LLM Mart Basic

Use when turning one named customer's measured win into a case study, or the attributed testimonial quote that travels with it — consent-cleared, metrics-anchored proof for the next skeptical buyer. NOT the deck that sells the vision to a room (that is `pitch-deck`), NOT thought-

Use when building or shipping a Manifest V3 browser extension and hitting its quirks — service worker dying and losing state, permission warnings, a Chrome Web Store rejection, content-script/worker/popup messaging, or an MV2-to-V3 migration. NOT a generic web app (that is `nextj

Use when a spec exists and must be de-risked before planning — hunt its ambiguities, unstated assumptions and edge cases, ask the few build-changing questions, bake the answers back into the spec. The rsc SDD gate between `specify` (writes the spec) and `plan` (designs the build)

Use when running a ClickHouse server for high-volume OLAP: choosing a MergeTree engine and ORDER BY/PARTITION BY keys, ingesting billions of event/log/metric rows, pre-aggregating with materialized views, or fixing a query that scans instead of pruning. NOT in-process file analyt

Use when a deal closed or a user signed up and the first 30 days need an activation plan: sales→delivery handoff, one verifiable activation event, kickoff, and a 30/60/90 or day-0→14 plan with owners, dates and a measurable exit. NOT reactive ticket triage (that is `customer-supp

Use when working on Cloudflare's edge platform — wrangler.jsonc bindings, choosing between D1/KV/R2/Durable Objects/Queues, deploying a Worker or SPA via Static Assets, or designing around a Workers runtime limit. NOT generic CI/release (that is `deployment`), NOT Next.js framewo

Use to judge a concrete diff, branch, or GitHub PR on its own merits with no rsc-SDD spec/plan chain to key off — the spec-less giving pass behind /code-review: only findings you can defend, one verdict, read-only unless --comment or --fix. NOT the SDD gate keyed to 02-DOCS/wiki/

Use when you land in an unfamiliar or inherited codebase and must get productive fast: a breadth-first map of entry points, request flow, module ownership, hidden side effects (cron, webhooks, workers) and churn hotspots, committed as CODEBASE-MAP.md. NOT a deep audit of one modu

Use when writing a cold email or LinkedIn DM to a stranger and its cadence: first-touch copy under a word ceiling, 4-7 step bump sequences, per-inbox volume and warm-up limits, the compliant opt-out footer. NOT SPF/DKIM/DMARC setup (that is email-deliverability), NOT sourcing the

Use when building or running a persistent two-way community space — Discord, Telegram, Circle: platform choice, structure, onboarding, native→bot→human moderation, rituals, growth loops, health metrics. NOT churn of paying product customers (that is `retention`), NOT broadcast em

Use when an already-named set of rivals is watched on a cadence — pricing, features, positioning and changelog diffed into a maintained tracker plus an append-only, classified change log. NOT sizing the market or choosing who the rivals are (that is `market-research`), NOT one-of

Use when scoping which regulatory frameworks bind a business — SOC 2, ISO 27001, HIPAA, PCI DSS, EU AI Act, DORA, NIS2 — building a control register with owners and evidence, or standing up the cadence that keeps it audit-ready. NOT drafting privacy-policy/ROPA/DPA or ToS text (t

Use when building one shared Compose UI in Kotlin across Android, iOS, and desktop — commonMain @Composables, expect/actual, source-set placement, native interop, multiplatform ViewModel/navigation/Koin. NOT a single-platform native build (that is kotlin-android / swift-ios), and

Use when setting or amending a project's non-negotiables — stack canon, quality bars, conventions, security/a11y floors — as numbered, testable rules later phases obey. First rsc-sdd phase; writes 02-DOCS/wiki/sdd/constitution.md. NOT a feature spec (that is `specify`), NOT the t

Use when a content operation needs a SYSTEM: a dated editorial calendar built top-down from pillars, plus the stage gates, briefs, WIP limits and 1:10 atomization plan that move each slot to publish-ready. NOT writing the pieces (that is `article-writing`), NOT publishing them (t

Use when drafting or reviewing business contracts and clauses in plain language — NDAs, MSAs, SOWs, contractor agreements, risk boilerplate (liability caps, indemnity, force majeure, termination, IP) — or redlining a counterparty's paper. NOT consumer Terms of Service (that is te

Use when self-hosting apps and databases with Coolify on a VPS you own — install, first-admin lockdown, Git-to-deploy (Nixpacks/Dockerfile/compose), managed Postgres/Redis, scheduled S3 backups, domains + auto-SSL. NOT a PaaS someone else runs (that is `railway`), NOT sizing/hard

Use when metering and capping AI or cloud app spend — tokens read from the response `usage` object, priced off a dated rate table, ledgered per user/tenant/feature, with alerts and a hard cap before the bill. NOT cash runway (that is `finance-ops`), NOT cost-per-unit margin (that

Use when turning "I want to teach X" into a defensible course skeleton — measurable outcomes (Bloom + ABCD), assessment that proves each one, sequenced modules, and an outcome×module×assessment matrix — for a workshop, bootcamp, cohort or onboarding track. NOT making one concept

Use when lesson or course content is correct but forgettable and a concept has to LAND: profiles the learner, breaks the blocking false belief, then rebuilds it as epiphany story → named model → grounded analogy → proof → so-what. NOT outcomes, assessment or module order (that is

Fourteen posts of being wrong in production, compressed to checkboxes

Healthy nodes, a quiet network, 300 restarts in three days, and a latency budget measured in milliseconds

Discovery worked. Ping worked. Every TCP connection timed out, and later the tunnel only worked when someone had a terminal open.

