Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 273,553 indexed, measured the same four ways as everything else here.
A procedure for turning one video or its script, transcript, audio, or outline into publishing material for selected video platforms. It produces titles, descriptions, tags, and directions for cover artwork.
Satori MCP workflow for repository code intelligence: finding where unfamiliar behavior lives, tracing ownership and callers, reviewing change impact, and handling index readiness (create, sync, reindex, cancel). Use when a task needs Satori search, navigation, or index lifecycle decisions beyond a known path or…
Install or add requested npm or pnpm dependencies through SafeInstall's existing artifact-bound installation gate. Use when a user requests dependency installation, including development dependencies. Never use for arbitrary registry-code execution or to bypass a policy block.
Request a one-off human approval through Sanction for an exact proposed tool action, or resume that same request after review. Use for explicit approval requests and synthetic approval tests, not ordinary tool discovery or usage reporting.
Start with GSPC — read the live measurement board, verify a signed card, and list the signed cards relevant to one obligation. Measurement, not certification.
Pick at most five of the newest vidtheque videos for the owner, each with one line on why, using what Claude knows about them from its memory, and learn from their thumbs on earlier picks. Use for the daily picks routine (companion.md §6.4), or when asked to curate the vidtheque feed or dry-run the picks.
Write Harbor task verifiers using Reward Kit. Use when creating or editing a task's tests/ directory, adding grading criteria, setting up LLM/agent judges, or designing verifiers that produce a reward score.
Research current open-source AI agents, evaluation tools and Agent Skills for Keryx, then adapt a source-backed pattern to an observed project need. Use for OSS learning/adoption requests; ordinary implementation and unrelated product work do not need this survey.
Use when building, changing, testing or debugging a wick SERVICE plugin — the always-on plugin wick supervises and serves at /x/{key}/ (webhook receivers, public or token APIs, pages for signed-in users, A2A / Team remote agents). Covers the pkg/service Module (Meta, Routes, Configs, CallbackScopes, Register…
Discover, assess, verify and manage MCP servers with the @getmcpm/cli package. Use when working with mcpm evidence, project locks or AI client MCP configuration.
A tool for creating example time-series data and loading it into an IDMP system. It models assets such as equipment and their hierarchy, then produces configuration and simulated readings.
Convert a function, method, or service's control flow — in any programming language — into a Mermaid flowchart diagram. Use when the user wants to visualize code logic, map a control flow, turn a method into a diagram, or understand a complex/branchy function visually.
★not rated 2 2mo agoA61 tokens
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: