Set up CIAgent regression testing for the AI agent in this repo — write a runner, record golden baselines, generate a test spec, and verify it. Use when the user asks to add tests, evals, or regression testing for their AI agent, or to set up CIAgent.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Onboard CIAgent into this repo
You are setting up CIAgent (`pip install ciagent`) so this repo's AI agent has
recorded golden baselines and a runnable regression suite. The end state: the
user can run `ciagent test --runs 3` and see a stability report for their agent.
Work through the steps in order. Do not skip the cost gate in step 4.
## 1. Find the agent and install CIAgent
- Locate the agent: search for LLM SDK usage (`openai`, `anthropic`, `langgraph`,
`langchain`) and for the function or endpoint that takes a user message and
returns the agent's answer.
- Install with the matching extra so trace capture hooks the SDK:
`pip install "ciagent[openai]"`, `[anthropic]`, `[langgraph]`, or `[all]`.
- Sanity check: `ciagent --version` then `ciagent doctor` (it reports what is
missing; a missing spec is expected at this point).
## 2. Write the runner
Create `agentci_runner.py` at the repo root (or inside the package if the repo
has one clear package):
```python
def run_for_agentci(query: str) -> str:
"""CIAgent entry point: one query in, final answer text out."""
# import the user's agent and invoke it ONCE, no chat history
...
…
The line at the top of this page pins the label git:20260709.8e73ef5, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
GET https://markdownregistry.com/api/v1/artifacts/art_ncgjzbjsixp4gskk
GET https://markdownregistry.com/api/v1/resolve?ref=davepoon/buildwithclaude/onboard
GET https://markdownregistry.com/api/v1/blob/9d7dc93b4c3085b9e5ffce47532772df2f28c952c44585820b964126af8eb955
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
davepoon/buildwithclaude · plugins/agent-triforce/skills/code-health/SKILL.md · Scans the codebase for dead code, tech debt, outdated dependencies, and code quality issues. Delegates to the Centinela…
davepoon/buildwithclaude · plugins/agent-triforce/skills/implement-feature/SKILL.md · Implements a feature from its specification. Reads the spec, designs architecture, writes code and tests. Delegates to…
davepoon/buildwithclaude · plugins/agent-triforce/skills/review-findings/SKILL.md · Addresses and fixes findings from a QA code review. Reads the review report, fixes critical and warning issues, and…
davepoon/buildwithclaude · plugins/agents-uc-taskmanager/skills/init/SKILL.md · Initialize uc-taskmanager for the current project. Creates works/ directory and configures Bash permissions in…
davepoon/buildwithclaude · plugins/agents-uc-taskmanager/skills/work-pipeline/SKILL.md · Triggers the WORK-PIPELINE when a user request starts with a [] tag (e.g., [new-feature], [bugfix], [WORK start]). Use…
davepoon/buildwithclaude · plugins/agents-uc-taskmanager/skills/work-status/SKILL.md · Shows WORK progress and TASK status. Use when the user asks about WORK list, WORK progress, TASK status, or pipeline…
wesammustafa/claude-code-everything-you-need-to-know · solutions/a-6/team-marketplace/plugins/team-kit/skills/onboard/SKILL.md · Explains this repository's shared Claude Code setup to a new teammate, covering what is committed and shared, what…
wesammustafa/claude-code-everything-you-need-to-know · examples/advanced/06-share-your-setup/plugins/team-kit/skills/onboard/SKILL.md · Explains this repository's shared Claude Code setup to a new teammate, covering what is committed and shared, what…
clacky-ai/openclacky · lib/clacky/default_skills/onboard/SKILL.md · Onboard a new user OR curate a single piece of the assistant's inner state. Without arguments, runs the full first-run…
athola/claude-night-market · plugins/gauntlet/skills/onboard/SKILL.md · Guides a new developer through five staged challenge sets covering architecture, domain, patterns, and hardening. Use…
justxor/claude-code-pro-course · starter-kit/.claude/skills/onboard/SKILL.md · Проводит онбординг нового разработчика в проект - обзор архитектуры, запуск, ключевые потоки и первая задача…
jongwony/epistemic-protocols · epistemic-cooperative/skills/onboard/SKILL.md · Quick protocol recommendation from recent sessions, or quest-based learning through scenario, trial, and quiz.