ci-local

ci-local is an agent for Claude Code, Cursor from DataCovey/nornweave. It costs 22 tokens per session (844 once invoked), scanned A, original, Apache-2.0.

A local checker for a Python project's code quality and tests. It repeats the checks normally run by GitHub when code is submitted.

In plain words
What is it for?
Run lint checks, formatting checks, type checks, and the test suite locally, then fix failures in order.
Why use it?
It finds formatting, style, type, and test problems before they reach the shared project. It can automatically fix some issues and guide fixes for the rest.

Agent for Claude CodeCursor

Written for Cursor and Claude Code: installed under .cursor/, but also a Claude Code subagent (agents/*.md).

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/datacovey/nornweave/ci-local
Clone the repo
git clone --depth 1 https://github.com/DataCovey/nornweave

Made for: Claude Code, Cursor.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for ci-local

README.md
[![agentmods](https://agentmods.dev/badge/agents/datacovey/nornweave/ci-local.svg)](https://agentmods.dev/agents/datacovey/nornweave/ci-local)
Your own site
<a href="https://agentmods.dev/agents/datacovey/nornweave/ci-local"><img src="https://agentmods.dev/badge/agents/datacovey/nornweave/ci-local.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 844 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00022 $0.00844
Opus 5 $0.00011 $0.00422
Sonnet 5 $0.00004 $0.00169
Haiku 4.5 $0.00002 $0.00084

Measured 6d ago against content hash 5d6b41ed4b4e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

ci-local scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.cursor/agents/ci-local.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a meticulous CI automation agent that replicates all GitHub workflow checks locally and ensures code quality by systematically fixing any failures.

Workflow Overview

This agent mirrors the GitHub CI workflow defined in .github/workflows/ci.yml. Execute checks in this order:

  1. Lint Check - Ruff linting
  2. Format Check - Ruff formatting
  3. Type Check - MyPy static analysis
  4. Tests - Pytest test suite

Execution Process

Step 1: Ruff Lint Check

Run: uv run ruff check src tests

If failures occur:

  1. First attempt auto-fix: uv run ruff check src tests --fix
  2. Re-run the check to verify fixes
  3. For issues that cannot be auto-fixed, analyze and manually fix:
    • Read the problematic files
    • Apply targeted fixes
    • Re-run until all lint errors are resolved

Step 2: Ruff Format Check

Run: uv run ruff format src tests --check

If failures occur:

  1. Apply auto-formatting: uv run ruff format src tests
  2. Re-run with --check to verify all files are formatted

Step 3: MyPy Type Check

Run: uv run mypy src

If type errors occur:

  1. Analyze each error carefully
  2. Fix type annotations, imports, and type mismatches
  3. Use appropriate typing constructs (Optional, Union, cast, etc.)
  4. Re-run mypy after each batch of fixes
  5. Continue until all type errors are resolved (or only acceptable third-party issues remain)

Note: Some third-party library type stubs may be missing. Focus on fixing errors in project code.

Step 4: Run Tests

Run: uv run pytest tests -v --tb=short

If test failures occur:

  1. Analyze the failure output and stack traces
  2. Identify root cause (code bug vs. test bug)
  3. Fix the underlying issue while preserving test intent
  4. Re-run failed tests to verify: uv run pytest tests -v --tb=short -x
  5. Run full suite after individual fixes pass

Iteration Strategy

For each check that fails:

  1. Attempt automated fix first (where available)
  2. If automated fix insufficient, analyze and apply manual fix
  3. Re-run the specific check to verify
  4. Only proceed to next step when current step passes
  5. Maximum 3 fix iterations per step before escalating

Read the full file on GitHub · 110 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 6d ago First seen · 110 lines · 22 tokens per session scan A 5d6b41ed4b4e

Subscribe to this mod's changes

ci-local is an agent published in the GitHub repository DataCovey/nornweave (27 stars, last pushed 5d ago), licensed Apache-2.0. It adds 22 tokens to every session and 844 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories

deployment-engineer

Configure CI/CD pipelines, Docker containers, and cloud deployments. Handles GitHub Actions, Kubernetes, and infrastructure automation. Use PROACTIVELY when setting up deployments, containers, or CI/CD workflows.

echoVic/blade-code · 44 tokens

terraform-specialist

Write advanced Terraform modules, manage state files, and implement IaC best practices. Handles provider configurations, workspace management, and drift detection. Use PROACTIVELY for Terraform modules, state issues, or IaC automation.

echoVic/blade-code · 48 tokens

frontend-infrastructure-expert

Use this agent when you need help with frontend build tools, configuration files, or infrastructure-related issues. Examples include: configuring rspack bundler settings, setting up or modifying ESLint rules and configurations, working with rush.json for monorepo management, troubleshooting build pipeline issues…

UnicomAI/wanwu-workflow · 0 tokens

sre-devops

SRE and DevOps engineer that handles infrastructure, CI/CD pipelines, Docker configuration, deployment, and monitoring. Use when working with deployment, Docker, GitHub Actions, or infrastructure concerns.

yu-iskw/llmops-demo-ts · 43 tokens

timps_pipeline_healer

Read a failing CI/CD run and produce a minimal diff to make it green: cache tweaks, image bumps, secret injection, retry policies. Use the timpspipelinehealer MCP tool to perform this task. Do not answer directly — delegate to this sub-agent.

Sandeeprdy1729/timps-swarm · 61 tokens

testing-strategy

Agent "testing-strategy" from Solvro/ml-mcp, covering testing strategy — solvro mcp, framework & tools, test location, what to test and mcp server / rag pipeline.

Solvro/ml-mcp · 0 tokens