A framework for building deterministic CLI tools that Claude Code shells out to. Universal primitives + a marketplace convention for service wrappers.
Skill Claude CodeCodex
Reviews code for quality, bugs, security, and best practices. Use when changing code or before merge. Checks security, authentication, and validation; ensures new code follows project rules and conventions.
Skill Claude CodeCodex
Expert test writer for unit, component, E2E, and integration tests. Writes only high-value tests — branching, side effects, transactions, corner cases. Use for TDD or filling coverage gaps. Never writes tests for constants, single pass-throughs, or thin wrappers. Adapts to the project's test framework and conventions.
Skill Claude CodeCodex
A pure-markdown skill that gives Claude Code precise triggers for when to offer to install agent-plus on a user's behalf, plus the safety rails for how. No bin, no Python — the skill is the documentation; the agent is the runtime.
Skill Claude CodeCodex
The meta plugin. Eight+ subcommands across init, envcheck, refresh, list, extensions, marketplace, doctor. JSON output only. Use at session start to give the agent day-one context — installed plugin set, env-var readiness, resolved project IDs — without grep-mining the project for every fact.
Skill Claude CodeCodex
Trigger doctrine for when to check whether the agent-plus framework itself is out of date, and how to offer the fix — same shape as agent-plus-installer, but for the upgrade path instead of the install path. No new mechanism: agent-plus-meta upgrade-check and agent-plus-meta upgrade already exist, fully built, with a…
Skill Claude CodeCodex
Structured triage of a git diff. One call replaces the per-file Read sweep an agent normally does to figure out which files in a diff are tests, which touch the public API, which are migrations, which need careful review.
Skill Claude CodeCodex
The map, not the contents. One call replaces the cold-start dance — file-tree exploration, finding entrypoints, reading every manifest, scanning README. Session mining showed 67 grep + 60 ls ops on a typical fresh-repo session, almost all of it answerable from one structured payload.
Skill Claude CodeCodex
Append-only self-assessment log for Claude Code skills. The agent rates its own use of a skill; the rating lands in /.agent-plus/skill-feedback/ .jsonl (user-global), never on a network. Skill authors run report to aggregate, or submit to bundle into a GitHub issue body for the skill's source repo.
Skill Claude CodeCodex
The fifth universal primitive of agent-plus. Turns repeated Bash patterns from real Claude Code sessions into project-scoped Claude skills, audits the skills you already have, and feeds back two streams of evidence (explicit ratings + implicit failure signals) into one quality loop.
Skill Claude CodeCodex
A sample skill fixture used by inquire's skill-target detection tests.