andr-ca/agentharness

Portable engineering policies for coding agents — git, testing, logging, and language conventions written once and referenced everywhere

This repository also configures its own agents. See what agentharness tells them →

1Stars on the repository
90Mods indexed here, across every type
5d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

andr-ca/agentharness

Cursor rule Claude CodeCursor

Use when two or more agent sessions may work on the same repository concurrently — covers the per-feature lock-file protocol, stale-lock detection, worktree isolation rules, and what to do when a feature is already locked.

not rated 1 5d ago C 43 tokens original MIT

mutation-testing

26

andr-ca/agentharness

Cursor rule Cursor needs its repo

Use when writing tests for critical business logic, auditing test suite quality beyond line coverage, or interpreting surviving mutants — covers mutation operators, mutation score thresholds, and tooling (mutmut, Stryker, gremlins) for Python, TypeScript/JS, and Go.

not rated 1 5d ago A 55 tokens original MIT

andr-ca/agentharness

Cursor rule Cursor

Use when diagnosing slow code, high memory usage, or CPU spikes — language-agnostic profiling workflow: form a hypothesis, identify the hot path, benchmark before and after, and interpret profiler output. Includes Python (cProfile, py-spy), Go (pprof), and Node.js (--inspect, clinic.js) tooling.

not rated 1 5d ago A 66 tokens original MIT

planning-with-files

28

andr-ca/agentharness

Cursor rule Cursor

Use when starting a complex multi-step task, a research project, or any task requiring more than 5 tool calls — creates and maintains taskplan.md, findings.md, and progress.md to preserve state across context resets.

not rated 1 5d ago A 44 tokens original MIT

port-agent-config

29

andr-ca/agentharness

Cursor rule Cursor

Use when asked to port, migrate, or add equivalent agent instructions, skills, or custom sub-agents for a different coding tool than the one already configured — e.g. "add Cursor support from our CLAUDE.md", "we're switching from Cursor to Codex, port our rules", "make this work for Copilot too", "port our review…

not rated 1 5d ago A 112 tokens original MIT

project-bootstrap

30

andr-ca/agentharness

Cursor rule Cursor

Use on the first run in a project, or when asked to set the harness up, tailor it to this repository, or work out which conventions apply here — inventories what the project already does, interviews the owner about the decisions only they can make, and applies a confirmed plan without overwriting existing setup.

not rated 1 5d ago A 61 tokens original MIT

python-conventions

31

andr-ca/agentharness

Cursor rule Cursor

Use when writing or reviewing Python code — naming conventions, type hints, common pitfalls (mutable defaults, bare except, is-vs-==), and testing structure.

not rated 1 5d ago A 33 tokens original MIT

andr-ca/agentharness

Cursor rule Cursor

Use when writing, reviewing, or optimizing React or Next.js code — component architecture, hooks rules, server vs. client components, data fetching patterns, bundle size, and accessibility in React.

not rated 1 5d ago A 38 tokens original MIT

refactoring

33

andr-ca/agentharness

Cursor rule Cursor

Use before restructuring code — covers behavior-preservation contracts, characterization tests, incremental reversible steps, and protected public contracts. Ensure refactoring remains a code change, not a feature change.

not rated 1 5d ago A 36 tokens original MIT

andr-ca/agentharness

Cursor rule Cursor

Use before implementing a significant feature or change when requirements are ambiguous, underspecified, or likely to have multiple reasonable interpretations, or when a requirement arrives pre-formed as an issue, audit finding, or review comment whose claim needs checking — covers verifying the premise before acting…

not rated 1 5d ago A 77 tokens original MIT

security-review

35

andr-ca/agentharness

Cursor rule Cursor

Use when reviewing code for security vulnerabilities, performing a security audit, or checking for OWASP Top 10 issues — covers injection flaws, broken access control, cryptographic failures, secrets exposure, dependency vulnerabilities, and language-specific pitfalls for Python, TypeScript/JavaScript, and Go.

not rated 1 5d ago B 57 tokens original MIT

solid-principles

36

andr-ca/agentharness

Cursor rule Cursor

Use when designing classes or APIs to evaluate SOLID compliance — SRP, OCP, LSP, ISP, DIP. Covers what each principle means, how to diagnose violations by symptom, and how to refactor.

not rated 1 5d ago A 44 tokens original MIT

testing

37

andr-ca/agentharness

Cursor rule Cursor

Use when writing tests, deciding on test coverage, choosing between unit/integration/E2E tests, applying TDD, or reviewing test quality — covers rigor tiers, the Red-Green-Refactor cycle, coverage requirements, and Playwright for UI testing.

not rated 1 5d ago A 52 tokens original MIT

andr-ca/agentharness

Cursor rule Cursor

Use when writing, reviewing, or refactoring TypeScript or JavaScript code — naming conventions, type annotations, private fields, null vs. undefined, async/await pitfalls, and module structure.

not rated 1 5d ago A 39 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: