LLM Mart Basic

Post-install setup for foundry plugin. Run once after installing on a new machine, or after a plugin version upgrade to sync settings and symlinks. Merges statusLine, permissions.allow, enabledPlugins, and advisorModel into ~/.claude/settings.json; symlinks rules and TEAM_PROTOCO

Prepare release communication and check readiness. Main mode: notes with optional flags --changelog, --summary, --migration, --append (incremental: reruns the full pipeline scoped to newly-landed commits, integrating results into existing DRAFT.md/CHANGELOG.md/SUMMARY.md/MIGRATIO

OSS maintainer fast-close workflow for GitHub PRs. Three phases: (1) PR intelligence — reads full thread, linked issues, PR body to synthesize contribution motivation and classify every comment into action items; (2) conflict resolution — checks out PR branch (fork-aware via gh p

Multi-agent code review of GitHub Pull Requests (Python source, documentation (Markdown/RST), and CI/CD config PRs) covering architecture, tests, performance, docs, lint, security, and API design. TRIGGER when: user provides a GitHub PR number (e.g. 42, #42) and asks to review/au

Post-install setup for the oss plugin. Run once after installing on a new machine, or after a plugin version upgrade, to deliver this plugin's rules/*.md into ~/.claude/rules/ as namespaced symlinks. TRIGGER when: user installed or upgraded the oss plugin and its rules are not lo

Investigation-first debugging — gather evidence, form confirmed root-cause hypothesis, hand off to fix mode with diagnosis file. TRIGGER when: user reports a symptom or failing test with Python traceback, or asks to investigate a runtime/CI failure with reproducible evidence; phr

TDD-first feature development — crystallise API as a demo test, drive implementation to pass it, run quality stack and progressive review loop. TRIGGER when: user asks to build new functionality, add a capability, or implement a feature in a Python project; phrases: "add X", "imp

Reproduce-first bug resolution — capture bug in failing regression test, apply minimal fix, run quality stack and review loop. TRIGGER when: user reports a bug, regression, or unexpected behaviour in Python code with a traceback, failing test, or issue number; phrases: "fix this

Analysis-only planning — classify and scope a task without writing code; outputs a structured plan to .plans/active/. TRIGGER when: user wants to understand scope and risks before implementation; phrases: "plan this", "scope out X", "what would it take to Y", "analyse before we s

Test-first refactoring — audit coverage, add characterization tests, apply changes with safety net, run quality stack and review loop. TRIGGER when: user wants to restructure existing Python code without changing behaviour; phrases: "refactor X", "clean up Y", "extract Z", "restr

Multi-agent code review of local Python files, directories, or the current git diff covering architecture, tests, performance, docs, lint, security, and API design. Scope: Python source files in local working tree. Python-file-free targets (pure JS/TS/Go/Rust projects) are out of

Post-install setup for the develop plugin. Run once after installing on a new machine, or after a plugin version upgrade, to deliver this plugin's rules/*.md into ~/.claude/rules/ as namespaced symlinks. TRIGGER when: user installed or upgraded the develop plugin and its rules ar

Systematic ablation study runner. After research:run finds improvements, fortify identifies component candidates from git diff + diary, creates isolated git worktrees per ablation (main repo never modified), runs metric+guard in each worktree, ranks component importance, and opti

Research-supervisor review of program.md — validates experimental methodology (hypothesis clarity, measurement validity, control adequacy, scope, strategy fit), emits APPROVED / NEEDS-REVISION / BLOCKED verdict before expensive run loop.

Generate a Kaggle competition notebook as a Jupytext `# %%` Python script following the user's established ML research style: PTL for DNN training, best-fit tool selection, EDA→Baseline→Train→Inference pipeline with per-stage lens cells, small single-purpose cells each carrying a

Interactive wizard that scans the codebase, proposes a metric/guard/agent config, and writes a program.md run spec. Also runs cProfile on a file path to surface bottlenecks before prompting for optimization goal.

Post-run retrospective: reads .experiments/ JSONL, computes Wilcoxon significance, detects dead iterations, flags suspicious jumps, generates next-hypothesis queue for --hypothesis flag.

