Run CIAgent regression checks after changing an agent’s code, prompts, or knowledge base. Interpret failures and repeated runs to distinguish incorrect answers, inconsistent model judgments, and setup problems before committing changes.
中文简介正在准备中。当前显示英语简介。
Run CIAgent regression checks after changing an AI agent's code, prompts, or knowledge base in a repo that has agentci_spec.yaml, and interpret the results. Use after editing agent logic, before committing agent changes, or when the user asks whether the agent still works.
安装前可以查看交给 AI 代理的指令内容。
The repo has agentci_spec.yaml (if it does not, use the onboard skill
instead). Your job: run the right check for the change that was just made,
read the result correctly, and never paper over a failure.
| Situation | Command |
|---|---|
| Spec or wiring changed, or no API keys | ciagent test --mock |
| Agent code / prompt / retrieval changed | ciagent test --yes --format json |
| Result differs from last run, or flakiness suspected | ciagent test --runs 3 --yes |
| Knowledge base changed | ciagent generate-checks --dry-run, review, then apply |
| The LLM judge's verdicts look wrong | ciagent judge-audit |
Live runs (test without --mock, judge-audit, generate-checks) call model
APIs on the user's keys. Mock mode is free. If the user has not already
approved live runs in this session, prefer --mock or ask.
Exit codes: 0 pass (including flaky-but-passing), 1 correctness failure
(with --runs N: failed in every run), 2 infra or config error — fix the
setup, not the agent.
With --format json: per-query entries carry layer results (correctness /
path / cost) and the answer text; with --runs N a top-level stability block
lists flipped queries with flip_source.
Flip sources route the work:
agent-variance — the agent's answer changed between runs → fix the agent
(prompt, retrieval, temperature).judge-flake — same answer, the LLM judge changed its verdict → fix the
eval (tighten the rubric or replace with a deterministic check).infra-error — a judge API call failed → retry; fix nothing.mixed — ambiguous; look at the answers yourself.ciagent bootstrap --runner <runner> --queries <file> --yes for that query,
or update the spec's expectations — with the user's confirmation.还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Handle ActiveCampaign contact and marketing tasks through Rube MCP, a connection for agent tools. Find or create contacts, manage tags and subscriptions, enroll contacts in existing automated workflows, and create follow-up tasks.
中文简介正在准备中。当前显示英语简介。
Research competitors’ live Meta and Google ads to identify opening hooks, offers, calls to action, and landing pages. Receive a sourced creative brief and up to three test ideas adapted to your product.
中文简介正在准备中。当前显示英语简介。
Analytics your AI agent can actually use. Track, analyze, run A/B experiments, and optimize across all your projects via CLI. Includes a growth playbook so your agent knows HOW to grow, not just what to track.
中文简介正在准备中。当前显示原文说明。
Teaches when to recall from long-term memory before acting and when to save durable decisions, corrections and failures afterwards. Use when a memory tool or MCP memory server is connected but the agent is not using it consistently, when the user complains that the assistant forgets preferences, conventions or past decisions between sessions, or when setting up persistent memory for a project. Works with any memory backend: a folder of Markdown files, a local MCP server, or a managed service.
中文简介正在准备中。当前显示原文说明。
Audit local AI coding-agent sessions with agenttrace for cost, tokens, tool failures, latency, anomalies, health, diffs, and CI gates.
中文简介正在准备中。当前显示原文说明。
Checks which private files (.env, keys, secrets) Claude Code and its subagents reached in this project, whether a value came into an agent's context, and which key to change, by running the open source agentwhy CLI over the session records Claude Code already keeps on disk. Use when the user asks whether the agent or a subagent read their .env or other secrets, which private files a session touched, whether a key leaked into the conversation, or which key to rotate. Runs locally and never prints a secret value.
中文简介正在准备中。当前显示原文说明。