LLM Mart Basic
@llm-mart · Joined Jun 2026
Apply when repeated fixes sharing an assumption fail. State the assumption and choose an observation that can challenge it before trying another fix that depends on it.
Apply when wiring validation, error handling, or framework adapters. Concentrate guards at system boundaries (CLI, config, network, external APIs); trust internal types and keep business logic in pure functions.
Apply to any non-trivial work, not just bulk work: edits, migrations, analyses, checks. Build the tool that does it or proves it (codemod, script, generator, or a skill your subagents follow) instead of working by hand. The tool is the artifact a reviewer can rerun.
Apply when you catch yourself writing the same instruction a second time, or notice a recurring correction. Encode the rule as a lint, metadata flag, runtime check, or script instead of more text.
Apply when facing a novel UI interaction or architectural decision with no precedent in the codebase. Build 2-3 competing prototypes and compare side by side before committing.
Apply when product, UX, or feature-scope tradeoffs come up. Choose user delight over implementation convenience; ship fewer polished features over more rough ones.
Apply when debugging. Trace each symptom to its root cause and fix it there; reproduce first, ask why until you reach it, resist nil-check guards that silence crashes.
Apply before writing logic: choosing core types and data structures, sequencing scaffold-vs-feature work, asking what concurrent actors share. Get the data structures right so downstream code becomes obvious.
Apply when context is filling up: large outputs, long files, repeated reads, fan-out planning. Route bulk to subagents; keep summaries in the main thread, not raw payloads.
Apply when refactoring, evaluating diff size, or tempted to add abstractions, layers, or signal threading. Bias toward deletion and the smallest change that solves the problem.
Apply when designing commands, lifecycle steps, or processing loops that run amid crashes, restarts, and retries. Converge to the same end state regardless of partial prior runs.
Apply when introducing a new internal API while old callers still exist. Migrate callers and delete the old API in the same wave instead of preserving compatibility layers.
Apply when reviewing or shaping code that's hard to trace. Count layers between question and answer, and hidden state in the reader's head; collapse one-caller wrappers and shrink mutable scope.
Apply when writing stateful logic, or when code branches a lot or repeats a shape assumption across files. Encode the domain in a structure instead of scattered conditionals.
Apply when tempted to ask 'should I do X?' on reversible work. Proceed, present the result, let the human course-correct after the fact; reserve confirmation for irreversible actions.
Apply during planned rewrites and migrations with explicit phase boundaries. Converge on the target architecture; don't preserve smooth intermediate states with throwaway compatibility code.
Apply after completing a task, before declaring done. Verify against the real artifact (run the feature, read the actual value, inspect the diff), not a proxy, self-report, or 'it compiles.'
Apply when integrating a new requirement into an existing design. Redesign as if the requirement had been a foundational assumption from day one, instead of bolting it on.
Apply when concurrent actors might write to the same file, branch, key, or state object. Eliminate the sharing first; serialize structurally only when one shared writer is a real invariant.
Apply to multi-step work (sweeps, migrations, runs of similar edits) and to how you stack commits and PRs. Break work into small units that each end in a verifiable state, check each before the next, and order delivery so the sequence proves itself to a reviewer.
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.
Use MCP Inspector to connect to local or remote servers, inspect capabilities, call tools, read resources, test prompts, and diagnose failures before release.
/entry-points
Entry points
Identifies state-changing entry points in smart contracts
/scan-apk
Scan apk
Scans Android APKs for Firebase security misconfigurations
/git-cleanup
Git cleanup
Safely analyzes and cleans up local git branches and worktrees, categorizing them as merged, squash-merged, superseded, or active work before deleting anything.
/audit
Audit
Audit a file, directory, or whole repo for insecure default configuration: fallback secrets, default credentials, fail-open switches, weak crypto, permissive access, debug leakage. Parallel sweeps collect candidates, then a refuting verifier traces each one to the security decision it reaches before it is reported.
