MCP App StoreMCP App Store
from agentops416
Mine past agent sessions for working prompts, decisions, rituals and recovery patterns (operational tooling).
Practical guide and operational skill for mining and working with archived agent sessions. Focuses on discovery workflows, prompt mining (ritual detection), index health and recovery, cross-machine sources, and safe operational recipes. Includes quick-reference commands and jq recipes for extracting user prompts and resuming past sessions.
Anwendungsfälle: Find prior prompts that worked, recover sessions, audit agent decisions, build prompt libraries, cross-machine searches.
Structure:
Notes: This skill documents operational commands for the cass CLI. It depends on the cass binary and related tooling; it is an execution/supporting skill rather than an end-user conversational skill.
cass-session-search is an AgentOps skill for mining past agent sessions to find working prompts, decisions, and patterns. The SKILL.md is exceptionally well-structured with clear frontmatter, detailed operating doctrine, anti-pattern tables, safety boundaries, and a thorough reference index pointing to 16+ supporting markdown files. No bundled scripts were present in this fetch, so only static analysis was possible. The skill requires the external `cass` binary and has niche appeal — primarily useful for teams running agent-ops workflows with large session corpora.
Security: No curl|bash, no hardcoded creds, no destructive commands. Safety boundaries are explicit (pre-authorized vs needs-permission). One minor concern: multi_machine_search.sh uses SSH to remote hosts — not fetched but referenced. Code quality: Very thorough documentation, clear constraints, well-organized anti-patterns. Missing actual scripts in this fetch limits quality assessment. Architecture: Exemplary structure — frontmatter complete, output contract specified, progressive disclosure via references/, clear separation between doctrine and reference material. Usefulness: Niche — primarily valuable for teams already invested in agent-ops/cass ecosystem. The session archaeology concept is interesting but requires significant setup (cass binary, indexed sessions). Broad developer audience is limited.
Evolve — Goal-Driven Improvement Loop
Autonomous improvement loop that selects high-value work, runs a full research-plan-implement (/rpi) cycle, validates changes, and repeats to compound repo impr
RPI — Full Lifecycle Orchestrator
Orchestrates a three-phase RPI lifecycle (discovery → implementation → validation) for autonomous agent workflows, including complexity classification, routing,
Beads BV — Graph-Aware Triage
Graph-based backlog triage using bv/br: rank priorities, find bottlenecks, and produce machine-readable recommendations for agents (robot mode).
PR Preparation & Validation
Systematically prepares pull requests by validating tests, analyzing commit patterns, and generating high-quality, structured PR bodies.
Operationalize
Distill research and learnings into durable automation rules.
Handoff: Durable Session Continuation
Writes compact session handoffs to ensure seamless continuation across agents or context resets.
Meta Skill Search Engine
A powerful search and load engine for AgentSkills across multiple corpora, enabling agents to discover and implement the right skill for a task.
AgentOps Learning & Verdict Analysis
Analyze durable verdict collections to summarize recurring evidence and propose new deterministic checks for agents.
NGINX Integration
Integrate with NGINX via the Membrane CLI to query, manage, and proxy requests to NGINX for configuration, logs, and runtime operations.
Retriever (Membrane CLI)
Integrate Retriever search and discovery via the Membrane CLI — manage connections and run queries across Retriever data sources.
Starlark Dev
Create, debug, and test Kurtosis Starlark packages — write package structure, run dry-runs, and inspect plan execution for reliable orchestration.
Reverse Engineer
Provides step-by-step guidance and best practices for binary reverse engineering: static analysis, dynamic tracing, disassembly, and documentation workflows for
Sync Production Database to Development
Run a safe, scripted workflow to download production database dumps and restore them into a development environment (download-only and restore options).
Sandbox0 Integration
Guidance and templates for integrating Sandbox0 sandboxing into AI agents — CLI/SDK patterns, templates, volumes, network policy, and deployment choices.
ClawPod / Massive Unblocker
Bypass anti-bot restrictions and fetch rendered HTML or structured search results via Massive's Unblocker API (handles CAPTCHAs, JS rendering, geo-restrictions)
Retriever (Membrane) Integration
Integrate with Retriever via the Membrane CLI to search, query, and proxy Retriever data (documents, snippets, queries) with built-in auth and pagination.