LLM Mart Basic

Phase-1 Layer-0 of the comic-author suite — turn ANY raw idea / a locked video skeleton / an audience note into ONE schema-valid intent_spec node that fixes the logline (an editorial climax), the tagline, and the named DUAL-IDENTITY design constraint the whole comic optimizes aga

Phase-1 (S9, the FINAL comic-author step) — assemble the LOCKED storyboard + locked per-panel blueprints into ONE schema-valid `comic.json` (the comic-ir/1.0 contract boundary handed to comic-director / run_comic.py). Project the page_order + each panel's condition{} + render fie

Phase-1 Layer-2 of a comic — turn a LOCKED skeleton (intent_spec + the pre-locked beat/shot list) into an approved outline_spec: a 6-column beat table that binds every ARIS capability to a STORY COST, plus the continuity-motif contract the storyboard layer will be held to. NOT fr

Phase-1 step of comic-author — the DETERMINISTIC compiler (搬运工原則) that turns ONE gate-approved panel_spec + its status:locked blueprint into the EXACT fixed-section bake string for the spiral engine via the shipped scripts/build_prompt.py (+ the canonical scripts/_validate.py vet

Phase-1 comic-author step — turn a LOCKED, user-approved outline into the page-first storyboard that IS the authoring source of truth: a fixed page order BEFORE any prose, the MOTIF STATE TABLE (the master per-panel continuity ledger), a fixed 9-field per-panel spec, and one dedu

Phase-1 (S2) of the comic-author suite — compile the project's ART_BIBLE.md into an EXECUTABLE convergence target, not aesthetic prose. The bible is the ONE visual dialect read verbatim into every bake prompt AND into every visual reviewer's rubric (`style_consistency`/`identity_

Generate a publication-grade method / architecture / pipeline / workflow figure (a paper or README 'Figure 1') as an AUDITABLE object, not a one-shot prompt. A deterministic JSON blueprint LOCKS the content; an image model (gpt-image-2, baked by the agent via mcp__codex__codex —

End-to-end Pipeline A in ONE slash-command — turn a fuzzy story idea into a cross-model-audited, image-based movie + a clickable viewer. Chains comic-author (Phase 1 — intent→style→outline draft→provisional storyboard→assets→final locks→blueprints→prompts→comic.json) → the zero-c

Analyze architecture for consistency between ADRs and AD, completeness, and quality issues. Use when validating generated or refined architecture artifacts, before feature development, during architecture review, or periodically to detect drift.

Generate a full Architecture Description (AD.md) from accepted ADRs using multi-agent DAG orchestration. Use when accepted ADRs exist and you need to produce or update unified architecture documentation.

Review, accept, reject, or defer Change Decision Records (ChDRs) discovered by change-init. Interactive one-ChDR-at-a-time workflow that validates inferred decisions against their git/issue evidence before promotion to project memory.

Mine git history for Change Decision Records (ChDRs) by detecting commit messages that link to issue trackers, clustering the commits into change stories, and inferring the decisions behind them. Use when bootstrapping project memory from an existing repo's history (brownfield),

Promote accepted Change Decision Records (ChDRs) from drafts to project memory at .adlc/memory/chdr/, write OKF-style frontmatter, and regenerate the boot-facing .adlc/memory/chdr.md index that team-boot injects at session start. Use after /change-clarify has accepted ChDRs.

Analyze evaluation results and close the loop. Specification failures create local CDRs to fix agent rules; generalization failures go to evaluator backlog.

Refine, cluster, and accept draft criteria into the published goldset. Isolates 20% holdout split and publishes goldset.md + goldset.json.

Generate executable graders and configs from goldset. Generates Python graders / metrics and auto-runs unit tests to verify grader correctness.

Initialize evals/{system}/ directory structure for evaluation system following EDD principles (Standalone). Choose PromptFoo or DeepEval based on tech stack, generate security baseline.

Extract eval criteria from product specs and production failure traces (bottom-up error analysis). Writes proposed criteria to .adlc/drafts/evals/.

Run evaluations and validate evaluator quality (SLA compliance, TPR/TNR, statistical accuracy). Executes PromptFoo or pytest DeepEval.

Read-only analysis of PDR↔PRD consistency, PDR quality, cross-PDR conflicts, and staleness. Outputs a structured markdown report with severity-assigned findings. Use after /product-implement or periodically to detect drift.

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.

{{SKILL_ENTRY:refactor}}

{{SKILL_ENTRY:release}}

Review a diff with the reviewer fleet, funneled to one triaged verdict. Targets the current working diff, a path, or an inbound GitHub PR.

Exploratory spike on a throwaway branch — answer a named question with disposable code. Never merges; exits to a findings note or {{CMD:feature}}.

Autonomous sprint — one interactive spec gate, then plan-to-PR execution with every auto-decision SMARTS-scored and logged. Hard gates remain true stops.

Daily repo hygiene — review the day's repo state, then perform the cleanups under per-action confirmation. Fast-forward only, never destructive without a yes.

Show the project's current state at a glance — stage, open tasks, open questions, overrides since the last checkpoint, current branch. Read-only.

Wire codeArbiter's statusline into ~/.claude/settings.json, or remove it.

The sanctioned task-board mutator — add a queued task, start one (flips to in-progress and stamps the date, minting a dotted ID on pick-up), or mark an in-progress task done. The only blessed write to open-tasks.md.

{{SKILL_ENTRY:security-architecture}}

{{SKILL_ENTRY:tribunal}}

Watch a PR's CI to completion — diagnose on red, notify and offer the merge on green. Never auto-merges.

Copy a file OUT of a running sandbox box to the host — host-initiated egress only (docker cp). The reverse, a host→container bind, is impossible by construction.

Tear down a sandbox box — remove its container and named volume. --keep-volume leaves the volume; with no id, prune reclaims any leaked ca.sandbox=1-labeled object. Cached images are retained.

Run a single command inside a running sandbox box and capture a JSON result — exitCode, separate stdout/stderr, and a truncated flag past the byte cap. The scriptable exec seam.

Open an interactive shell inside a running sandbox box at /work/repo. Read-only root, non-root user, no host-FS access — explore the untrusted code interactively, then exit.

Pull an untrusted repo into an ephemeral, host-FS-isolated Docker container — clone into a named volume, build a dep-cached image, run under structural isolation. Network defaults to offline. Requires Docker and nixpacks.

Vet a new or changed third-party dependency for license, provenance, and supply-chain risk before any install runs.

Inspect ADR health read-only; optionally select one ADR with --adr N.

Record user-decided ADRs or inspect their health read-only. Preserve attribution and acceptance evidence.

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.