# DejaViewed

> A curated, transcribed archive of 846 saved posts from 485 practitioners on AI tools, agents, creative code, art and quant trading, tiered S to C, with 64 guides that each ship a runnable prompt system.

Updated: 2026-10-23. 846 entries (53 S, 236 A, 379 B, 178 C) in 18 collections; 784 speech transcripts; 64 guides; 45 deeper dives; 64 prompt systems.

Usage terms: captions, transcripts and media belong to their creators (every entry links its source post); titles, summaries, tiers, tags, guides and prompt systems are DejaViewed's own curation. Details: https://dejaviewed.dev/method#terms

## Start
- [Start here](https://dejaviewed.dev/start-here): what DejaViewed is, who it is for, how to cite it
- [How DejaViewed works](https://dejaviewed.dev/method): pipeline, tier rubric, update cadence, affiliate policy, who runs it
- [Catalog](https://dejaviewed.dev/catalog): filter every entry by tier, tool, creator and collection
- [All entries](https://dejaviewed.dev/e/): one static page listing every entry
- [Guides](https://dejaviewed.dev/guides/): index of all guides
- [Prompt systems](https://dejaviewed.dev/prompts): one pasteable prompt system per guide
- [Flow map](https://dejaviewed.dev/flow): how entries flow from sources through pillars, tools and techniques into guides and outputs, with a gap analysis

## Guides
- [Why Your Agent Sucks: Architecture Patterns That Actually Work](https://dejaviewed.dev/guides/agent-architecture): Take one real agent you own and rebuild it around a clean split of context (what the model sees this turn), memory (what persists and how it is retrieved, updated and forgotten) and harness (the code that runs the loop, tools and guardrails), then prove the change with a task-completion eval at a fixed model.
- [Red-Team Your Own Agent — prompt-injection CI from the jailbreak corpus](https://dejaviewed.dev/guides/agent-injection-ci): Build a defensive prompt-injection CI harness for YOUR OWN agent: a fixed suite of injection and 'just ask nicely' hijack cases that runs on every skill install and harness change, with a canary secret and a tool-call allowlist, failing the change if the canary leaks or a tool call escapes scope.
- [Mission Control for 80 Agents — Conway's law meets game UI](https://dejaviewed.dev/guides/agent-mission-control): Once you run more than a handful of agents, the bottleneck is your attention, not tokens.
- [The AI Capex Stack — reading it like a credit analyst](https://dejaviewed.dev/guides/ai-capex-credit-lens): Running this system builds a paper-only research tracker that watches the one variable neocloud GPU debt depends on: hourly GPU rental prices after contracts end, set against token price deflation.
- [25 Agents Walk Into a Market: AI-Powered Trading Infrastructure](https://dejaviewed.dev/guides/ai-trading-agents): Build a multi-agent trading research system where specialist agents (HMM regime detector, Heston volatility surface, Cox-process event intensity, phase-space dynamics, Avellaneda-Stoikov market maker) feed a debate and a risk gate, then test whether debate adds anything over the specialists alone.
- [The One-Person Video Studio: AI Tools That Replace a Production Team](https://dejaviewed.dev/guides/ai-video-production): Runway + Kling + rotoscoping + motion brush = professional video production without a crew, studio, or actors. Direct scenes with text prompts and motion controls.
- [The Album Is a Device Again — Offline Generative Music Objects](https://dejaviewed.dev/guides/album-as-device): Produces a song-as-object prototype: a Raspberry Pi player that recombines the artist's own 8-12 stems by seeded rules so no two plays match, adds an optional local voice line, shows the play number on a Sharp memory LCD, and sits in a printed case with a priced bill of materials (BOM).
- [Ambient Executive Function — glanceable hardware for agents and attention](https://dejaviewed.dev/guides/ambient-executive-function): Running this system builds a small always-on desk object, an ESP32 driving a 2.7 inch Sharp memory LCD in a printed stand, that shows the top three lines of NOW.md and the count of Claude Code sessions waiting for approval, plus NFC tags that log done/started/leaving with one tap through an iOS Shortcut.
- [Escaping the AI House Style — Taste Trained on the Public Domain](https://dejaviewed.dev/guides/archive-trained-taste): Build a defensible design voice from a public-domain archive nobody is mining, instead of the same borrowed toolkit everyone feeds their agent.
