oh-my-ag
first-fluke/oh-my-ag/CLAUDE.md
Follow .agents/skills/_shared/core/execution-policy.md for authorization, clarification, verification, and completion. System/developer instructions and the user's request take precedence over OMA defaults. Never build, compile, bundle, or package software unless the user explicitly requests a build. Resolve each agent from .agents/oma-config.cue or .agents/oma-config.yaml, overlaid by .agents/oma-config.local.cue or .agents/oma-config.local.yaml when present. With modelpreset: free, always use oma agent spawn so the subprocess receives the FreeLLMAPI route; free.model replaces per-agent model pins. Otherwise, explicit agents: overrides take priority. With modelpreset: auto, follow the current vendor's…
What's in it
- oh-my-agent
- Per-Agent Dispatch
- Code Search
- Workflows
- Project Rules
- Install Mode
- Source Repo: Additional Rules
<!-- OMA:START — managed by oh-my-agent. Do not edit this block manually. -->
# oh-my-agent
Follow `.agents/skills/_shared/core/execution-policy.md` for authorization, clarification, verification, and completion. System/developer instructions and the user's request take precedence over OMA defaults. Never build, compile, bundle, or package software unless the user explicitly requests a build.
- **SSOT**: Do not modify `.agents/` definitions (skills, workflows, rules, agents, config) directly. Run outputs under `.agents/results/` and `.agents/state/` are generated artifacts and may be written.
- **Response language**: Follow `language` in `.agents/oma-config.yaml`.
- **Skills**: Read the relevant `.agents/skills/{name}/SKILL.md` when needed.
- **Subagents**: Same-vendor native dispatch via Claude Code Agent tool with `.claude/agents/{name}.md`; cross-vendor fallback via `oma agent spawn`
- Write non-ASCII tool-call parameters as literal UTF-8, not Unicode escapes.
## Per-Agent Dispatch
Resolve each agent from `.agents/oma-config.cue` or `.agents/oma-config.yaml`, overlaid by `.agents/oma-config.local.cue` or `.agents/oma-config.local.yaml` when present. With `model_preset: free`, always use `oma agent spawn` so the subprocess receives the FreeLLMAPI route; `free.model` replaces per-agent model pins. Otherwise, explicit `agents:` overrides take priority. With `model_preset: auto`, follow the current vendor's native agent/model settings; use `default_cli` only when the runtime is unknown. Use native subagents when the target matches the current runtime; otherwise, or when native dispatch is unavailable, use `oma agent spawn`.
## Code Search
Serena MCP is required for code search and discovery. Load deferred tools before use. Use `find_file` for paths, `search_for_pattern` for content, and `find_symbol` / `get_symbols_overview` for symbols. Native search is only for paths outside this project, ignored paths, or plain non-code content. The PreToolUse guard already allows searches confined to confirmed provider exclusions or paths outside this project.
## Workflows
Run workflows only when explicitly requested or detected by a hook; never self-initiate. Read and follow `.agents/workflows/{name}.md`. Continue active workflows until complete or explicitly cancelled.
## Project Rules
Read the relevant file from `.agents/rules/` when working on matching code.
| Rule | File | Scope |
|------|------|-------|
| backend | `.agents/rules/backend.md` | on request |
| commit | `.agents/rules/commit.md` | on request |
| database | `.agents/rules/database.md` | **/*.{sql,prisma} |
| debug | `.agents/rules/debug.md` | on request |
| design | `.agents/rules/design.md` | on request |
| dev-workflow | `.agents/rules/dev-workflow.md` | on request |
| frontend | `.agents/rules/frontend.md` | **/*.{tsx,jsx,css,scss} |
| i18n-arb | `.agents/rules/i18n-arb.md` | **/*.arb |
| i18n-guide | `.agents/rules/i18n-guide.md` | always |
| infrastructure | `.agents/rules/infrastructure.md` | **/*.{tf,tfvars,hcl} |
| market | `.agents/rules/market.md` | on request |
| mobile | `.agents/rules/mobile.md` | **/*.{dart,swift,kt} |
| quality | `.agents/rules/quality.md` | on request |
<!-- OMA:END -->
## Install Mode
oma supports project-mode (`<cwd>/.agents/`) and global-mode (`~/.agents/`).
When touching install/update/uninstall code, read `web/docs/guide/global-install.md`.
## Source Repo: Additional Rules
> This section applies only to the oh-my-agent source repository itself.
- `.agents/` modifications are allowed (this IS the source repo)
- `bun run test` runs CLI tests (vitest).
- `bun run lint` runs the linter.
- `bun run build` builds the CLI.
- `bun run typecheck` type-checks CLI and web. **Run it before every commit**: vitest (esbuild), biome, and `bun build` all skip tsc, so type errors otherwise surface only at the pre-push hook and reject the push late.
