Plugin Claude Code
Plugin marketplace listing 1 plugin: kk.
Plugin Claude Code
Plugin marketplace listing 1 plugin: kk.
Settings file Claude Code
Agent settings declaring 10 allowed tools.
MCP server Claude CodeCodexCursor +2
MCP server "capy" as configured in serpro69/claude-toolbox. Launched with bash .claude/scripts/capy.sh serve.
Instructions file CodexOpenCode
AGENTS.md instructions for serpro69/claude-toolbox, covering agents.md, repository overview, architecture, codex support and testing.
Instructions file
Claude Code instructions for serpro69/claude-toolbox, covering claude.md, repository overview, architecture, codex support and testing.
Plugin Claude Code
kk. Minimal by design, explicitly multi-lang, production-ready and battle-tested collection of configs and plugins for your Claude Code agentic development workflows: mcp, configs, skills, agents and more.
Agent
Agent with a model override in the manifest.
Agent
A test agent for validation.
Skill Claude CodeCodex
Profiles at ${CLAUDEPLUGINROOT}/profiles/go/.
Agent
A fixture agent definition. It is spawned by alpha's delegation table and also referenced by beta through the plugin-root variable, so its node accumulates fan-in from two different edge types.
Skill Claude CodeCodex
Alpha links a shared instruction directly, delegates to a peer skill, and spawns a review agent. Together these exercise the markdown-link, symlink (via the sibling shared-common-helper.md), skill-invocation, and agent-delegation edges.
Skill Claude CodeCodex
Beta reaches shared resources through the plugin-root variable, which exercises the template-ref (concrete suffix) and parameterized-nav ( expansion) edges. Its dangling link is the fixture's intentional broken edge.
Skill Claude CodeCodex
A Go security skill for reviewing code.
Skill Claude CodeCodex
Go testing best practices.
Plugin Claude Code
Development workflow skills, commands, and hooks from claude-toolbox.
Agent
Independent code reviewer with no authorship attachment. Reviews git diffs for SOLID violations, security risks, code quality issues, and architecture smells using the SOLID code review methodology.
Agent
Independent design document reviewer with no authorship attachment. Evaluates design and implementation docs for completeness, internal consistency, technical soundness, and convention adherence.
Agent
Independent skill-eval grader with no review authorship and no fixture access. Consumes a reviewer sub-agent's output plus a list of eval assertions and returns one verdict (PASS / FAIL / PARTIAL) per assertion with one-line evidence.
Agent
Resolves active profiles and their checklist-load decisions for a given diff, using the shared profile-detection procedure. Emits a structured resolution report: active profiles with per-file triggeredby signal, plus loaded vs. not-loaded checklists with Load-if reasoning. Useful wherever profile detection must be…
Agent
Independent spec conformance reviewer with no authorship attachment. Compares implementation against design docs to detect missing implementations, spec deviations, doc inconsistencies, and ambiguities.
Hook
Runs when a session starts, executing set-plugin-root.sh via bash. From serpro69/claude-toolbox.
Hook
Runs before the agent uses a tool for Bash tool calls, executing validate-bash.sh. From serpro69/claude-toolbox.
Skill Claude CodeCodex
Apply Chain-of-Verification (CoVe) prompting to improve response accuracy through self-verification. Use when complex questions require fact-checking, technical accuracy, or multi-step reasoning.
Skill Claude CodeCodex
TRIGGER when: adding or upgrading any dependency — library, SDK, framework, API, IaC API version (K8s/Terraform/Helm), CRD, or container image. Use BEFORE writing the call. Forces context7/capy lookup instead of guessing.