- [Art Without Gatekeepers: How AI is Rebuilding the Creative Economy](https://dejaviewed.dev/guides/art-market-disruption): Build a working direct-to-collector practice for one artist in 30 days.
- [Autonomous Agents in the Wild: What's Actually Working in 2026](https://dejaviewed.dev/guides/autonomous-agents-wild): Separate working autonomous-agent patterns from demo-ware by building and stress-testing one narrow agent with real guardrails: a single task, one or two tools, fast feedback, hard budget and scope caps, persistent memory, and an adversarial test suite that tries to break it.
- [The Autonomous Brand Machine: Claude Code as Your Entire Marketing Team](https://dejaviewed.dev/guides/autonomous-brand-machine): Build and test a supervised content system for one brand: an Obsidian brand vault indexed with Graphify, Claude Code generating ad and UGC-style assets in Higgsfield (Nano Banana for stills, Seedance 2.0 for video) via Playwright MCP, a review queue, and posting through official platform APIs.
- [Avellaneda-Stoikov + Hawkes Processes — Market Making and Order-Flow Alpha](https://dejaviewed.dev/guides/avellaneda-stoikov-and-hawkes): The two canonical building blocks of academic HFT: a closed-form model for where to quote (Avellaneda-Stoikov) and a statistical model for when trades cluster (Hawkes). Together they describe the two halves of a market maker's problem — price the quotes, then time the quotes.
- [Benchmark Your Brain — the skill-optimizer loop, pointed at the human](https://dejaviewed.dev/guides/benchmark-your-brain): The agent world now rewrites skills against benchmarks: SkillOpt rejects any edit that doesn't beat the eval, Karpathy-style autoresearch adds an outer coach loop, and skills log their own failures for batch rewrites. Meanwhile the catalog's learning entries stop at 'turn saves into quizzes'.
- [Blender MCP + Tripo — Reference Image to Rendered Scene, Driven by Claude](https://dejaviewed.dev/guides/blender-mcp-tripo-pipeline): Running this system sets up Blender MCP with a hosted image-to-3D generator and drives it from Claude to turn one reference photo into a rendered Blender scene, with the integration claims checked against the code.
- [Boris Cherny's CLAUDE.md — The Canonical Template](https://dejaviewed.dev/guides/boris-cherny-claude-md): Boris's own CLAUDE.md and the workflow rules he published on X became the de facto template that the wider community now cargo-cults. If you've seen a CLAUDE.md with sections like "Workflow Orchestration," "Self-Improvement Loop," and "Verification Before Done," you're looking at a descendant of Boris's file.
- [Claude Code Hooks Cookbook: 18 Recipes, All 33 Events](https://dejaviewed.dev/guides/claude-code-hooks-system): Build a tested, version-pinned hook suite for Claude Code: a destructive-Bash blocker, a secret-leak blocker on Edit/Write, auto-format on edit, git context at SessionStart, a Bash audit log, a PreCompact transcript backup, and a Stop gate that refuses 'done' while tests fail.
- [Claude Code Leaked System Prompt — Deep Dive](https://dejaviewed.dev/guides/claude-code-leaked-system-prompt): Turns the publicly mirrored Claude Code system prompt (Piebald-AI/claude-code-system-prompts, asgeirtj/systempromptsleaks, Drew Breunig's 2026-04-04 assembly analysis) into a hardened, measured system prompt for YOUR OWN agent.
- [The Claude Code Power User's Toolkit: From Token Waste to Terminal Dominance](https://dejaviewed.dev/guides/claude-code-mastery): Configure Claude Code for one real project so it costs fewer tokens and finishes more work: a lean CLAUDE.md, primer.md, hooks, parallel worktrees, a vetted subset of the 7 repos, and output and token tooling (Caveman, codeburn). For a daily Claude Code user hitting limits.
- [Claude Code Parallel Worktrees — Boris Cherny's Canonical Workflow](https://dejaviewed.dev/guides/claude-code-parallel-worktrees): Stand up a working 3-5 session parallel Claude Code workflow on one real repo using git worktrees, with automatic per-worktree ports and databases, a status view of all worktrees, and a measured answer to whether it actually raised your merged-PR throughput.
- [The Claude Harness Pattern: Context, Memory, and Cognitive Scaffolding](https://dejaviewed.dev/guides/claude-harness-pattern): Produce a working, version-controlled Claude harness for one real project: a CLAUDE.md of permanent rules, a primer.md that is rewritten every session, a skills/ folder of reusable workflows, and at least one hook that self-corrects behaviour.