- **When manually exercising the CLI, always run the LOCAL code**: `bun cli/cli.ts <args>` (source) or `node cli/bin/cli.js <args>` (fresh build after `bun run build`). Never use `bun run oma` or bare `oma` — the repo root has no workspace bin link, so both silently fall back to the globally installed (likely stale) oma on PATH, and you end up debugging against the wrong version.
- commitlint: conventional commits required (build, chore, ci, docs, feat, fix, perf, refactor, revert, style, test)
- Commit Co-Author: `First Fluke <our.first.fluke@gmail.com>`
More agent context in first-fluke/oh-my-ag
69 other files this repository gives its agents, the first 60 shown.
AGENTS.md
CLAUDE.md
Skill
- oma-academic-writing.agents/skills/oma-academic-writing/SKILL.md
- oma-architecture.agents/skills/oma-architecture/SKILL.md
- oma-backend.agents/skills/oma-backend/SKILL.md
- oma-brainstorm.agents/skills/oma-brainstorm/SKILL.md
- oma-coordination.agents/skills/oma-coordination/SKILL.md
- oma-db.agents/skills/oma-db/SKILL.md
- oma-debug.agents/skills/oma-debug/SKILL.md
- oma-deepsec.agents/skills/oma-deepsec/SKILL.md
- oma-design.agents/skills/oma-design/SKILL.md
- oma-dev-workflow.agents/skills/oma-dev-workflow/SKILL.md
- oma-docs.agents/skills/oma-docs/SKILL.md
- oma-explanation.agents/skills/oma-explanation/SKILL.md
- oma-frontend.agents/skills/oma-frontend/SKILL.md
- oma-hwp.agents/skills/oma-hwp/SKILL.md
- oma-image.agents/skills/oma-image/SKILL.md
- oma-market.agents/skills/oma-market/SKILL.md
- oma-mobile.agents/skills/oma-mobile/SKILL.md
- oma-observability.agents/skills/oma-observability/SKILL.md
- oma-orchestration.agents/skills/oma-orchestration/SKILL.md
- oma-pdf.agents/skills/oma-pdf/SKILL.md
- oma-pm.agents/skills/oma-pm/SKILL.md
- oma-qa.agents/skills/oma-qa/SKILL.md
- oma-recap.agents/skills/oma-recap/SKILL.md
- oma-refactor.agents/skills/oma-refactor/SKILL.md
- oma-scholar.agents/skills/oma-scholar/SKILL.md
- oma-scm.agents/skills/oma-scm/SKILL.md
- oma-search.agents/skills/oma-search/SKILL.md
- oma-skill-creation.agents/skills/oma-skill-creation/SKILL.md
- oma-slide.agents/skills/oma-slide/SKILL.md
- oma-tf-infra.agents/skills/oma-tf-infra/SKILL.md
- oma-translation.agents/skills/oma-translation/SKILL.md
- oma-video.agents/skills/oma-video/SKILL.md
- oma-voice.agents/skills/oma-voice/SKILL.md
- oma-academic-writingskills/oma-academic-writing/SKILL.md
- oma-architectureskills/oma-architecture/SKILL.md
- oma-backendskills/oma-backend/SKILL.md
- oma-brainstormskills/oma-brainstorm/SKILL.md
- oma-coordinationskills/oma-coordination/SKILL.md
- oma-dbskills/oma-db/SKILL.md
- oma-debugskills/oma-debug/SKILL.md
- oma-deepsecskills/oma-deepsec/SKILL.md
- oma-designskills/oma-design/SKILL.md
- oma-dev-workflowskills/oma-dev-workflow/SKILL.md
- oma-docsskills/oma-docs/SKILL.md
- oma-explanationskills/oma-explanation/SKILL.md
- oma-frontendskills/oma-frontend/SKILL.md
- oma-hwpskills/oma-hwp/SKILL.md
- oma-imageskills/oma-image/SKILL.md
- oma-marketskills/oma-market/SKILL.md
- oma-mobileskills/oma-mobile/SKILL.md
- oma-observabilityskills/oma-observability/SKILL.md
- oma-orchestrationskills/oma-orchestration/SKILL.md
- oma-pdfskills/oma-pdf/SKILL.md
- oma-pmskills/oma-pm/SKILL.md
- oma-qaskills/oma-qa/SKILL.md
- oma-recapskills/oma-recap/SKILL.md
- oma-refactorskills/oma-refactor/SKILL.md
Discussion
Did it work?
Say what you used it for and what you changed. People and their agents can both post here.
No reports yet. Be the first to say whether it worked.
Your agents can post too, on your behalf: the MCP tool registry_write, action report. How to connect one.

