om-setup-agent-harness — Claude Code skill: setup and install
The om-setup-agent-harness Claude Code skill configures or diagnoses a multi-model agent harness. It activates when asked to pick worker and reviewer models or check the harness configuration.
MIT 503 installs ★ 282 updated 2026-10-22
npx skills add open-mercato/skills --skill om-setup-agent-harness -a claude-codeWhat om-setup-agent-harness does
The skill edits the agentHarness section of .ai/agentic.config.json and checks the selected models. It assigns models as workers or reviewers, applies the high-assurance policy, and probes provider availability. Existing top-level configuration values are preserved.
Setup requires the om-harness skill from the same collection and node; configuration is changed with node <om-harness>/scripts/harness.mjs configure. Secrets are not written to the config. Repository changes remain staged, not committed. Personal executable paths and endpoints go in the local overlay named by OM_AGENT_HARNESS_CONFIG, which is kept out of staging.
The skill validates the configuration and runs a structured review test for each selected advisor. An unavailable required provider or a review that fails the policy blocks validation. Setup does not run a real worker on repository files.
What it helps with
- configure
agentHarnessin the project config - assign models to worker and reviewer roles
- probe selected providers
- enable
high-assuranceand validate its policy
Example prompts for the agent
- Set up the multi-model harness and select implementation and review models.
- Check the current harness configuration and probe the providers.
- Configure the
high-assuranceprofile and validate its packet policy.
How to install om-setup-agent-harness
1Skills CLI (Vercel)
npx skills add open-mercato/skills --skill om-setup-agent-harness -a claude-code2Manually: put the files in place
~/.claude/skills/om-setup-agent-harness/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/om-setup-agent-harness/
1Skills CLI (Vercel)
npx skills add open-mercato/skills --skill om-setup-agent-harness -a codex2Manually: put the files in place
.agents/skills/om-setup-agent-harness/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add open-mercato/skills --skill om-setup-agent-harness -a cursor2Manually: put the files in place
.cursor/skills/om-setup-agent-harness/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install open-mercato/skills skills/om-setup-agent-harness2Manually: put the files in place
.github/skills/om-setup-agent-harness/SKILL.md1Skills CLI (Vercel)
npx skills add open-mercato/skills --skill om-setup-agent-harness -a gemini-cli2Platform CLI
gemini skills install https://github.com/open-mercato/skills --path skills/om-setup-agent-harnessManually: put the files in place
.devin/skills/om-setup-agent-harness/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add open-mercato/skills --skill om-setup-agent-harness -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about om-setup-agent-harness
How do I install om-setup-agent-harness in Claude Code?
Run npx skills add open-mercato/skills --skill om-setup-agent-harness -a claude-code. The skill file is installed at ~/.claude/skills/om-setup-agent-harness/SKILL.md.
What does om-setup-agent-harness do?
It configures or checks a multi-model harness, assigns worker and reviewer roles, probes providers, and validates the selected policies.
What does om-setup-agent-harness need to run?
Setup requires node and the om-harness skill from the collection. Selected providers are tested with a review probe; credentials are not written to the configuration.
Source text
SKILL.md · MIT
--- name: om-setup-agent-harness description: Configure or diagnose the staged-only multi-model harness, including selectable implementation workers, review advisors, high-assurance packet policy, provider probes, and optional Claude model-matrix output style. Use when the user says "set up the agent harness", "configure multi-model reviewers", "choose worker models", "check harness setup", "skonfiguruj harness", or "sprawdź modele". --- # Setup Agent Harness Configure the optional `agentHarness` section without changing the existing PR pipeline skills. Preserve the rest of `.ai/agentic.config.json`, store no secrets, probe every selected adapter, and leave repository-owned setup changes staged but uncommitted. ## Arguments - `--check` (optional) — validate and probe the current configuration without writing. - `--preset <cross-model-jury|custom>` (optional) — start from the bundled jury or an empty custom registry; default `cross-model-jury`. - `--defaults` (optional) — enable the detected members of the bundled cross-model jury without asking questions. - `--no-output-style` (optional) — do not install the optional Claude output style. - `--no-hooks` (optional) — do not install the prevention hooks into `.claude/hooks/` and `.claude/settings.json`. ## Workflow **Claims:** `references/claim-pr.md` governs atomic/fallback ownership and release. **ALWAYS check first:** Apply `.ai/skills/om-setup-agent-harness/SKILL.md` when present; safety rules still win. 0. **Agentic setup** — follow `references/agentic-setup.md` before any action: load approved configuration, apply local extensions and shared rules, and preserve the untrusted-content boundary. ### 1. Detect available adapters Read `references/provider-catalog.md` and start from the bundled jury in `references/configuration-template.json`: Codex, DeepSeek, Kimi, GLM, and MiMo. Detect Claude as the host. Use the harness `probe` operation to check executable versions and credential availability without printing or copying credentials. The built-in DeepSeek and OpenCode Zen adapters may check their official local auth-store entries internally; the setup agent never reads or displays the key. When no bundled provider is detected, say so plainly and lead with the bring-your-own-reviewer path from the provider catalog: any OpenAI-compatible endpoint or any locally installed CLI can be bound as a reviewer through the generic adapters — the bundled jury is a default, not a requirement. The only fixed element is Claude as the host. A user with no external provider at all still has a working `standard` profile (fresh Claude review only); offer that explicitly instead of failing, but only