Sustained metric-improvement loop with atomic commits, auto-rollback, and experiment logging. Iterates with specialist agents, commits atomically, auto-rolls back on regression. Accepts a program.md file path. Supports --resume, --team, --colab, --codex, --researcher, --architect

Post-install setup for the research plugin. Run once after installing on a new machine, or after a plugin version upgrade, to deliver this plugin's rules/*.md into ~/.claude/rules/ as namespaced symlinks. TRIGGER when: user installed or upgraded the research plugin and its rules

Non-interactive end-to-end pipeline — auto-configure program.md (accept defaults), run judge+refine loop (up to 3 iterations), then run the campaign. Single command from goal to result.

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.

Instrument services with structured logging, Prometheus metrics, and OpenTelemetry tracing. Build Grafana dashboards, write Prometheus alerting rules, run k6 load tests, and plan infrastructure capacity.

Generate, test, validate, explain, and debug OPA (Open Policy Agent) Rego policies and Conftest configurations. Covers deny/warn/violation rules, unit tests, regal linting, conftest fmt, namespace design, input shape analysis, and GitHub Actions integration. Use when asked to "write a policy", "test a rego file", "validate policies", "explain this rego", or "why is my policy not firing".

OpenShift SCC diagnosis and hardening, Route TLS patterns, OpenShift GitOps app delivery, and cluster upgrade validation.

Comprehensive PR review across six dimensions — cost impact, environment drift, ownership gaps, SOC 2 compliance, deprecated API / version hygiene, and rollback feasibility. Each mode inspects the diff and current file state, reports findings with severity, and recommends concrete fixes. Use when preparing a PR for merge, conducting a pre-deployment readiness check, or performing a post-merge risk assessment.

Production-readiness preflight check for a directory, repo, or single file. Auto-detects file types (Kubernetes manifests, Terraform, GitHub Actions workflows, Helm values/charts, Flux Kustomizations/HelmReleases, Dockerfiles, shell scripts) and applies type-specific checks across the whole scope. Returns a per-file summary table and aggregated verdict. Use before deploying, merging, or applying a folder of config. For PR diffs spanning multiple files use /platform-skills:pr-review instead. For deep Helm chart work use /platform-skills:helmchart instead.

Apply product thinking to platform work — DevEx audits, friction analysis, RFC/ADR drafting, incident communication, post-mortems, capacity planning, cost optimisation, and platform health review.

Generate renovate.json covering all dependency file types used in a repo, emit a GitHub Actions workflow that validates renovate.json on every PR, or generate a pre-commit hook for local validation.

Detect and respond to in-container threats at the syscall level using Falco (eBPF-based, CNCF, open-source, no license cost). Covers Falco installation on EKS/GKE with eBPF driver, custom rule authoring, alert routing via Falcosidekick, rule debugging, and bridging Falco runtime signals to Kyverno admission enforcement. Use when asked to "detect privilege escalation in containers", "set up runtime threat detection", "write a Falco rule", "route Falco alerts to Slack", or "debug why my Falco rule is not firing".

Secrets strategy, External Secrets Operator scaffolding, Sealed Secrets seal/rotate/backup, rotation runbooks, and Kubernetes-side secrets audit.

Bootstrap and operate a self-improving agent workspace. Scaffolds .learnings/ and memory/ directories, captures errors and learnings during a session, detects recurring patterns, recalls verified lessons, and promotes stable entries to scoped rule files (.claude/rules/ or ~/.claude/rules/). Also implements the Proactive Agent pillars — WAL protocol, working buffer, SESSION-STATE, daily notes, VBR, VFM scoring, ADL decision logic, heartbeat, and reverse prompting. Use when asked to "remember this lesson", "set up agent memory", "log that error", "what did we learn about X", "promote learnings", "revoke that rule", "capture session state", or "enable proactive mode".

Scaffold a multi-agent AI setup for any repo. Scans the codebase, interviews the developer, generates agent configs for whichever AI tools the repo uses (Copilot, Claude Code, Cursor, Codex, Windsurf). Use when asked to "set up agents", "scaffold Copilot agents", or "create an AGENTS.md".

