02-DOCS/It remembers your project.
A wiki of your decisions, stack and progress. The agent reads it before it starts and adds to it as it works.
Free and open source. A star is how the next developer finds it.
No config files, no setup guide. You send one message to the agent you already use, and it sets itself up.
Read https://ericrisco.github.io/rsc-harness/ and set up rsc for this project. Ask me the onboarding questions, show me the exact plan, and wait for my acceptance before writing.
npx @ericrisco/rsc@latest onboard
02-DOCS/A wiki of your decisions, stack and progress. The agent reads it before it starts and adds to it as it works.
01-TOOLS/Your CRM, your ERP, your APIs. Each connection is built once, tested, and kept for every next session.
skillsThe know-how for what you build, picked for this project. A handful out of 273, so the rest never costs context.
hooksRules that run by themselves: proof for every task, the right amount of process, your language in every reply.
An agent without documentation opens files, greps, reads the same module twice, and still guesses. With a well-structured 02-DOCS/ it knows where to look.
Illustration of the mechanism, not a benchmark.
CRMs, ERPs, the program on the office PC. connect-tool reads the vendor's current docs, takes the safest route, builds 01-TOOLS/ and proves it works. Pick one.
.env.exampleCREDENTIALS.mdREADME.mdtest_connection.shExample run. The skill checks each vendor's current docs every time, and says so when it finds nothing reliable. Any tool works, not only these.
Five steps, from install to the next morning.
How technical to talk, what the project is for, its goal, which assistants. It reads only the project root.
Every piece comes with its reason. You accept that exact plan, or nothing happens.
An answer, a quick change, or the full chain. It says which in one line, in your language.
Decisions, connections and progress land in 02-DOCS, not in the chat.
You, a teammate on another machine, or another assistant open the project, and the agent already knows.
A task is checked off when its proof was seen: the test output, the command's result. Belief does not count.
Every rule rsc declares binding ships with the check that enforces it, and a test that watches that check fail and pass.
Silence for the trivial, ceremony only where failure is expensive. A harness that nags gets switched off.
Known limits, stated openly: the hard guards run in Claude Code; on other assistants the rules travel as instructions. Session memory is local by design and never touches the network.
Do not choose components or onboarding answers for the user.
npx @ericrisco/rsc@latest onboard and relay every required question.--technical-level --project-kind --goal --software-scope --target.--accept-plan <printed-id> only after exact acceptance.rsc-harness is a free, open-source (MIT) harness builder for AI coding agents. One message to Claude Code, Codex, Cursor or another of its 18 supported assistants installs a project memory (02-DOCS/), tested tool connections (01-TOOLS/), a handful of skills chosen from 273, and hooks that check the work before the agent says it is done.
Everything around the model that makes it useful in a real project: the instructions it reads, the memory it keeps, the tools it can call, the skills it loads and the checks that run on their own. The model is the engine. The harness is the rest of the car.
Paste the setup message into your agent, or run npx @ericrisco/rsc@latest onboard in the project root. It asks a few questions, shows the exact plan (selected, deferred and excluded pieces, each with its reason) and writes nothing before you accept it. Agents can run it non-interactively with --technical-level and, after your acceptance, --accept-plan.
Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, DeepSeek Harness, Windsurf, Cline, Roo, Zed, Continue, Amp, Antigravity, Jules, Junie, Kiro and Aider. You can pick several: skills are written once and shared.
That is how a Frankenstein harness happens: duplicated skills, premature hooks and unnecessary MCP servers that fill the context and contradict each other. rsc installs only what the project root and your answers justify, loads skills progressively, on demand, and adds more only when new evidence appears.
Yes, as a mechanism. An agent with a well-structured 02-DOCS/ knows where to look instead of searching file by file, so it reads less, reuses the code you already have instead of duplicating it, and guesses less. We show the mechanism, not a benchmark number.
It is MIT-licensed and needs no API key and no account. Session memory is local by design and never touches the network. It runs inside the assistant you already use.
Yes. Knowledge in 01-TOOLS/ and 02-DOCS/ travels through one exchange branch and reaches main inside normal pull requests, a second agent in the same folder gets its own worktree, and you choose at install whether work goes straight to main or through branches and pull requests.