maicongambini/omp-harness-guide/harness-bootstrap
Claude Code and agent skill by maicongambini/omp-harness-guide
- community
Checking that the SKILL.md file is still in the repository.
Installs or merges the complete Agent OS harness into a repo. Use when adopting the full harness suite after approval. Do NOT use for read-only harness audits (use harness-initializer).
Install
npx vskill@latest install maicongambini/omp-harness-guide/harness-bootstrapSKILL.md
The same SKILL.md was published earlier as maicongambini/omp-harness-guide/harness-bootstrap.
Harness Bootstrap
Install a full harness into any project, but only after explicit user approval (or pre-authorized when invoked via novo-projeto).
Portable Onboarding Integration
Full bootstrap installs the entire package while preserving project-specific files, then delegates environment detection, baseline setup, and service drafting to the shared onboarding CLI:
Path & Environment Resolution
<harnessHome>dynamically resolves to the installed harness home (~/.omp/agentin Oh My Pi, or canonical~/.config/opencodein OpenCode).- Commands must be absolute and quoted to safely support paths with spaces. Never hardcode machine-specific usernames.
- Dry-run is the default when
--writeis omitted.
Automated Onboarding Execution
The shared onboarding CLI automates four essential artifacts without inventing data:
- Project Profile & Cérebro (`agent-os/project-profile.json`): Detects test components, containerization, CI, and delivery config via
harness-project-profile.mjs, publishing automatically to the Obsidian project cérebro (--publish-cerebro). - Bounded Eval Mining (`evals/dataset.json`): Mines bugfix commits and corresponding test pairs from git history via
harness-eval-runner.mjs --mine --write. If the repository is fresh or lacks bugfix commits, it leaves an explicit empty dataset/gap; it never fabricates synthetic tests or fake passing suites. - Evidence-Backed Security Contract (`agent-os/security-contract.json`): Scans for routes and policy files to draft tenant isolation, authz, and IDOR targets. Entries specify
{ "path": "<file>", "command"?: "<runner>", "requires"?: [{ "host": "127.0.0.1", "port": 5432 }], "envFile"?: "<path>", "requireNoSkips"?: true }. If no contract or security tests exist, it records an explicit gap with the status returned by the tool (status: "unavailable"when the contract file is absent, orstatus: "not_applicable"when no executable tests are declared); it never invents placeholder tests. - Quality Thresholds (`agent-os/quality-thresholds.json`): Configures the repository in Phase A, where all metrics are set to
observeexceptregression_suite(which isblocking). Existing blocking settings, tighter ratchets, and custom operator fields survive repeat onboarding unchanged; onboarding never downgrades an existing blocker.
Full Package
Propose these files:
AGENTS.mdfeature_list.jsondocs/harness/progress.mddocs/harness/session-handoff.mddocs/harness/sprint-contract.mddocs/harness/matt-pocock-tracker.mddocs/harness/refine-log.mddocs/harness/findings/README.mddocs/harness/licoes-aprendidas.mddocs/ARCHITECTURE.mddocs/PRODUCT.mddocs/RELIABILITY.mdagent-os/judges/project-judge.mdagent-os/standards/*agent-os/specs/_template/*agent-os/quality-thresholds.jsonagent-os/learned-rules.jsonagent-os/prevc-autonomy.jsonagent-os/skills-proposals/agent-os/dependency-ledger.jsonagent-os/redteam-allowlist.jsonagent-os/quality-decisions.mddocs/review.mddocs/pull-request.md.github/pull_request_template.mddocs/review-area.md
Install mapping — quality and continual-harness files
| Global template | Installs to | |
|---|---|---|
templates/agent-os/quality-thresholds.json | agent-os/quality-thresholds.json | |
templates/agent-os/quality-decisions.md | agent-os/quality-decisions.md | |
templates/docs/review.md | docs/review.md | |
templates/docs/pull-request.md | docs/pull-request.md | |
templates/agent-os/learned-rules.json | agent-os/learned-rules.json | |
templates/agent-os/prevc-autonomy.json | agent-os/prevc-autonomy.json | |
templates/agent-os/skills-proposals/ | agent-os/skills-proposals/ | |
templates/agent-os/dependency-ledger.json | agent-os/dependency-ledger.json | |
templates/agent-os/redteam-allowlist.json | agent-os/redteam-allowlist.json | |
