Qredence Plugins is a catalogue of dual-target plugins that work in both Claude Code and OpenAI Codex. Each plugin gives a coding agent a specific operating mode — auditing repo readiness, optimizing evaluation harnesses, building research wikis, or orchestrating issue-driven workflows.Documentation Index
Fetch the complete documentation index at: https://docs.qredence.ai/llms.txt
Use this file to discover all available pages before exploring further.
Start with your goal
Make a repo agent-ready
Use harness-engineering to audit repo legibility, validation, and drift controls.
Optimize an LLM harness
Use meta-harness for outer-loop search across prompts, retrieval, and parsing strategies.
Build a research wiki
Use rlm-wiki for a Daytona-backed markdown wiki you can ingest, query, and lint.
Orchestrate issue-driven work
Use symphony for Linear-driven Codex orchestration with isolated workspaces.
What ships today
| Plugin | Use it for |
|---|---|
harness-engineering | Auditing repo readiness for agents, improving guardrails, scaffolding durable repo docs |
meta-harness | Optimizing a fixed LLM task across measurable metrics through repeated experiments |
rlm-wiki | Building a markdown research wiki that can ingest, query, and maintain large source sets |
symphony | Issue-driven orchestration with isolated workspaces, retries, and workflow hooks |
development | Stress-testing plans, rendering data visualizations, and scoring skills for quality |
legal | Auditing Terms of Service and privacy policies for unfair clauses |
autoresearch-dspy | Ratchet-style autonomous experiment loops that keep only measured improvements |