Git, testing, logging, and language conventions written once and
referenced everywhere — instead of re-authored (and drifting) in every project's own
CLAUDE.md. One source of truth for the rules your coding agents follow,
across every project you run them in.
Status: early — see the repo's MANIFEST.md for what exists today and ROADMAP.md for what's planned.
One project's conventions work fine — until the second project quietly diverges, and the third, and the fourth.
A single project's CLAUDE.md works fine — until there's a second project,
and its CLAUDE.md quietly diverges: a different coverage bar, a
branch-naming rule that contradicts the first repo's, a logging convention nobody
remembers deciding. Multiply by N projects and the conventions aren't really policies
anymore — just N independent guesses that happen to overlap.
agentharness fixes that specific problem: one CLAUDE.md router plus a set of
skills and convention docs that every project's own (short) CLAUDE.md
references. You still write a project-specific CLAUDE.md; it just
stops being where the shared rules live.
<!-- project-a/CLAUDE.md -->
## Testing
Aim for 80% coverage. Use pytest.
Don't mock the database.
<!-- project-b/CLAUDE.md, six months later -->
## Testing
Try to keep coverage reasonable
(70%+ ok for now). pytest preferred.<!-- both projects, identical -->
## Testing
See agentharness's
patterns/testing/COVERAGE_REQUIREMENTS.md
for the coverage bar by rigor tier.
This project is Production tier.Most agent configuration is advisory. agentharness layers in three governance mechanisms most coding-agent setups lack.
Agents verify and stage work locally, then stop and ask before pushing, opening a PR, or auto-implementing a recommendation. Full remote-write authority requires an explicit flag file or per-task instruction — work that's only staged locally is never "complete."
Before an agent can declare done, it runs a completion check verifying lint, types, tests, coverage, and content quality in one shot. A Stop hook enforces it — the agent cannot end its session until the gate exits 0.
Merging on CI green alone is not enough. The mandate requires fetching issue-level and inline PR comments, verifying each finding against current code, fixing what's real, and replying to every comment — closing the "agent silently ignored review feedback" failure class.
Built for and dogfooded in Claude Code; also tested with Codex CLI, Gemini CLI, and GitHub Copilot.
Generators produce an always-on routing file plus an Agent-Skills-standard skill index for every major agentic coding tool:
| Platform | Always-on file | Status |
|---|---|---|
| Claude Code | CLAUDE.md | ✅ built + dogfooded |
| Codex CLI | AGENTS.md | ✅ built + tested |
| OpenCode / Zed | AGENTS.md | ⚠️ passively covered |
| Gemini CLI / Antigravity | GEMINI.md | ✅ built + tested |
| GitHub Copilot | .github/copilot-instructions.md | ✅ built + tested |
| Kilo Code | .kilo/rules/agentharness.md | ✅ built, not live-tested |
| Cursor | .cursor/rules/agentharness-router.mdc | ✅ built, not live-tested |
The lifecycle CLI covers init, plan, status,
doctor, audit, update, and
uninstall.
Via npm — no separate clone step:
npx agentharness-toolkit init /path/to/your-projectOr via git clone:
git clone https://github.com/andr-ca/agentharness.git ~/agentharness
~/agentharness/tools/setup/harness-link.sh init /path/to/your-projectPreview without changing anything with --dry-run (or run
plan instead of init), and verify afterward with
doctor. Opt into the trunk-protection git hook with
--with-hook, or a generated coverage-enforcing pre-push hook with
--with-coverage-hook.