Agent
Tailors omp to a specific repo — the per-project setup device. Introspects a repository's real stack statically (never executing configs): languages, framework, monorepo layout, test/build/lint commands, dev ports, and data layer; then generates or updates a tailored /.omp/ so omp fits THIS repo (LSP rootMarkers for…
Agent
Senior QA / SDET — the test-strategy producer for a lean team. Designs the test pyramid, finds coverage gaps, and WRITES real tests that defend an observable contract and fail on a plausible bug — edge / boundary / invariant / transition / precedence, negative + error-path, deterministic + isolated + full-suite-safe.…
Agent
Senior application-security engineer — audits and hardens auth, access control, and data handling. Covers authn/authz (JWT/session/OAuth, IDOR, least-privilege), OWASP Top-10 (injection/XSS/SSRF/CSRF/broken-access), input validation + output encoding, secrets handling (no hardcoded keys, env/.env hygiene), dependency…
Agent
Senior technical writer — owns developer-facing documentation: README (a quickstart that actually runs), API docs (endpoints, params, examples, error responses), ADR prose, onboarding guides, runbooks (step-by-step incident response), CHANGELOG (Keep a Changelog format), and docstrings/comments that explain WHY, not…
Agent
Verifies a frontend UI change in a real browser with Playwright before it is reported done. Checks scroll containment, viewport fit, primary-button reachability (e.g. the save button stays reachable inside the scroll area), selection-state sync between a sub-component and its parent preview, and console errors. Use…
Agent
Senior UX writer — owns microcopy (buttons, labels, tooltips, empty/loading/error states), UX writing in the product's language (natural phrasing, honorific/register consistency, concise + scannable), error messages (what happened + how to fix it, no blame/no jargon), tone + voice consistency, i18n keys, and…
Skill Claude CodeCodex
Use when verifying accessibility (WCAG 2.2 AA) of a rendered UI in a real browser before reporting done — the omp-native replacement for the chrome-devtools a11y plugin. Runs a concrete ordered checklist with omp's builtin browser tool (open tab → tab.evaluate DOM query / elementFromPoint / getComputedStyle /…
Skill Claude CodeCodex
Use when verifying a chrome-extension/ change before reporting done. The canonical 7-check list (build → Service Worker vm.createContext compat → manifest sanity → per-site content-script DOM contract → message-passing trace → test suite → manual-load checklist) + verdict rules. chrome-extension/ is a strong-guard…
Skill Claude CodeCodex
Use when verifying data-shape claims against a real store — MongoDB or a SQL store (SQLAlchemy / SQLite / Postgres) — before reporting any data-touching change done. Detects the store from repo config, then runs the canonical checks (existence count, type distribution, 10-row/doc sample, index or owner crosscheck) and…
Skill Claude CodeCodex
Use when building or hardening an LLM feature — prompt design, RAG, eval harness, model/provider selection, guardrails, and token/cost budgeting — with omp-native tools (bash for real API round-trips, read/grep for the repo's own client, no vendor-plugin dependency, provider-agnostic). PRIME RULE — no LLM feature is…
Skill Claude CodeCodex
Use when investigating or optimizing performance in a real browser/build/DB before reporting a fix — the omp-native replacement for the chrome-devtools LCP/memory-leak plugins. Ordered MEASURE-before-and-after methodology (Core Web Vitals → LCP breakdown → bundle → render → DB query → caching → memory leaks) driven by…
Skill Claude CodeCodex
Use when verifying a frontend UI change in a real browser before reporting done. The canonical 7-check list (real auth → render≠behavior → scroll containment → primary-button reachability → selection-state sync → responsive → console) + environment fail-fast rule (transport-unreachable vs HTTP error distinction) +…
Agent
Fresh-context architecture-fit critic — reviews a diff against the project's stated architecture (its ARCHITECTURE.md / the CLAUDE.md spine / ADRs) and an architecture-smell taxonomy: layer compliance, smell delta, domain invariants, reuse-before-build, throwaway-vs-durable intent, blast radius of the touched module…
Agent
Independently verifies that a code change is actually complete before it is reported done. Confirms every callsite of a changed signature was updated, runs the affected tests, and finds missing wiring (a new field/component/ endpoint that is never consumed). Use before claiming a migration, interface change, or…
Agent
Independently falsifies a TERMINAL / analytical claim before it is stated as a conclusion — "X is the limit / ceiling", "this is impossible", "the context is sufficient", "this fully solves it", "no effect". Checks whether the claim was MEASURED or merely asserted, names the measurement that would falsify it, and…
Agent
Independent critic for an INCOMING multi-step instruction, before any work starts. Audits the request against three cores — ① ambiguity ② scope ③ is this the real problem — plus repo grounding (a mentioned PR# / file / field actually exists and isn't already done). Use on a non-trivial instruction, or when the user…
Agent
Tracks a pull / merge request toward a mergeable state — but it does NOT assume any particular PR workflow. It DISCOVERS the repo's actual setup (host, CI, reviewers, bots) at runtime, honors a per-repo prworkflow config for intent it can't infer, and degrades gracefully when something isn't there. Use after opening /…
Agent
Critic for a HUMAN-FACING output (a report / summary / dashboard / scorecard): can a person actually make a DECISION from it? Readable labels, actionable rows, no jargon-only descriptions. Use before shipping a human-facing surface, or when the user says "가독성 검토", "사람이 판단할 수 있어?", "내가 판단할 게 없잖아", "can a human decide…
Agent
Independent critic for a SPEC / DESIGN / plan ARTIFACT — does it actually solve the user's ORIGINAL stated requirement, or has it drifted to an easier/adjacent problem? Catches drift at the artifact stage, before code is built on a drifted premise. Use after a spec/design is drafted, or when the user says "이거 내가 시킨 거…
Agent
Independently checks a PR's diff against what its active spec REQUIRED — did the change deliver the spec's scope, silently exceed it, or skip a plan task it claims to close? If the PR has NO spec (hotfix / doc-only), it NO-OPS and never blocks. Use at PR time, or when the user asks "스펙대로 됐어?", "범위 넘었어?", "did this…
Agent
Runs Kent Beck's red → green → refactor loop end-to-end for a single behavior change and returns one green-with-evidence verdict. Writes the failing test FIRST, runs it to confirm red, implements the minimum to go green, then refactors. Use when the user wants a behavior built/fixed test-first hands-off, or says "TDD…
Hook
Runs before the agent uses a tool for Bash tool calls, executing protected-branch-guard.sh. From jhlee0409/omni-harness-kit.
Hook
Runs when the agent finishes a response, executing verify-loop.sh. From jhlee0409/omni-harness-kit.
Skill Claude CodeCodex
Record an architecture / cross-cutting decision as the next numbered ADR under docs/adr/. Use when a non-obvious or hard-to-reverse decision is made (a module boundary, a trade-off, a tech choice), or when the user says "record an ADR", "ADR 남겨", "이 결정 기록", "document this decision".