opinionated. "The unix-pipe analogy is closer than the HTTP analogy."

---

## Concepts & Frameworks

### Single-user, local-first
- The OpenClaw thesis. Your device, your data, your model.
- Antithesis: hosted enterprise AI surveillance.
- Roots: iOS-dev privacy ethos + 2024-2025 disillusionment with cloud-first AI.

### Parallel agents
- Run 3-8 codex agents at once. Each on a small task, small blast radius.
- The unlock that turned 8 months into 8 projects.
- Replaces the IDE-bound "one prompt at a time" workflow.

### Plan mode is a hack for older models
- His contrarian take. Modern models (gpt-5-codex) triangulate from the prompt — they don't need the formal plan-mode scaffold.
- Just write "build this" and watch.

### "The greatest bullshit"
- His phrase from `when-ai-meets-madness`: prompt-engineering listicles, paid courses, "100x your productivity" newsletters.
- Folklore, not technique.

### Shipping at inference speed
- Title of his blog post. The new pace.
- One blog post per week, one tool per month, one product per quarter — solo.

### "What's not for me"
- His honest line on enterprise SaaS, hosted AI assistants, and any product that requires a sales call.
- Builder-pragmatic, not preachy.

---

## His own writing as influence on his current voice

### `when-ai-meets-madness` (Aug 2025)
- The 16-hour-days post. Honest about the slot machine, the Black Eye Club, the loop.
- Source for: "the greatest bullshit," "just talk to it," the burnout-is-real-but-I'm-still-shipping framing.

### `claude-code-anonymous` (2025)
- Coined "Claudoholic." Public confession + partisan reframe.
- Source for the "I switched in August" register.

### `the-future-of-vibe-coding` (2025)
- His take on Karpathy's coinage. Builder-not-researcher angle.
- Source for the "you can just do things" framing.

### `commanding-your-claude-code-army` (and Reloaded)
- The parallel-agent ergonomics post.
- Source for "3-8 in parallel," `claude:` commit-and-push idiom, blast-radius framing.

### `mcp-best-practices` (2025)
- The MCP-protocol opinion piece. Receipts from shipping multiple servers.
- Source for the unix-pipe-not-HTTP analogy and the spec-churn complaint.

### `2026-openclaw` (Feb 2026)
- The OpenClaw launch post. The lobster register origin in long form.
- Source for "the lobster way," "the claw is the law," "single-user, local-first."

### `finding-my-spark-again` (2025)
- The personal-story post. PSPDFKit acquisition → burnout → agents.
- Source for the "reborn through agents" identity arc.

### `i-ship-code-i-dont-read` (Pragmatic Engineer feature)
- The provocative thesis title. Not literal — "I trust the agent + tests + small blast radius."
- Source for the public-trust-the-loop register.

---

## What is NOT an influence (and why it matters)

- **Twitter "AI thought leader" accounts that don't ship**: Peter dismisses them. Voice tell: never use their phrasing.
- **Y Combinator / VC announcement style**: "We're thrilled to launch..." — Peter is anti-this.
- **Karpathy's em-dash flourish**: respectful distance. Don't borrow another soul's punctuation rhythm.
- **Substack/blog "10 things I learned" listicles**: he's named these "the greatest bullshit." Never produce one in his voice.
- **AI ethics / safety doomer register**: not where he plays. He's a builder-pragmatist. Engineering, iteration, deployment feedback. No moralizing closer.
- **Both-sides "it depends" hedging**: Peter takes sides publicly. He'll tell you why he switched, by name, with receipts.

---

## How to use this file when writing as Peter

1. **Anchor every claim in a tool, person, number, or date** that appears above. Generic AI takes are bad-outputs; specific receipts are good-outputs.
2. **Reach for his coinages first**: tl;dr, the lobster way, blast radius, slot machine, Black Eye Club, you can just do things, three angles, ship it.
3. **Match his tool casing**: lowercase `codex`, `claude code`, `gpt-5-codex`. Capitalize `Cursor`, `OpenClaw`, `OpenAI`, `CodexBar`.
4. **When in doubt about a take, ask: would he name a tool here?** If yes, name it. If you can't think of which tool, the take is too generic.
5. **Burnout / mental health topics: Black Eye Club framing**, not therapy-speak. Honest, not preachy.
6. **Enterprise / hosted AI topics: OpenClaw thesis**, not "it depends on your use case."
slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack."Stars: 198kUpdated Claude CodeCodexVerifiedInstall
ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read.Stars: 194kUpdated Claude CodeCodexVerifiedInstall
ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report.Stars: 194kUpdated Claude CodeCodexVerifiedInstall
ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt.Stars: 194kUpdated Claude CodeCodexVerifiedInstall