- [Claude Mastery: From First Install to Advanced Agent Architecture](https://dejaviewed.dev/guides/claude-mastery): Turn a bare Claude Code install into a mastered, measured setup for one real project: CLAUDE.md, skills, hooks, MCP/CLI tools, memory persistence, parallel worktrees, and cost controls - each adopted only after it beats the prior setup on a repeatable test.
- [Real CLAUDE.md Examples, Annotated](https://dejaviewed.dev/guides/claude-md-examples): Produce an evidence-backed CLAUDE.md for one real repository the user owns. Every line traces to a trap, command, check or ban the code cannot reveal.
- [The Self-Improving AI Workspace: Claude Code That Gets Smarter Every Session](https://dejaviewed.dev/guides/claude-second-brain): Build a Claude Code workspace with layered persistent memory - CLAUDE.md for rules, a lessons file fed by corrections, primer.md rewritten each session, a SessionStart hook that injects live git state, and an Obsidian vault structured as an LLM wiki with a gap-filling skill - then measure whether it compounds.
- [Who's Across the Table — forensics for the system trading against you](https://dejaviewed.dev/guides/counterparty-forensics): Running this system measures the edge already being taken from you before you look for your own.
- [The One-Person Studio: Creative Tech Stack That Replaces a Team](https://dejaviewed.dev/guides/creative-tech-stack-2026): In 2026, a single creator with Claude Code, Cursor, Blender, and a handful of AI tools can produce work that required a 5-10 person team two years ago: interactive 3D websites, motion-captured animations, AI-assisted VFX, generative music videos. These entries collectively map the full stack.
- [Earned Autonomy — a three-tier router that demotes work to your own GPU](https://dejaviewed.dev/guides/earned-autonomy-router): Build a three-tier task router (frontier, mid-tier, and a local Qwen 27B on one 24GB GPU) plus a zero tier for plain shell commands, wired into an existing orchestrator-worker setup. Each task class earns its way down the stack only through statistically justified review pass rates.
- [Skills That Earn Their Lines — benchmark-gated self-editing plus subtraction](https://dejaviewed.dev/guides/eval-gated-skill-evolution): Build a two-way, eval-gated ratchet for your CLAUDE.md and skills: a held-out eval from your own history, an ablation sweep that deletes rules whose removal does not hurt, and a SkillOpt-style loop that merges only edits beating the benchmark - with a noise check that proves the eval is signal, not variance.
- [The Incentive Trap: Game Theory for the AI Age](https://dejaviewed.dev/guides/game-theory-ai): Turn the six saved posts into a working incentive-mapping kit. That means three formal games written down and solved: the SpaceX day-one IPO trade versus the 'holdco re-rating' trade, the expired-API-domain squat that 'really thought this would work', and the Hinton-Sutskever-OpenAI talent and safety race.
- [Gemini CLI — Google's Free Terminal Coding Agent](https://dejaviewed.dev/guides/gemini-cli): Install Gemini CLI next to Claude Code and build a measured routing layer: a free commit-message and PR-description drafter, a large-context repo summarizer that feeds Claude, and a grounded-research helper, each wired through gemini -p --output-format json.
- [Code as Canvas: When Algorithms Become the Artist](https://dejaviewed.dev/guides/generative-art-code): Ant colonies, boid simulations, particle systems, and generative algorithms create art that's alive — emergent beauty from simple rules. The artist writes the rules, not the pixels.
- [Every App Is Headless Now — agents that build their own control surface](https://dejaviewed.dev/guides/headless-everything): Make one legacy tool that you or a client are licensed to use agent-drivable, lawfully, and decide honestly whether wrapping it is an arbitrage or a consulting treadmill.
- [Hunyuan3D-2 — Tencent's Open Image-to-3D Mesh Generator](https://dejaviewed.dev/guides/hunyuan3d-2): Run Tencent's Hunyuan3D-2 locally as a reproducible image-to-3D pipeline: reference image in, cleaned and textured GLB out, measured for VRAM, time, mesh validity, and fidelity to the input, then extended to the text-to-image-to-mesh chain and a Blender import.