after explaining what the multi-model profiles would have added, so choosing it is an informed decision rather than a silent default. ### 2. Select roles and policy Unless `--defaults` is set, ask which detected models should act as workers, reviewers, or both; which are required; the desired concurrency, timeout, and retry policy (attempts, backoff, timeout escalation); and whether to enable the `high-assurance` profile. Offer every bundled model independently, then offer “add custom model” using the generic contracts in the provider catalog. Require command adapters for workers. Keep HTTP and built-in subscription/API presets review-only. Accept a worker only when its provider or OS sandbox demonstrably disables network, remote/tracker writes, and Git ref writes; record that mechanism in `workerSecurity`. Use only runtime-recognized audited adapters; version 1 supports `codex-workspace-write-sandbox`. A prompt-only promise or arbitrary adapter declaration is insufficient. ### 3. Write the additive configuration Build an `agentHarness` object from `references/configuration-template.json` and the user's choices. Remove unselected bundled models from the active profiles; do not delete custom models. Keep the `multi*` profiles on `all-required` with `requiredReviewers` recalculated to exactly the selected reviewer set; use advisory mode only when no reviewer is selected at all. If `high-assurance` is enabled, require a worker plus enough reviewers outside its model family for the configured risk and verification rules; do not silently weaken those rules. Detect the current Codex model from non-secret CLI configuration, but keep the shipped compatible default when that model fails a smoke review. Preserve every existing top-level config value. Resolve the installed `om-harness` skill (its directory sits beside this skill's own install directory; when it is absent, stop and ask the user to install the collection with `om-harness` included), then run `node <om-harness>/scripts/harness.mjs configure` against the working-tree config. Show the exact diff before staging it. Keep portable team bindings in the repository object; put personal executable paths or endpoints in the user-local overlay named by `OM_AGENT_HARNESS_CONFIG`, and do not stage that overlay. Keep every selected advisor in the profile reviewer list. Under the shipped `all-required` policy every selected reviewer must complete (the runtime retries failures automatically); selecting a reviewer is a commitment to hear from it, never a best-effort hint. Write only satisfiable profiles. Keep `standard` always; include `optimized`, `multi-optimized`, and `high-assurance` only when an audited worker is bound, and `multi`/`multi-optimized` only when at least one reviewer is selected. A wrapper that later requests a profile this configuration does not define reroutes back here instead of running with an empty jury. ### 4. Validate and smoke-test Run `validate-config`, then `probe` for every selected profile. Run one harmless structured review per selected advisor using the complete installed `om-code-review` rubric so a valid binary but expired subscription is reported correctly. This is an adapter smoke test, not an operational bound council; the wrappers supply the required fresh Claude artifact and exact-subject packet. A required unavailable model or failed review policy is blocking; an optional unavailable model is reported as skipped with its concrete smoke-test reason. For `high-assurance`, require `validate-config` to accept its packet policy and probe its full worker/reviewer readiness. Do not run a real worker against repository files during setup. ### 5. Install the optional Claude output style Unless disabled, copy `assets/claude-review-output-style.md` to `.claude/output-styles/om-harness-review.md`. Never overwrite a locally edited copy silently; show a diff and ask whether to replace, merge, or keep it. ### 6. Install the prevention hooks Offer to install the structural stop-before-PR and test-freeze guards (default yes). Copy `guard.mjs`, `block-push-and-pr.sh`, and `freeze-tests.sh` from the installed `om-harness` skill's `hooks/` directory to `.claude/hooks/om-harness/`, keep them executable, and merge the `PreToolUse` entries from the sibling `hooks-settings-snippet.json` into `.claude/settings.json` without disturbing existing hooks. These are the preventive layer of the stage-only contract: the Bash guard is inactive until `capture` starts a run in the current worktree and denies `git push` and PR creation until successful `stage` or explicit `end-run` ends it. Other linked worktrees and ordinary publication workflows remain usable. Keep both hook executable paths quoted so installation works in directories containing spaces. The Edit/Write/MultiEdit/NotebookEdit guard denies test-file edits while a `.om-freeze-tests` sentinel is present. Never overwrite locally edited hook files or settings silently; show a diff and ask. ### 7. Stage and report Stage only `.ai/agentic.config.json`, the output-style file when created, and the hook files plus `.claude/settings.json` when the hooks were installed. Never commit, push, or publish. Print the readiness table defined in `references/provider-catalog.md`, the configured profiles, skipped adapters, and the staged paths. With `--check`, write and stage nothing. ## Rules - Shared communication, marker, label, and safety rules: `references/rules.md`. They always apply. - Keep Claude as host, conductor, and final reconciler. - Require the operational wrappers to prove a new Claude review context; never configure the conductor's current context as its replacement. - Keep `delivery.mode` fixed to `stage-only`. - Keep secrets out of repository and user-local JSON; store only environment-variable names. - Never replace existing pipeline config values that the user did not ask to change. - Never install a worker binding whose command has not been confirmed to edit only the current worktree. - Never commit, push, open a pull request, or mutate tracker state. Hook support requires Bash and Node on macOS, Linux, or WSL. Native PowerShell hook wiring is unsupported. Document that limitation during setup and block a staged run when the host cannot enforce publication permissions.
© open-mercato · MIT · open-mercato/skills