LLM Mart Basic

Research State of the Art (SOTA) literature for an Artificial Intelligence / Machine Learning (AI/ML) topic, method, or architecture. Finds relevant papers, builds a comparison table, recommends the best implementation strategy for the current codebase, and optionally produces a

Paper-vs-code consistency audit. After research:scientist implements a method from a paper, verify the implementation matches paper claims across five dimensions — formula matching [F], hyperparameter parity [H], eval protocol [E], notation consistency [N], and citation chain [C]

Read local codemap telemetry logs and produce a diagnostic/usage report. Supports date filtering, session filtering, and optional anonymization before sharing. TRIGGER when: analyse recent codemap usage, debug query patterns, investigate errors, or prepare a shareable anonymized

Adapter over `codemap-py integrate` — audit, plan, source-wire, locally sync, and demonstrate the codemap-py integration with its supported consumers. Trigger with `/codemap-py:integration audit|plan|apply|sync|demo [--runtime {claude,codex,both}] ...`. Default (no args) is `audi

Query Codemap's Python structural index for dependencies, callers, paths, symbols, blast radius, test impact, mocks, fixtures, subprocesses, and static gaps. Trigger for "what depends on", "who calls", "imports of", "dependency graph", or "blast radius". Skip for renames, text se

Atomic rename of Python symbols or modules via the structural index — static callers, import sites, __all__ re-exports, Sphinx cross-refs; optional deprecated alias (--deprecate) or hard-delete (--remove-if-no-callers). TRIGGER: "rename X to Y" (function/class/method/module), "mo

Scan the Python codebase and build a structural JSON index (import graph + blast-radius metrics). TRIGGER when: user asks to build, refresh, or rebuild the codemap index; user mentions stale index, missing symbols, or re-indexing after significant project changes; phrases: "build

Identify which tests need rerunning after a code change — traces static call graph (function-level) or import graph (module-level) to find affected test files, then emits a ready-to-run pytest command. TRIGGER when: user asks which tests are affected by a change; phrases: "which

Telemetry report: `$codemap-py:debrief-coding [flags]`; skip integration/index/query.

Codemap integration: audit|plan|apply|sync|demo; skip query/index rebuilds.

Query Codemap.

`$codemap-py:rename-refs`: rename Python names; skip non-Python/unbuilt/local/grep/split/pkg-dir.

`$codemap-py:scan-codebase [flags]` only: Python index; never auto-invoke; skip query/integration.

`$codemap-py:test-impact <qname> [--no-mocks]`: affected tests; skip caller/dependency query/exec.

Ask Codex a read-only question with explicit model, effort, budget, and compact results.

Request cancellation of a running detached Codex bridge job.

Ask Codex for one bounded write-capable change with compact results.

Read a completed detached Codex bridge job's compact result.

Request a read-only adversarial Codex review with explicit model, effort, budget, and compact findings.

Configure, authenticate, repair, and verify the Claude Code to Codex Bridge; safe stages run by default and sensitive stages require separate approval.

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.

One-line reliability verdict (OK / DEGRADED / FAILING) for Claude Code usage

Print a quick SLO snapshot — completion rate, tool success rate, and error rate

Generate an evidence-backed CCAM executive, cost, reliability, or workflow report.

List live and persisted CCAM-launched Claude Code and Codex runs

Search Agent Monitor sessions by cwd, model, or status and print the top matches.

List the N most recent Claude Code sessions from the Agent Monitor.

Summarize one Agent Monitor session by id — header plus a concise transcript recap.

Print the orchestration DAG edges (parent→child subagents) for a session.

List recent Workflow-tool fleet runs with status and agent counts.

Summarize the workflow intelligence for a session — stats, complexity, and top patterns.

Run broadcast on a distilled Raw — update related existing pages conversationally

Distill raw session records into refined Notes and Projects

Save knowledge to the cortex vault (Notes or Projects) and update index

Initialize cortex vault — set up config, vault structure, and rebuild index

Manually search the cortex vault (Notes, Projects, Raw) for existing notes

Create, resume, or clear a session hand-off baton (one per work line)

Command → Agent → Skill orchestration for end-to-end feature development.

Command → Agent → Skill orchestration for investigating and fixing bugs.

Brief the CEO: coordinate with the peer CTO and start or resume a founder project across 8 departments and 54 skills

Configure an optional active team profile in three short questions

Open-source, self-hosted AI media server. One server replaces your entire media stack, with a web app, native iPhone app, and an AI agent that gets things done.…

A curated list of tools built for Jev — TypeSafe AI's System One model for typed decisions.

🦦 Crayotter: A Multimodal AI-Agent for Video-Editing, Video-Composing, and Video Production. Powered by Multimodal LLMs for autonomous Text-to-Video agentic fr…

Webextension tool for Odoo