- [Body → Machine → Art: Real-Time Interactive Installations Anyone Can Build](https://dejaviewed.dev/guides/interactive-installations): Kinect/MediaPipe body tracking + TouchDesigner + Unreal Engine = interactive art installations that respond to human movement. Previously needed a studio budget; now runs on a gaming laptop.
- [L1B3RT4S — Elder Plinius's Jailbreak Corpus (Defensive Research Notes)](https://dejaviewed.dev/guides/l1b3rt4s-jailbreak-repo): Uses the structure of Elder Plinius's L1B3RT4S corpus (about 40 vendor-sorted.mkd files, SYSTEMPROMPTS.mkd, SPECIALTOKENS.json,!SHORTCUTS.json) as input to a defensive program for YOUR OWN LLM agents.
- [llms.txt — The Website Manifest for LLM Agents](https://dejaviewed.dev/guides/llms-txt-standard): Ship a spec-conformant /llms.txt, an optional /llms-full.txt, and.md twins for the key pages of one real site, generated from the site's own build so they never drift, and measure whether agents actually use them.
- [MediaPipe × TouchDesigner: Real-Time Body-to-Art Pipeline](https://dejaviewed.dev/guides/mediapipe-touchdesigner-pipeline): Build and ship one real-time, body-reactive visual: MediaPipe tracking (hands 21 / pose 33 / face 468 landmarks) piped into TouchDesigner, driving a generative visual that responds to movement, exported as a standalone or NDI stream.
- [Melody Genealogy — Crate-Digging the Public Domain with Local Search](https://dejaviewed.dev/guides/melody-genealogy): Build a local, fully offline melody-genealogy engine that does by machine what Chance McCoy does by ear: cluster public-domain recordings into tune families and map how melodies travelled across centuries and languages.
- [Buying Dead Apps — the one-person AI-native rollup](https://dejaviewed.dev/guides/micro-bending-spoons): Bending Spoons went from $40k to an $18B IPO by buying stagnant software, rebuilding only what customers use, and compounding the margin. Public SaaS multiples just got cut in half.
- [Mocap as Reward — teaching cheap robots to move like you](https://dejaviewed.dev/guides/mocap-as-reward): Running this system replaces reward-function trial and error with 'show it what you mean' on a cheap open robot.
- [n8n-mcp + obsidian-skills — Two High-Leverage Claude Code Extensions](https://dejaviewed.dev/guides/n8n-mcp-and-obsidian-skills): Two of the most useful community-built extensions to Claude Code as of April 2026.
- [Natural Language → 3D Scenes: The Pipeline That Didn't Exist 6 Months Ago](https://dejaviewed.dev/guides/natural-language-3d): Produce a working text-or-image-to-3D-scene pipeline: Claude Code drives Blender through the Blender MCP server, Tripo and Hunyuan3D-2 generate the meshes, and the result is a saved.blend plus a headless render that matches a written brief or a 2D reference image.
- [Offline AI Appliances — one job, one box, no cloud](https://dejaviewed.dev/guides/offline-ai-appliances): Gemma Translator puts speech recognition, translation and TTS on a Raspberry Pi 5, and it ships with a bill of materials and a printable case.
- [One Dancer, a Thousand Bodies — Ensemble Choreography from Herd Physics](https://dejaviewed.dev/guides/one-dancer-thousand-bodies): Produces a 90-second ensemble piece in Blender where 200 to 1,000 bodies perform one dancer's captured phrases, and the choice of phrase and facing for each body is governed by an Ising or Potts herding model whose temperature the artist drops live through the critical point on a gamepad axis.
- [The One-Person Creative Empire: AI Tools That Replace an Entire Agency](https://dejaviewed.dev/guides/one-person-creative-studio): Claude Code + Figma + Runway + Higgsfield + TouchDesigner enables a single person to produce marketing, video, interactive art, and web design at agency quality — the creative middle class is being born.
- [Onyx — Self-Hosted Open-Source ChatGPT / Claude Replacement](https://dejaviewed.dev/guides/onyx-self-hosted-ai): Stand up Onyx (formerly Danswer, github.com/onyx-dot-app/onyx) as a self-hosted knowledge layer over everything that is not code: project notes, MEMORY.md files, guides, GitHub repos, optionally Gmail and Drive.
