LLM Mart Basic

Map reading notes to thesis chapters and integrate key arguments into the manuscript. Use after completing a reading session to weave new material into the thesis.

Show literature-to-chapter coverage and the writing progress dashboard — which sources support which chapters, and word counts against targets.

Record reading notes to a structured notes file. Use when the user says "take notes" or "record this" during reading sessions.

Read PDF page by page with structured output — key arguments, terms glossary, thesis connections. Use when reading academic papers, books, or articles.

Open a reader panel. Instruction-bound amnesiac sub-agents read the abstract or introduction and report what they carried away, set against the author's intended points. Use when those sections change or the writing loop marks the panel stale.

Review a manuscript or chapter as an external reviewer, or run an own-work self-review in a fresh-context clean room, producing anchored findings and a recommendation.

Use when checking BibTeX reference records for missing fields, malformed identifiers, duplicate keys, or metadata mismatches before submission.

Build evidence-controlled literature reviews and gap maps with source-status labels, claim registers, citation-role plans, traceability tables, and overclaim audits. Use when drafting or auditing review papers, thesis literature reviews, scoping reviews, or evidence syntheses whe

Use when validating, repairing, or mapping human-evaluation handoff packages, filled annotation CSVs, rebuttal annotation UIs, or reviewer annotation returns across package versions. Applies to checking row alignment, detecting cross-snapshot contamination, converting old labels

Review stable chapter or manuscript drafts for paragraph flow, transitions, argument continuity, and repeated rhetorical functions before editing. Use after the author-approved spine is stable; route structural drift back to thesis-control.

Reframe report-like academic drafts into paper-form scientific arguments while preserving or explicitly renegotiating author intent; requires an approved old-versus-proposed spine, evidence and argument baselines, analysis-role control, and post-edit drift review.

Review another author's manuscript, paper, thesis chapter, proposal, or preprint as an external reviewer. Use when asked to evaluate novelty, significance, gap-contribution fit, claim-evidence adequacy, methods, evaluation, overclaim risks, structure, writing, required revisions,

Show reading and writing progress dashboard — how many sources read, chapters completed, word counts, and coverage gaps.

Use when preparing, auditing, releasing, PDF-hardening, or rebuttal-hardening academic manuscripts, datasets, artifacts, reviewer packets, or claim registers involving multiple refs, local assets, human labels, agent-assisted drafts, wide tables, figure provenance, submission PDF

Stop repeated failed writing, coding, manuscript, rebuttal, or restructuring revisions when the same issue has gone through 3+ unsatisfactory edits, vague feedback such as still wrong/weird/unclear/weak/越改越乱, version contamination, or possible gap/claim/evidence/venue-fit drift.

Review the user's own manuscript, paper, thesis chapter, rebuttal, or release packet with clean-room anti-contamination controls and, when needed, an unfamiliar-reader comprehension gate. Use for internal review, readiness checks, reviewer simulation, or claim-evidence self-audit

Check thesis text for British English consistency and safe mechanical spelling fixes.

Use when AI-assisted thesis or manuscript edits risk claim drift, scope creep, loss of intended use, experiment-role promotion, or repeated revisions that fail to converge; provides author-intent control, lightweight or strict contracts, drift audits, revision escalation, and hum

Fact-check claims encountered during reading — dates, names, events, citations. Use when encountering historical facts or disputed claims.

Use when the user wants their Claude agent to self-improve from past usage, asks about a nightly/offline 'sleep' or 'dream' cycle, memory/skill consolidation, or says things like 'make my agent better the more I use it', 'review my past sessions', 'learn my preferences', 'consoli

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.