maicongambini/omp-harness-guide/harness-initializer

Claude Code and agent skill by maicongambini/omp-harness-guide

Trust tier 2
  • community
LLM review pending
Source check pending

Checking that the SKILL.md file is still in the repository.

Conducts a non-destructive audit of harness readiness. Use when assessing a repo before harness setup to inspect conventions. Do NOT use for installing files (use harness-bootstrap).

Install

npx vskill@latest install maicongambini/omp-harness-guide/harness-initializer

SKILL.md

The same SKILL.md was published earlier as maicongambini/omp-harness-guide/harness-initializer.

Harness Initializer

Audit any project before writing. Propose before creating. Write only with explicit user approval.

When to Use

Use for /harness-init, new projects, missing harness artifacts, or before declaring harness maturity complete.

Audit Sequence

Run in order from the current project root. Record each result. Do not create files during audit.

  1. Repo root — locate .git, package files, or current directory. If unknown, say unknown.
  2. Entry — AGENTS.md, CLAUDE.md, README.md, or no root instructions?
  3. Context — docs/ARCHITECTURE.md, docs/PRODUCT.md, docs/RELIABILITY.md present or missing?
  4. State — find feature_list.json, .specs/features/*/tasks.md, .specs/project/STATE.md, docs/harness/progress.md, or agent-progress.md. Also check for agent-os/learned-rules.json (learned rules ledger), agent-os/prevc-autonomy.json (PREVC autonomy policy: verificar se existe e se autoConfirm é false; aviso se true), agent-os/project-profile.json (verificar se fixLoop.maxAttempts <= 3), and docs/harness/session-handoff.md.
  5. Feedback & Review — find init.ps1, init.sh, make check, package scripts, test/build/lint commands, or none. Check if agent-os/quality-thresholds.json exists and which commands are wired (bypass_scan, skill_lint, redteam). Check if docs/review.md exists and contains real critical failures. Check if .github/pull_request_template.md (or docs/pull-request.md) exists and contains the 4 required sections (O que muda e por quê, Tier, Testing, Como reverter). Check if the review role in config.yml uses a different model family from implement.
  6. Evaluation — find agent-os/judges/, project rubrics, CI checks, or none.
  7. Skills & Evolution — find project .opencode/skills/harness-* and global harness skills. Also check for agent-os/skills-proposals/ (project-local skill proposals mined from failure traces).
  8. Fresh-session test — answer from files only:
  • What does this repo do?
  • How is it organized? (architecture)
  • How do I start and verify it?
  • What is currently unfinished?
  • What is the next task?
  • What decisions were made and why?

Output

Produce a table. Then stop. Do not create files.

LayerArtifactStatusGapRecommended Fix
Review.github/pull_request_template.mdPresent/MissingMissing 4 required sectionsInstall PR template with required sections
Reviewdocs/review.mdPresent/MissingGeneric checklist, no real critical failuresPopulate real area critical failures
Autonomyagent-os/prevc-autonomy.jsonPresent/MissingMissing or autoConfirm: trueEnsure autoConfirm: false
Profileagent-os/project-profile.jsonPresent/MissingfixLoop.maxAttempts > 3Set fixLoop.maxAttempts <= 3
Rolesconfig.ymlCheckedreview uses same model family as implementConfigure distinct model family for review

Then propose a minimal bootstrap plan and ask approval before writing anything.

Rule

Do not assume init.ps1, feature_list.json, .specs/project/STATE.md, or zharnessengineering/ exist. If a discovered startup command fails, make that the first fix unless the user asks for an audit-only report. Context layer gaps are non-blocking — flag them but continue the audit.

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

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
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/maicongambini/omp-harness-guide/harness-initializer/badge)](https://verified-skill.com/skills/maicongambini/omp-harness-guide/harness-initializer)

Something wrong with this skill or its page? Tell us.