templates/docs/harness/refine-log.md | docs/harness/refine-log.md | |
templates/docs/harness/findings/README.md | docs/harness/findings/README.md | |
templates/docs/harness/licoes-aprendidas.md | docs/harness/licoes-aprendidas.md | |
templates/github/pull_request_template.md | .github/pull_request_template.md (somente GitHub; para projeto com tracker Azure não crie .azuredevops/ — registre como pendência futura) | |
templates/docs/review-area.md | docs/review.md (só se não existir; nunca sobrescrever arquivo existente) |
The thresholds template now carries learned_rules (the loop's governing knobs), so the first row installs the knob block with the thresholds. The ledger itself is the separate row above. Bootstrap also installs the project-local dependency ledger as a fresh starting point. These ledgers contain no history, approvals, or rules from another project; they are owned by the target project after install. Bootstrap also provisions agent-os/skills-proposals/ for project-local skill proposals mined from failure traces.
Install the thresholds file at Phase A, with every metric observe except regression_suite. The memory_available metric is retired. Never carry another project's numbers into this one. The global template is a reusable source only and owns no project tree. After bootstrap, recommend harness-project-calibration: calibration is the project rollout boundary and derives the repository's own thresholds, high-risk paths, and tool-availability list from its layout and history, then writes that project's agent-os/quality-thresholds.json.
The redteam_findings and dependency_cooldown rows remain observe-only with null baselines until calibration replaces them with measurements from the target repository.
The bypass_findings metric is installed in observe with a null command by default (like skill_lint). The skill_lint metric is observe with a null command by default; projects that ship skills set commands.skill_lint to: node "<home>/.omp/agent/scripts/harness-skill-lint.mjs" --root . --json (the linter resolves agent/skills or .omp/skills; --global lints ~/.omp/agent/skills); red-team allowlist entries are content-hash keyed, require reason/allowedBy/expires, and are an operator decision, never an agent's.
Workflow
- Detect repo root and existing files.
- Run
harness-stack-routerto identify stack signals. - Run
harness-startup-pathto find startup/verification commands. - Compare target files with global templates in
~/.config/opencode/templates. - Print a change plan: create, merge, skip, or preserve.
- Authorization check:
- If invoked via
novo-projeto: explicit authorization to create and onboard the project is already granted; proceed directly. - If invoked directly: Ask:
Apply this full harness to the current repo? yes/no. If no, stop with the plan only.
- Create missing directories and write template files from
templates/into the repo, strictly preserving existing files and proposing merges where appropriate. - Execute shared onboarding CLI:
node "<harnessHome>/scripts/harness-project-onboarding.mjs" --root "<path-to-repo>" --write. - Run discovered startup verification if safe.
- End with next recommendation:
harness-project-calibration(to derive project-specific baselines). Recomendarcerebro-carga-inicialquando o projeto estiver registrado em~/.task-pipeline/projects.json, enovo-projetoquando não estiver; ou/harness-session-start.
Rules
- Never write before confirmation (unless pre-authorized by
novo-projeto). - Always install the full package, not minimal modes. The shared CLI complements the package; it does not replace full template installation.
- Preserve project-specific content, existing blockers, and operator configuration.
- If a file exists, propose a merge instead of overwriting.
- Do not assume
init.ps1,feature_list.json, or.specs/project/STATE.mdexist. - No tests or history means an explicit gap with the status returned by the tool (
unavailableornot_applicable), never an invented test or fake passing suite.
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingomp/agent/skills/harness-bootstrap/SKILL.md
Popularity
- 7-day trend score
- 5
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/maicongambini/omp-harness-guide/harness-bootstrap)