LLM Mart Basic

Use when the user asks for a weekly sentiment report, weekly social summary, or how mentions looked this week. Not for continuous monitoring or alerting.

Use when defining product strategy, starting or redirecting a product, or repairing stale STRATEGY.md. Not for project plans, roadmaps, scheduling, or work needing no interview.

Use when asked to find distribution opportunities for a template, tool, or artifact. Not for content creation or campaign management.

Use when a user asks for a product spec with invariants, a tech spec, or a PRD. Modes: product (default), technical, requirements. Not for task breakdown: use plan.

Use when asked to design or change a public API, route, CLI flag, or module boundary. Not for remote, credential, publish, deploy, or irreversible changes.

Use when non-trivial code needs a design, architecture needs improving, or one module needs targeted interface narrowing, seams, or testability. Not for diagrams, deploy, or irreversible changes.

Use when asked to run AST-based structural search, lint, or rewrite of code when regex is too fragile. Not for remote, credential, publish, deploy, or irreversible changes.

Use when bloated code needs clean re-derivation, or the user says "this module is bloated" or "break it and rebuild". Not for untracked data or changes without VCS rollback.

Use when asked to run /clean-clean-cut to cut accumulated records and residue. Not for untracked or non-VCS changes, or branch/worktree cleanup: use git-cleanup.

Use when the user asks to simplify, clean, or refine code. Not for new abstractions or whole-codebase refactors.

Use when asked to implement under non-negotiable constraints: performance budgets, platform limits, legal or API rules. Not for remote, credential, publish, deploy, or irreversible changes.

Use when crossing a public API boundary, guarding complex invariants, or hardening untrusted input or integration seams. Not for remote or irreversible changes.

Use when asked to remove old code, migrate consumers, or decide whether to maintain or sunset a system. Not for untracked data or changes without VCS rollback.

Use when dependency upgrades need batching for CVEs, a major release, forced compatibility, a scheduled or vulnerability-triggered sweep. Not for PR queue triage: use github-backlog-triage.

Use when asked to design a module interface, seam, or testable boundary. Not for UI direction picking: use design. No source or remote-system changes.

Use when the user says deslop, debloat, tidy, simplify, clean a diff, or deslop branch diff, or remove dead code or config. Not for remote, credential, publish, deploy, or irreversible changes.

Use when code mixes units, fixed-point precisions, scaling factors, rates, prices, shares, or conversions. Not for type-level unit modeling: use type-driven.

Use when reconciling an API endpoint's generated OpenAPI schema and declared response types with its actual runtime response. Not for general API documentation: use docs-and-adrs.

Use when replacing a greenfield attempt with a clean pad of verified requirements. Not for rebuilding from primitives: use from-first-principle. Requires a committed, VCS-recoverable attempt.

Use when dead, duplicate, superseded, or generated residue must leave more than one artifact class of a repo or subsystem, preserving behavior. Not for one enumerated record set: use clean-clean-cut.

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.

Periodic multi-reviewer sweep of the whole codebase — surfaces a triaged checkpoint report.

Sanctioned lane for non-behavioral work — docs-only edits, dependency bumps, reverts. Type-scaled gates; no TDD demanded of prose.

{{SKILL_ENTRY:post-merge-cleanup}}

Show the codeArbiter command catalog — the public command list and what each routes to.

{{SKILL_ENTRY:commit-gate}}

Stop everything and surface a rule conflict — persona vs. docs vs. code. Present both sides and the conflict-hierarchy level; the user resolves. No silent reconciliation.

{{SKILL_ENTRY:context-check}}

{{SKILL_ENTRY:context-creation}}

{{SKILL_ENTRY:debug}}

{{SKILL_ENTRY:decompose}}

Verify the active host install, package, command ownership, enforcement{{IF:pi}}, wrapper self-test, and active-dispatch coverage gap{{ELSE}}, and harmless live-fire probe{{END}}. Read-only.

Start a feature: brainstorm a spec, get it approved, then drive it test-first through the pipeline. The one entry to implementation.

Fix a confirmed bug: a failing regression test first, then a minimal fix, then the rest of the tdd gates.

Opt this repo into codeArbiter — scaffold the root-level .codearbiter/ state store.

Read-only 3-metric governance glance — override rate, small-lane rate, sprint low-confidence ratio — each with a trend arrow vs. the prior 20-commit window.

Sanctioned, logged bypass of a gate or hard rule — one audit line, then proceed.

{{SKILL_ENTRY:finishing-a-development-branch}}

Zero-onboarding, read-only dry-run of the reviewer fleet against the current uncommitted diff. Predicts reviewers, runs the state-free secret scan, writes nothing.

Trim transcript clutter to extend session lifetime — analyze, prune a copy, or toggle the after-each-turn service. Dry-run by default; gains land at resume/compaction, not the current turn.

{{SKILL_ENTRY:decision-variance}}

Atom Agent, Open-Source Governed AI Agent Platform for Self-Hosted Automation

The agent engineering intelligence harness, optimized tools, memory system, subagents and mixture of models packages ⚚

Sesori iOS/Android app and the Sesori Bridge CLI — drive Claude, Codex, OpenCode, Cursor, Pi, OMP, Hermes coding sessions from your phone

🧠 RepoBrain (formerly Antigravity) — Give your repo a brain. ChatGPT for your codebase: works in Claude Code, Cursor, Codex, Windsurf & more.

Use ChatGPT (Codex), Claude, and Grok (X Premium) subscriptions as DeepSeek Harness LLM providers — OAuth login in the web UI, no API keys

Latitude is the open-source AI monitoring platform.

Open-source AI browser agent for Chrome and Firefox (monorepo) 🧠

Official Model Studio CLI（阿里云百炼 CLI）built for AI Agent frameworks, exposing models, search, multimodal, and workflow capabilities as structured tool calls.

Curated DeepSeek Harness (DSH) plugins, extensions, tools, skills, clients, runtimes, integrations, and verified references — English and Chinese.

Turn papers, code, and docs into presentation-ready, natively editable PPTX in Codex / Claude Code. Native charts and equations, speaker notes, click-build anim…

Grix : Work with agents like talking to people.

Local First Ai Agent. Optimized for Local Ai models. Long context window. Proper tools callings. Runs privately on your device.

Model Context Protocol server that integrates AgentQL's data extraction capabilities.

AI that ships your tickets.

Metadata-driven CLI for AI Agent Bots — 48 operations across 7 domains, structured JSON envelope I/O, zero interactive prompts.

An open-source, extensible, self-hosted agent workspace with multi-runtime support for Codex, Claude Code, and more, plus reusable local apps for custom interfa…

Open-source Windows desktop client and GUI for DeepSeek Harness — zero-setup installer with Codex, plugins, skills, SSH, mobile remote access, and 11 skins.

The open-source AI workbench for scientific research

DeepSeek-native AI coding agent for your terminal. Engineered around prefix-cache stability — leave it running.

A Fully free agentic browser driver for AI , few tools, full control, real stealth, top-tier token efficiency.