Miosa-osa

Miosa-osa/OSA

Agent

Fast, cheap read-only codebase exploration — file search, code search, architecture mapping.

Miosa-osa/OSA

Agent

Fast read-only codebase exploration — file search, code search, architecture analysis.

Miosa-osa/OSA

Agent

General-purpose agent for researching complex questions, searching code, and executing multi-step tasks.

Miosa-osa/OSA

Agent

Offensive security operator — runs live penetration tests against authorized targets, executes recon, exploitation, and evidence capture in isolated sandboxes.

Miosa-osa/OSA

Agent

Performance analysis — profiling, bottleneck identification, optimization.

Miosa-osa/OSA

Agent

Read-only implementation planning — explores the codebase and produces a step-by-step plan without changing anything.

Miosa-osa/OSA

Agent

Implementation planning specialist — architecture design, step-by-step plans, dependency analysis.

Miosa-osa/OSA

Agent

Reconnaissance specialist — subdomain enumeration, port scanning, service fingerprinting, OSINT, attack surface mapping. Runs fast parallel recon and returns structured findings.

Miosa-osa/OSA

Agent

Code refactoring without behavior change — extract, rename, simplify, dedup.

Miosa-osa/OSA

Agent

Research agent — web search, documentation analysis, technology comparison.

Miosa-osa/OSA

Agent

Security vulnerability scanner — OWASP Top 10, auth, injection, secrets detection.

Miosa-osa/OSA

Agent

Independent vulnerability validator - reproduce or reject one candidate. Never trust the parent.

Miosa-osa/OSA

Agent

Tests, coverage, edge cases, validation, QA.

Miosa-osa/OSA

Skill Claude CodeCodex

Diagnose broken, failing, incorrect, flaky, or unexpectedly slow software. Use whenever a user reports a bug, regression, crash, hang, visual defect, or unexplained behavior, even if they ask directly for a fix.

Miosa-osa/OSA

Skill Claude CodeCodex

Decompose a large task into DISJOINT file-owned workstreams, fan out isolated full-power peers, collect structured reports, run ONE authoritative gate, and commit when green — the collision-free, self-verifying multi-agent flow. Ultra-gated.

Miosa-osa/OSA

Skill Claude CodeCodex

Build, debug, review, or polish user interfaces with responsive layout, accessibility, and pixel-level visual verification. Use for frontend components, browser UI, terminal UI, resize defects, visual regressions, and interaction problems.

Miosa-osa/OSA

Skill Claude CodeCodex

Implement a requested feature or change completely in an existing codebase. Use for multi-file coding tasks, specifications, acceptance criteria, and requests to build or modify behavior rather than merely explain it.

Miosa-osa/OSA

Skill Claude CodeCodex

Recover the work a fleet wave dropped when two parallel nodes edited the same file — read each claimant's version out of its worktree, reconcile them into one correct file, and re-run the authoritative gate instead of re-running the wave.

Miosa-osa/OSA

Skill Claude CodeCodex

Full-scope penetration testing — reconnaissance, vulnerability discovery, exploitation, post-exploitation, and reporting against authorized targets. Covers network, web app, API, and host pentesting.

Miosa-osa/OSA

Skill Claude CodeCodex

Review code, configuration, permissions, authentication, data handling, and dependencies for exploitable security weaknesses. Use for security reviews, threat analysis, trust boundaries, secrets, authorization, sandboxing, and dangerous command handling.

Miosa-osa/OSA

Skill Claude CodeCodex

Create or improve reusable OSA skills with progressive disclosure, precise selection descriptions, supporting resources, and realistic evaluations. Use when users ask to create, package, test, optimize, or maintain a skill or skill library.

Miosa-osa/OSA

Skill Claude CodeCodex

Build features and bug fixes test first using a strict red, green, refactor loop. Use for TDD requests, regression tests, behavior changes with clear acceptance criteria, and risky logic that benefits from executable specification.