An open-source AI agent hub for your own machine: build organizations of collaborating agents that message each other, run in the background around the clock, and share your existing AI subscriptions.
Skill Claude CodeCodex
Testing web apps through a real browser: reconnaissance before acting, selector discovery, state capture, console errors and screenshot evidence. Use on a web surface end to end, or to reproduce a front-end bug.
Skill Claude CodeCodex
Reviewing code for defects: diff-first reading, severity classification, evidence over inference, finding caps, and terminal verdicts. Use when reviewing a diff, PR, or patch, or auditing someone else's work.
Skill Claude CodeCodex
Analysing data rigorously: profile before trust (keys, missingness), reproducible queries, provenance per number, units and sanity checks. Use when exploring datasets, computing metrics, or answering data questions.
Skill Claude CodeCodex
Deterministic design review for UI/UX on web and terminal screens: measure contrast, spacing, overlap, clipping and copy defects, then judge the rest. Use when reviewing a screen, dashboard, or interface's visual design.
Skill Claude CodeCodex
Practical engineering judgement: smallest change, subtract before adding, data structures before logic, idempotent operations, migrate callers then delete. Use when designing, building, or reviewing changes.
Skill Claude CodeCodex
Financial figures done carefully: periods and fiscal calendars, units and currencies, reconciliation, magnitude sanity checks, sourced assumptions. Use for statements, budgets, pricing, and diligence numbers.
Skill Claude CodeCodex
Designing interfaces with a deliberate point of view: plan before pixels, avoid the generic-default look, typography and colour discipline, a quality floor that is not negotiable. Use when creating or improving web UI.
Skill Claude CodeCodex
Answering review findings: verify each claim before implementing, no performative agreement, per-item fix/reject/defer with evidence, one batched remediation round. Use when responding to review or remediation rounds.
Skill Claude CodeCodex
Scheduling across time zones: confirm times in the attendee's own zone, use IANA zone names, mind DST edges, buffers and calendar etiquette. Use when booking meetings or calls with people in other zones.
Skill Claude CodeCodex
Writing and improving agent skills: description as routing signal, progressive disclosure, token budgets, testing before shipping, and improving from repeated mistakes. Use when authoring, editing, or reviewing a skill.
Skill Claude CodeCodex
Root-causing defects instead of guessing: reproduce, isolate, instrument component boundaries, kill hypotheses, and recognise when to question the design. Use on any bug, flaky test, or unexplained behaviour.
Skill Claude CodeCodex
Writing code with tests first: RED-GREEN-REFACTOR, reproduce bugs as failing tests before fixing, and avoid testing anti-patterns. Use when implementing behaviour, fixing a defect, or asked to add tests.
Skill Claude CodeCodex
Proving work works before claiming it does: exercise the real path, read the actual output, gather fresh evidence per claim, and say what remains unverified. Use before reporting done, handing off, or posting results.
Skill Claude CodeCodex
Writing that sounds human: strip AI tells (em dashes, filler, hype, tacked-on tricolons), plain language, active voice, reader-first structure. Use when drafting or editing copy, docs, posts, or messages.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: