LLM Mart Basic

The credo work-item model, where the FOLDER an item file lives in is the single source of truth for its status, gated by a hard Definition of Done. Use whenever you create, update, or track a work item; whenever you decide whether something is "done" and may move to 2_done/; when

The credo procedure for migrating an existing repo into the .credo/ structure, without any loss risk. Use when migrating a repo into .credo/, onboarding a legacy project into credo, or turning scattered process docs (requirements logs, handoffs, progress notes, audits, plans, spe

Delegate work to subagents safely and efficiently - decide how many subagents to run, keep parallel tracks on disjoint files, monitor them without flooding your context, inherit security to every subagent, and use return-and-resume so a subagent can ask a question and continue wi

Use when the user wants to thoroughly investigate, vet, review, or security-scan a pull request before deciding how to handle it - especially PRs from external or unknown contributors. Runs a parallel multi-agent investigation (technical, security, value/fit, contributor reputati

Capture a user requirement, decision, approval, or constraint word-for-word into an append-only dated log so it survives context compaction and can never be trimmed, softened, or reinterpreted. Use whenever the user states or approves a requirement, gives a GO, sets a constraint,

Clear this session's credo role, returning to the default of NO role (the agent does everything). Use ONLY when the user actually drops the role, for example "clear the role", "no role", "forget the role", "you are no longer the plan/task agent", "back to doing everything", "roll

Per-repo credo special rules (project-local grants) that live in the target repo's `.credo/RULES.md` and travel with the repo. Load and honor these at the start of every session and inside every subagent, so a project can widen credo's autonomy for itself - for example "in this d

Hard safety rules that must travel with the project: filesystem-protection and no-autonomous-installs. Use before any delete, rm, shred, unlink, find -delete, mkfs, dd, or wipefs, before removing local files, and before any install (pip, npm, apt, system or global tools). These a

Do WRITING pre-work for a clarify item that is blocked by a knowledge gap - a missing measurement, a mockup, or a feasibility proof - WITHOUT touching production code, without git, and without disturbing the task / build agent. Use when a 1_clarify item cannot be answered by a pr

The credo behavior for a session running in ACTIVE mode - intensive live collaboration with the user present at the keyboard. Load this when the session-mode inject line says "Load skill session-active", right after the /credo:session-active command, or whenever you are collabora

The credo behavior for a session running in AUTONOMOUS mode - work approved GO items unattended while the user is away, hook-enforced self-scheduled keep-alive, budget caps always on. Load this the MOMENT the user hands off full-autonomy, unattended, or AFK work - EVEN BEFORE the

The credo behavior for a session running in PASSIVE mode - you carry most of the work alongside and the user is available only for clarifications, with no keep-alive. Load this when the session-mode inject line says "Load skill session-passive", right after the /credo:session-pas

Turn a recurring in-session workflow into a reusable Claude Code skill. Load this the moment you notice you have run the SAME multi-step sequence (same ordered steps or commands, small variation allowed) about three times in the current session, or when open candidates are waitin

Visual verification as the Definition of Done for any change with a runtime surface (a rendered page, a UI, a live view). Use whenever you are about to call a UI or frontend change done, before moving an item to done, whenever an item is marked ui: true, or when someone asks "doe

Reach and act on Windows-side services, processes, launchers, and logs when the agent runs inside WSL. Use whenever a service seems unreachable from WSL (a localhost curl fails), when you need to start/stop or inspect a Windows-side process or .ps1 launcher, read Windows logs, hi

Author and edit Skmtc generators — packages that project an OpenAPI domain model into application code. Method: clone the nearest stock generator, then apply the engine rules imitation can't teach. Assumes zero prior Skmtc knowledge. Use when asked to "write a skmtc generator", "

The TypeScript target-language layer for Skmtc generators (@skmtc/lang-typescript): projection base factories, TsSnippet, the three register shapes, identifier kinds and the type-only import machinery, composition helpers, sanitization, TsFile render rules. Use ALONGSIDE skmtc-ge

The model-generator shape for Skmtc: one definition per component schema, built by copying the shipped SKELETON package and filling its SLOT markers with the target library's syntax. Covers the edge cases every model generator must survive — refs, recursion, optional vs nullable,

The operation-generator shape for Skmtc: one definition per (path, method), for any output family — client hooks, SDK methods, forms, route stubs, docs. Output varies wildly; the DECOMPOSITION of the operation and the peer-consumption rules do not. Core teaching: every schema tha

Use the Skmtc CLI to scaffold projects, install or clone generators from JSR, configure schema sources and enrichments, and produce code artifacts from an OpenAPI v3 or GraphQL SDL schema. Teaches the workspace mental model (`<root>/.skmtc/<project>/`, client.json, bundle, manife

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.