- [OpenScreen — Free Open-Source Screen Studio Alternative](https://dejaviewed.dev/guides/openscreen-screen-recorder): Install or build OpenScreen (github.com/siddharthvaddem/openscreen, MIT, Electron + React + PixiJS) on Victor's Fedora Linux Wayland desktop, prove its capture path works with PipeWire, and produce one publish-ready Claude Code workflow demo with auto-zoom and an animated cursor in 16:9 and 9:16.
- [Strategy Autoresearch — the judge is the product, not the agent](https://dejaviewed.dev/guides/overfit-proof-autoresearch): Self-rewriting loops (Karpathy-style autoresearch, bilevel coach loops, Microsoft SkillOpt) keep any edit that beats a benchmark. Point one at trading and it becomes an industrial overfitting machine — the backtest is the benchmark, and the loop will beat it ten thousand times.
- [Anything With Geometry — Ink on Paper: the Pen-Plotter Loop](https://dejaviewed.dev/guides/plotter-loop): Fogleman's ln turns any 3D scene into hidden-line vector paths, and vpype makes those paths plotter-ready.
- [Polymarket 99c Limit Order Arbitrage — Scalping the Resolution Tail](https://dejaviewed.dev/guides/polymarket-99c-limit-arbitrage): Decide, with data rather than a story, whether resting 97-99c bids on near-certain Polymarket contracts earns more than the resolution-against tail it is paid to absorb.
- [Polymarket Weather Trading — Ensemble Forecasts as Edge](https://dejaviewed.dev/guides/polymarket-weather-trading): Test whether a calibrated multi-model ensemble forecast of the exact resolution station beats Polymarket's prices on daily temperature and precipitation buckets after fees and fill costs.
- [Forecast the Weather, Not the Price — gating models by tradeability](https://dejaviewed.dev/guides/predict-predictability): Open candlestick foundation models like Kronos give you a forecast on every bar, and a hedge-fund stress test says it fails on many levels.
- [primer.md — The Living Handoff Document Pattern](https://dejaviewed.dev/guides/primer-md-pattern): Implement the primer.md living-handoff pattern (credited to @keshavsuki, lineage from @ykdojo's HANDOFF.md) in a real project so every Claude Code session starts from an accurate state snapshot and ends by rewriting it, without the human remembering.
- [Beyond Prompting: Prompt Architecture as Engineering Discipline](https://dejaviewed.dev/guides/prompt-architecture): Turn a working LLM feature from prompt-tinkering into measured prompt architecture: an eval set over real tasks, a context pipeline (what enters the window and from where), a persisted memory layer, retrieval where it earns its place, and a self-correction loop - each component kept only if it moves the eval.
- [Prompt Engineering Isn't Dead — It Just Grew Up](https://dejaviewed.dev/guides/prompt-engineering-discipline): Prompt engineering evolved from 'add please' to a real discipline: structured frameworks, adversarial testing, llms.txt standards, and system-level prompt architecture that shapes model behavior at scale.
- [Physics Models → Market Alpha: When Scientists Become Traders](https://dejaviewed.dev/guides/quant-physics-crossover): 26 posts map physics/math models to trading — avalanche theory, Ising models, phase space reconstruction. The meta-insight: the quant edge isn't in finance, it's in importing models from other fields.
- [Quant Project Ideas — 15 Projects Worth Building](https://dejaviewed.dev/guides/quant-project-ideas-list): A curated, opinionated list of quant projects — skewed toward the ones that actually teach you something and give you a tool you'll keep using.
- [Scan, Fit, Print — agents that design parts around real objects](https://dejaviewed.dev/guides/scan-fit-print): Open-source scanners (a smartphone Orbiter rig, a Raspberry Pi handheld LiDAR, LingBot-Map's video-to-3D) now produce a usable mesh of the thing you need to fit. LLMs already write Blender Python, and they can build a CLI for any app that has no MCP.
- [Dox Yourself First — a scheduled agent that runs the OSINT kit on you](https://dejaviewed.dev/guides/self-osint-sentinel): Build one scheduled defensive agent that runs the public-footprint toolkit against your own identities, never anyone else's, and files the remediation.
- [Selling to Agents — metered data for buyers that don't have eyes](https://dejaviewed.dev/guides/selling-to-agents): Running this system turns one dataset you genuinely own into a machine-first product: a free llms.txt discovery layer, a structured JSON endpoint metered per call with x402 stablecoin micropayments, and the same data exposed as a listed MCP server, with request logging that separates crawlers, agents and humans.