/semgrep-rule
Semgrep rule
Creates Semgrep rules with test-first methodology
/README
README
This folder gathers the project's 9 slash commands in a single place, plus the sub-procedure files the [Sub-procedure Locations](#sub-procedure-locations) table rosters. **The harness lists every `.md` here as invocable regardless of `user-invocable: false`** (this README is itse
/wiki-discover
Wiki discover
Discover unexpected connections in the LLM Wiki (Memex serendipity).
/wiki-export
Wiki export
Export wiki to merged files for Claude.ai Project Knowledge.
/wiki-graph
Wiki graph
Build the LLM Wiki knowledge graph.
/wiki-ingest
Wiki ingest
Ingest a source document into the LLM Wiki.
/wiki-lint-theme-mapping
Wiki lint theme mapping
Not a slash command — a sub-procedure of [`/wiki-lint`](wiki-lint.md), reached from `contradiction theme --fix`. Invoking it directly runs nothing.
/wiki-lint
Wiki lint
Health-check the LLM Wiki for issues.
/wiki-news
Wiki news
Search for latest news related to the LLM Wiki's key topics.
/wiki-query
Wiki query
Query the LLM Wiki and synthesize an answer.
/wiki-timeline
Wiki timeline
Generate a chronological timeline for an entity or concept in the LLM Wiki.
/wiki-trail
Wiki trail
Create, follow, or list associative trails in the LLM Wiki (Memex trail-blazing).
/burn-rate
Burn rate
Compute the recent 7-day spend trend (burn rate) from daily sessions and per-session cost.
/cost-today
Cost today
Quick total cost plus a per-model one-liner from the dashboard pricing engine.
/top-spenders
Top spenders
List the top N most expensive Claude Code sessions by inline cost.
/audit-config
Audit config
Quick Claude Code config audit — counts per surface (user vs project) and totals.
PiG (Pi in Go) is a faithful Go port of upstream Pi, the TypeScript codebase behind the Pi coding agent. It is a parity-bound translation, not a rewrite: upstre…
0 views 0 likesAn AI Agent that lives in your pocket. Local-first and privacy focused.
1 views 0 likesUnofficial skill that teaches coding agents to build with TypeSafe AI's Jev: typed decisions, calibrated confidence, and prior art from 150+ community projects.
5 views 0 likesAdaptive Test-time Learning and Autonomous Specialization
3 views 0 likesPrediction-market trading engine — Wang Transform pricing on 291K+ contracts; paper-traded across Kalshi · Polymarket · Solana DFlow (Jito bundles) · 633 tests
2 views 0 likesKnowledge Management for Humans and Agents
4 views 0 likesOpen-source Claude Cowork / Codex / WorkBuddy alternative — a local-first AI office agent that turns one request into real PPTX, DOCX, XLSX and HTML files. Runs…
4 views 0 likesDeepAgent Code: AI coding agent with persistent memory and control plane
3 views 0 likesAwesome Jev — evidence-graded index of TypeSafe System One: SDKs, MCP tools, agents, apps and open models. 20 languages, rebuilt every 2 hours.
4 views 0 likesCLI for Telegram — agent-friendly, daemon-based, with webhook event push.
4 views 0 likesAI deep-research agent that turns any question into a cited report: plans searches, reads real sources, verifies evidence. Self-hosted, multi-provider, Docker-r…
2 views 0 likesEvent-stream AI Agent framework for building your persona bot 🍊
0 views 0 likesGive the agent a machine. Just not yours. Each AI coding agent gets its own isolated machine with root, Docker, and systemd - active defense detects and stops t…
0 views 0 likesLocal Emperor-style AI agent with Vue WebUI, multi-provider LLMs, streaming chat, tools, skills, memory, and token telemetry.
0 views 0 likesOpen-source AI reverse-engineering agent platform and MCP server for Ghidra, Frida, x64dbg and Rizin — automated PE/APK/binary analysis, CTF and malware researc…
0 views 0 likes"Never send a human to do a machine's job" - Open Source AI hacking agent
0 views 0 likesPrismer Cloud
0 views 0 likesMy Personal Blog (Robotics)
0 views 0 likes