Every VM came back. The cluster did not. Declarative systems converge on config, and the datapath isn't config.

A surprising share of AI-in-the-terminal failures aren't the AI. They're zsh, and a version of bash from 2006.

A Claude Code plugin turns standalone project configuration into a namespaced, installable extension that teams and communities can update as one unit.

None of the safety came from the model. It came from six boring habits.

Skills package instructions and references. Subagents run work in a separate context and return results. They solve different problems and can be composed deliberately.

Six hours in, one step left, everything green, and the incident that didn't happen

CLAUDE.md carries persistent project context. Skills load reusable procedures when relevant. Separating stable facts from task-specific workflows keeps both easier to maintain.

Twenty minutes recovering secrets that never existed, and the one sentence from a human that ended it

An API request routing a model's tool call through an approval gate to a remote MCP server

31 config keys, two audits, and why the first one was wrong in both directions

The official MCP Registry stores standardized server metadata rather than package code. Publishers verify a namespace, describe installation or remote access, and submit immutable versions.

Everyone looks at the Dockerfile. The file that actually leaked the key was the project file.

Remote MCP authorization uses established OAuth standards, but secure integration still requires issuer validation, least-privilege scopes, protected token handling, and server-side enforcement.

"Copy it over and switch the reference" is two steps, and the outage lives in the one nobody checks

stdio fits local processes and prototypes. Streamable HTTP fits hosted services and shared integrations. The right choice follows where the capability runs and who must reach it.

The most important rule wasn't about what I could change. It was about what I was allowed to display.

Tools perform operations, resources expose readable context, and prompts provide reusable templates. Choosing the correct primitive makes an MCP server easier to understand and govern.

`crabbox attach` follows the recorded events of an active coordinator run and

`crabbox azure` groups Azure provider setup commands. It currently has a single

`crabbox bench` records and reports local benchmark timing observations. It is a

`crabbox cache` inspects, purges, or warms package and build caches on a

`crabbox capsule` captures, replays, and tracks lightweight failure capsules.

Save the state of a lease, then restore it onto another box or fork it into a

`crabbox claims list` prints the lease claims stored on the current machine. It

`crabbox cleanup` sweeps direct-provider machines and local provider state that

`crabbox code` bridges a Linux lease's `code-server` workspace into the

`crabbox config` inspects and updates user configuration. It has three

`crabbox connect` resolves a lease and opens an interactive SSH session to it.

`crabbox cp` copies files or directories between the host and a Crabbox-owned

`crabbox desktop` drives a visible desktop session on a lease that was warmed

`crabbox doctor` runs a preflight before you commit to a long workflow. It is

`crabbox egress` gives a lease mediated outbound network: a lease-local browser

`crabbox events` prints the broker's event log for a recorded run.

`crabbox heartbeat` refreshes the idle deadline for one owned lease and prints

`crabbox history` lists recorded remote command runs from the broker. Each run is

`crabbox image` holds the trusted-operator controls for provider base images:

`crabbox init` onboards the current repository: it writes the minimal config

Your Personal AI Assistant; easy to install, deploy on your own machine or on the cloud; supports multiple chat apps with easily extensible capabilities.

Agent OS: the agent gets smarter on its own. We just hold the line: the grading command and expected result never make it into the success contract we hand it.…

Curated systems, benchmarks, and papers etc. on memory for LLMs/MLLMs --- long-term context, retrieval, and reasoning.

:memo: Vimlike Modal Text Editor in Rust

CI-native security testing for MCP servers. Attack simulation, schema drift detection, and health scoring before agents depend on them.

Hermes Agent memory plugin/provider for scope-aware recall, SQLite truth, LanceDB semantic search, and hybrid retrieval.

For You Agent——AI 时代的个人随身数字人格。把你的模型、AI 账号、技能、提示词和工作方式，带到每一个 AI 工具里。

A coding agent: give it a prompt and it reads, writes, runs commands, and searches code in a loop until the work is done, using native tool-calling across OpenA…

A secure persistent personal agent server in Rust. One binary, sandboxed execution, multi-provider LLMs, voice, memory, Telegram, WhatsApp, Discord, Teams, and…

Self-evolving agent: grows skill tree from 3.3K-line seed, achieving full system control with 6x less token consumption

DeepSeek Harness Desktop (dsh-desktop). EAC: Embracing All Creation (揽尽万象). Bundled Node.js runtime with full dsh-CLI kernel, one-click startup, 10 built-in UI…

See your agent think. Zero-config observability & governance for 26 AI agent runtimes: Claude Code, Cursor, OpenAI Codex, GitHub Copilot, Gemini CLI, Cline, Ope…

Save 94% on AI coding tokens. Index your codebase, agents search instead of reading files. Works with Claude Code, Codex, Copilot, Cursor, Gemini CLI. Local MCP…

Yet another coding agent harness, lightweight and written in go.

a coding Agent from pi. ∞ providers, sub-agents, hashline edits, and a permission gate

Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting…

🧠 Leon is your open-source personal assistant.

The Station, an open-world multi-agent environment that models a miniature scientific ecosystem.

The Frontend Stack for Agents & Generative UI. React, Angular, Mobile, Slack, and more. Makers of the AG-UI Protocol

VelaTerm = iTerm2 + Codex, The Best Terminal for AI Coding