Assemble the governance record for a range — commits, overrides, ADRs, sprint auto-decisions, open questions, checkpoint findings — into one dated audit packet. Read-only.

Lightweight Q&A about the project — answer from context and return, no routing, no state change.

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.

Clean up an already-merged local branch after proving containment. Confirm each discard and preserve unique work.

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

Create a verified local Git commit when committing changes is requested. Not for explaining commit history, drafting a message only, or postponing a commit. Applies every commit gate and never implies a push or PR.

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.

Audit stale provenance-tracked docs on request. Report first; re-scout or re-baseline only for selected docs.

Build project context from an existing codebase through isolated scouts, resolve gaps, and preserve initialization gates.

Investigate an unexplained defect or unexpected behavior without changing application code. Use for root-cause diagnosis and an evidence-backed handoff. A no-action close records a board note. Not for implementing a known fix, new features, or explanation-only questions.

Develop greenfield project context through a layered interview, preserve decisions, and initialize only after the required gates.

Verify the active host install, package, command ownership, enforcement, and harmless live-fire probe. 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.

Open a PR or finish branch disposition; route CI watching and post-merge cleanup to their owners. Merge and discard need explicit authority.

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.

Okou connects to the tools your team already uses and does the work — across marketing, sales, engineering, and operations, under your control.

An open-source Digital Worker platform for reliable execution, continuous co-evolution, and building Enterprise AI assets.

A curated list of AI Agent evolution, memory systems, multi-agent architectures, and self-improvement projects. | evomap.ai

A governance harness for AI coding.

DeepSeek Harness 手机版：可直接安装的 Android APK，AI 免 Root 操作手机（Shizuku/root 可选），文件编辑只需所有文件访问权限，前台保活 + AI 通知

Local-first, governed AI agent runtime for Python — embed it in your app, or run it as a CLI or ACP server. Permissions, MCP, memory and audit replay built in.

Orbi — the factory that builds and operates AI software factories. GitHub Issues in, releases and runnable system out

Open-source AI agent harness in native Rust — GUI, CLI, headless, and webapp from one binary. Multi-provider, MCP, skills, plugins, agent teams.

The SDK for browser agents. Interact, search, extract, and fetch any site reliably across the web

Agent-native shopping for extreme value: verifiable same-product price evidence, checkout, orders, delivery, and after-sales.

The extensible power-user platform for Google Antigravity. Adds a native In-App Browser, animated Desktop Pets, revamped Gemini UI, and custom BYOK Gemini Pro k…

Open-source, single-binary, self-hosted AI agent — your models and data stay on your machine. A coding agent on par with Claude Code and a personal assistant li…

Your pocket agent. Local-first AI agents on iOS and Android — real workspaces, tool execution with approvals, and your choice of model (DSH · Claude Code · Code…

Bridge between QQ (SnowLuma OneBot v11) and DeepSeek Harness agents: social simulation, safe MCP tools, slang learning and more.

A 7×6 framework for agent architecture. 28 patterns, each placed at a coordinate, runnable Python code with verified engineering slices from Claude Code, Aider,…

针对 AI 自动化渗透 Agent 的新一代反制蜜罐，通过反向代理将API密饵载入真实业务、反向提示词注入等方式反制自动化渗透 Agent，实现多款主流通用Agent的反制上线控制。

Open-source, local-first AI agent for coding and real work. BYOK models, MCP, skills, plugins, workflows, and private knowledge bases.

A free AI-agent toolbox for Android, 一站式安卓AI Agent工具箱

Google Workspace CLI — one command-line tool for Drive, Gmail, Calendar, Sheets, Docs, Chat, Admin, and more. Dynamically built from Google Discovery Service. I…

Independent, unofficial CLI to edit CapCut and JianYing (剪映) projects — subtitles, timing, speed, volume, templates, cut long-form to shorts. No API needed, rea…