← ClaudeAtlas

project-bootstraplisted

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.
andr-ca/agentharness · ★ 1 · AI & Automation · score 70
Install: claude install-skill andr-ca/agentharness
# Project Bootstrap Use this the first time the harness runs in a project, or whenever the owner asks you to set it up, tailor it, or figure out which conventions apply here. The deterministic work is done by `agentharness bootstrap`. **Your job is the conversation** — the tool inventories the repository and lists the decisions that need making; you ask the owner about them, one at a time, and feed the answers back. **Check the command exists first:** `agentharness bootstrap plan --help`. If it is unavailable, this repository has not installed the harness CLI — fall back to `tools/setup/harness-link.sh` and assess the project conversationally rather than claiming a bootstrap flow exists. --- ## The loop ```bash # 1. Inventory (read-only — writes nothing, safe to run any time) agentharness bootstrap plan --json # 2. Feed answers back as you collect them agentharness bootstrap plan --answer rigor.tier=production # 3. Apply, only with the hash of the plan the owner approved agentharness bootstrap apply --answer ... --confirm <plan_hash> ``` `plan` is safe to re-run at any point. Re-run it after every answer — the question set and the proposed actions both change as answers come in. --- ## Reading the plan ```json { "detected": [{"capability": "test", "present": true, "detail": "pytest", "evidence": ["pyproject.toml"]}], "questions": [{"id": "rigor.tier", "prompt": "...", "default": "production"}], "actions": [{"path": "ruff.toml", "summary":