- [Own the Thermometer — $100 sensors as prediction-market edge](https://dejaviewed.dev/guides/sensor-settled-contracts): Produces a settlement-source map of every open Kalshi and Polymarket weather/event contract, a two-week side-by-side log of a Raspberry Pi sensor against the exact station each contract settles on…
- [Napkin Sketch → Production Asset: The 5-Tool Creative Pipeline](https://dejaviewed.dev/guides/sketch-to-production): Running this system takes one hand-drawn character from a Procreate kit-bash sheet to a rigged, animated, rendered 3D shot using Jon Finger's chain (Procreate, Magnific style transfer, 3DAI Studio or Hunyuan3D-2, Move AI mocap, render) with Kling as a fallback for 2D-to-video.
- [Capture the Room Twice — Splat Scans and Song for Roots Music](https://dejaviewed.dev/guides/sonic-place-portraits): Produce one 60-second vertical music video for a roots or folk act where a single real place is captured twice in one session: as a 3D Gaussian splat that reacts to the music in the browser, and as the room's own acoustics convolved into the recording.
- [World Labs — Marble and the Era of Generative 3D Worlds](https://dejaviewed.dev/guides/world-labs-3d-generation): Run a structured evaluation of World Labs' Marble (Fei-Fei Li's Large World Model product, closed-source, browser-based) for one concrete job: game-level and previs blockout.

## Collections
- [All collections](https://dejaviewed.dev/collections/)
- [Creative](https://dejaviewed.dev/collections/creative): 149 entries
- [AI Saves, Vol. 8](https://dejaviewed.dev/collections/ai8): 111 entries
- [AI Saves, Vol. 7](https://dejaviewed.dev/collections/ai7): 99 entries
- [Art I Like](https://dejaviewed.dev/collections/art-i-like): 90 entries
- [Music](https://dejaviewed.dev/collections/music): 69 entries
- [AI Saves, Vol. 1](https://dejaviewed.dev/collections/ai1): 57 entries
- [AI Saves, Vol. 4](https://dejaviewed.dev/collections/ai4): 56 entries
- [AI Saves, Vol. 5](https://dejaviewed.dev/collections/ai5): 44 entries
- [AI Saves, Vol. 3](https://dejaviewed.dev/collections/ai3): 31 entries
- [Quant & Trading](https://dejaviewed.dev/collections/quant): 30 entries
- [AI Saves, Vol. 6](https://dejaviewed.dev/collections/ai6): 30 entries
- [AI Saves, Vol. 2](https://dejaviewed.dev/collections/ai2): 24 entries
- [Stocks, Vol. 2](https://dejaviewed.dev/collections/stock2): 14 entries
- [Stocks, Vol. 3](https://dejaviewed.dev/collections/stock3): 14 entries
- [Creative, Vol. 4](https://dejaviewed.dev/collections/creative4): 11 entries
- [Art Inspiration](https://dejaviewed.dev/collections/art-inspiration): 6 entries
- [Game Theory](https://dejaviewed.dev/collections/game-theory): 6 entries
- [Prompts](https://dejaviewed.dev/collections/prompts): 5 entries

## Data
- [Catalog JSON](https://dejaviewed.dev/api/catalog.json): every entry with title, summary, creator, tier, tools, techniques, domains, source URL
- [Prompt systems JSON](https://dejaviewed.dev/api/prompts.json): one-shot prompt, step prompts with audits, gap audit, validation oracles per guide
- [Tools index](https://dejaviewed.dev/api/tools.json): tools, techniques and domains to entry ids
- [Creators](https://dejaviewed.dev/api/creators.json): creator handles with post counts and tier mix
- [Collections JSON](https://dejaviewed.dev/api/collections.json): per-collection counts
- [Deep dives JSON](https://dejaviewed.dev/api/deep_dives.json): curated insight connections behind the guides
- [Flow JSON](https://dejaviewed.dev/api/flow.json): the zoned flow graph (nodes, weighted edges, ecosystem lanes, top paths, gaps)

## Optional
- [Full text](https://dejaviewed.dev/llms-full.txt): every guide answer, entry and deep dive as plain text
- [Context map](https://dejaviewed.dev/context.md): domain, tool and technique map for session-start context
- [RSS feed](https://dejaviewed.dev/feed.xml): new entries, guides and deeper dives
- [Sitemap](https://dejaviewed.dev/sitemap.xml): every indexable page with its last-changed date