Skip to main content

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.

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.

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

PluginUse it for
harness-engineeringAuditing repo readiness for agents, improving guardrails, scaffolding durable repo docs
meta-harnessOptimizing a fixed LLM task across measurable metrics through repeated experiments
rlm-wikiBuilding a markdown research wiki that can ingest, query, and maintain large source sets
symphonyIssue-driven orchestration with isolated workspaces, retries, and workflow hooks
developmentStress-testing plans, rendering data visualizations, and scoring skills for quality
legalAuditing Terms of Service and privacy policies for unfair clauses
autoresearch-dspyRatchet-style autonomous experiment loops that keep only measured improvements

Repository

Source: github.com/Qredence/qredence-plugins