Secure the software supply chain from source to running container. Covers Cosign keyless image signing (Sigstore/Rekor), SBOM generation and attestation (Syft), vulnerability scanning with severity gates (Trivy/Grype), SLSA Level 2 provenance, and Kyverno/OPA admission enforcement. All open-source, no license cost. Use when asked to "sign my image", "generate an SBOM", "scan for CVEs", "attest build provenance", "enforce image signatures in Kubernetes", or "implement SLSA".

Runs through the full Terraform validation pipeline — fmt, validate, tflint, security scan — and reviews a module or plan for blast radius, IAM risk, and state impact.

Triages a PR comment — from a bot (Copilot, CI) or a human reviewer. Routes to the `triage_helper.py` helper for identity checks, thread snapshotting, isolated-worktree fixes, and publish/reply/resolve mechanics; you classify the finding and apply a justified fix. `--dry-run` is fully read-only (investigation and a printed plan, zero mutations). `--no-resolve` runs the full fix/reply workflow but never resolves a thread. Run from inside the repo.

Scan container images, filesystems, git repos, and existing SBOMs for CVEs, secrets, and license violations using Trivy. Covers local CLI, CI severity gates with SARIF upload, and continuous monitoring via Trivy Operator (Flux HelmRelease). Use when asked to "scan my image", "check for CVEs", "scan this repo for secrets", "scan an SBOM", or "set up continuous cluster vulnerability monitoring". IaC misconfig → /platform-skills:checkov. Admission posture → /platform-skills:kyverno. Image signing/SBOM generation → /platform-skills:supply-chain.

Audit GitHub Actions workflows, composite actions, Dependabot configs, and pre-commit configs for security findings using zizmor — template injection, credential persistence, unpinned uses, over-broad permissions, impostor commits. Covers local CLI, auto-fix, zizmor.yml policy, severity-based CI gates, SARIF upload, and pre-commit. Use when asked to "audit my workflows", "run zizmor", "is this workflow safe", "check for template injection", "pin my actions", or "set up a zizmor CI gate". Workflow syntax and shell errors → /platform-skills:github-actions (actionlint). IaC misconfig → /platform-skills:checkov. Image and dependency CVEs → /platform-skills:trivy. Keeping SHA pins fresh → /platform-skills:renovate.

반복 작업을 `/이름` 으로 호출. 파일명 = 커맨드 이름(`fix-issue.md` → `/fix-issue`).

이슈 #$ARGUMENTS 를 처리한다(이슈 우선 워크플로):

AGENTS.md 생태계(rules·memory·agents·skills·commands·workflows)의 연결 구조를

이슈/기획서 기준 SDLC 한 사이클(이슈→개발→테스트→검증→PR/MR)을 사람 개입 없이 자동 실행.

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…

An AI Agent that lives in your pocket. Local-first and privacy focused.

Unofficial skill that teaches coding agents to build with TypeSafe AI's Jev: typed decisions, calibrated confidence, and prior art from 150+ community projects.

Adaptive Test-time Learning and Autonomous Specialization

Prediction-market trading engine — Wang Transform pricing on 291K+ contracts; paper-traded across Kalshi · Polymarket · Solana DFlow (Jito bundles) · 633 tests

Knowledge Management for Humans and Agents

Open-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…

DeepAgent Code: AI coding agent with persistent memory and control plane

Awesome Jev — evidence-graded index of TypeSafe System One: SDKs, MCP tools, agents, apps and open models. 20 languages, rebuilt every 2 hours.

CLI for Telegram — agent-friendly, daemon-based, with webhook event push.

AI deep-research agent that turns any question into a cited report: plans searches, reads real sources, verifies evidence. Self-hosted, multi-provider, Docker-r…

Event-stream AI Agent framework for building your persona bot 🍊

Give 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…

Local Emperor-style AI agent with Vue WebUI, multi-provider LLMs, streaming chat, tools, skills, memory, and token telemetry.

Open-source AI reverse-engineering agent platform and MCP server for Ghidra, Frida, x64dbg and Rizin — automated PE/APK/binary analysis, CTF and malware researc…

"Never send a human to do a machine's job" - Open Source AI hacking agent

Prismer Cloud

My Personal Blog (Robotics)

Tau Coding Agent - like Pi, but twice as much

Open-source alternative to OpenAI Dots: self-hosted AI chat, tools, approvals, connectors, and computer tasks.