claudius

Plugin claudius from marketplace lklimek in lklimek/agents. Commands read from the repo's manifest — 2 days ago.

Skills (22)

• architecture

  This skill should be used when the user asks to \"design the architecture\", \"evaluate this library\", \"compare these technologies\", or \"check this plan\", or when work needs system design, module boundaries, architectural trade-offs, dependency review, or validating an implementation plan again

• bug-investigation

  This skill should be used when investigating a reported bug, diagnosing a failure, or performing root-cause analysis — especially before concluding \"not a bug\", tracing a symptom, or explaining unexpected behavior. It makes the reported observation the ground truth to reproduce and traces from the

• bye

  This skill should be used when the user says \"bye\", \"wrap up\", \"tear down\", \"we're done\", or otherwise ends the session. It shuts down spawned teammates and agents, removes their worktrees, and reconciles uncommitted or unpushed session work.

• check-pr-comments

  Fetches a PR's review comments, verifies each against the current code, presents a per-comment decision table, and — after the user's decisions or in fix mode — fixes, replies to, or resolves threads. This skill should be used when the user asks to \"check PR comments\", \"verify review comments are

• coding-best-practices

  This skill should be used when developing, modifying, reviewing, or testing code in any language. It defines the project rules for TDD, self-review, quality-tool timing, comments, logging levels, review output, and the Rust policy (typed thiserror errors, cargo wrapper discipline). MANDATORY for eve

• delegate

  This skill should be used before delegating work to an agent (one spawn or a whole wave) and when the user says \"spawn an agent\", \"delegate this\", \"parallelize this\", \"use a subagent\", \"send this to Codex\", or \"use Codex Astra\". It covers the spawn decision (inline vs spawn, model tier,

• dependabot-merge

  This skill should be used when the user asks to \"merge dependabot PRs\", \"process dependency bumps\", \"auto-merge bot PRs\", or \"handle the dependabot backlog\". It audits each dependency, comments findings, merges when CI is green, and requests rebases for conflicts or CI failures.

• git-and-github

  This skill should be used when running git or gh commands, interacting with GitHub, resolving git and gh access or permission-denied failures, or when the user says \"push\" or asks to \"commit and push\", \"create a PR\", \"ship this\", \"open a pull request\", or \"publish this branch\". It define

• grand-admiral

  This skill should be used when coordinating multiple agents — running a coordinator session, isolating agent worktrees, managing teammates, verifying and merging agent work, recovering stalled or silent agents, or managing a programme across projects. Coordinator agents that spawn, manage, or merge

• lessons-learned

  Extracts reusable knowledge from the current session, filters it through a quality gate, and saves it to persistent memory (MemCan). This skill should be used when extracting learnings, saving lessons, or capturing reusable knowledge from a session. It is also appropriate before presenting a plan, a

• merge-base

  This skill should be used when the user asks to \"merge the base branch\", \"update this feature branch from base\", or resolve conflicts while merging base into a feature branch. It merges (never rebases) the remote base, resolves conflicts without waiting for approval, and reports the resolutions

• product-design

  This skill should be used when the user asks to \"write user stories\", \"gather requirements\", \"design the UI flow\", or \"check accessibility\", or when work needs domain analysis, stakeholder mapping, interaction design, usability, API developer experience, or validating a plan against user nee

• release

  This skill should be used when the user asks to \"bump the version\", \"cut a release\", or \"create a GitHub release\". It applies SemVer 2.0, updates the changelog, commits, pushes, creates the release, and auto-detects Rust, Python, JS/TS, Claude Code plugin, and other supported stacks. Arguments

• report-format

  This skill should be used when emitting or consuming review findings. It defines the finding JSON shape (schema v4), the fields producers must and must not emit, and the ID prefixes, for every finding-producing agent.

• review-changes

  This skill should be used when the user asks for a \"code review\", \"review this code\", \"review my changes\", \"review this branch\", \"basic review\", \"full review\", or \"grumpy review\", to \"validate findings\" in a report.json, or before completing changes of at least 50 code lines per codi

• review-dependency

  This skill should be used when the user asks to \"review a dependency update\", \"audit this dependency bump\", or assess the security of an upgraded or newly added dependency. It reconciles the documented change against the real upstream diff, audits the changed source, checks our usage, and return

• review-pr

  This skill should be used when the user asks to \"review this PR\", \"audit this pull request\", or assess a PR for code quality, security, and correctness. It gathers context, verifies the PR description against the diff (Pass C), runs basic review by default (full on request), and prepares a summa

• security-best-practices

  This skill should be used when reviewing or writing code that handles authentication, cryptography, untrusted input, secrets, deserialization, or API endpoints, and before a security review of Rust, Go, Python, or TypeScript code. It routes to language-specific pitfall references that go beyond gene

• severity

  This skill should be used when rating findings in reviews, audits, and assessments, or deciding whether a finding blocks a merge. It defines the backstop zones, blocker gates, the likelihood/impact/relevance floats, severity bands, and merge classes. Load explicitly before producing findings.

• technical-writing

  This skill should be used when the user asks to \"write the docs\", \"update the README\", \"document this API\", \"write an ADR\", or \"review the documentation\", covering READMEs, API documentation, tutorials, migration guides, changelogs, ADRs, runbooks, and contributor documentation.

• triage-findings

  This skill should be used when the user explicitly asks to \"triage findings\" through an interactive browser-based workflow. Only invoke when explicitly requested.

• triage

  This skill should be used when the user says \"triage\" or asks to triage a GitHub issue: reproduce it, identify the root cause and owning component, estimate severity, discuss the findings with the user, and then post a short status comment.

Subagents (8)

• architect-nagatha

  Use for system design, module boundaries, dependency review, architectural trade-offs, technology evaluation, library comparison, or validating plans before presenting to user. Nagatha identity; follows the architecture skill.

• claudius

  Use as the personal software development assistant that leads and coordinates development efforts; always invoked when user interaction is needed. Claudius identity; follows the grand-admiral skill.

• developer-bilby

  Use for code changes in any language (Rust, Python, Go, TypeScript/JS, frontend): features, bug fixes, and tests. Implementation only, never code review. Bilby identity; follows coding-best-practices.

• project-reviewer-adams

  Use to check whether a change is a local optimum — a workaround fixed in the wrong layer or repository (e.g. UI patch for an SDK bug) — across the project and the organization's sibling repos, and whether new code or tests duplicate existing ones (DRY). Does not modify reviewed code (writes reports

• qa-engineer-marvin

  Use to validate code against requirements, or for adversarial correctness and cross-artifact consistency review (code, configs, docs, tests) — independently verifies claims rather than trusting the diff. Audits and writes missing tests, reports all mismatches. Marvin identity; follows review-changes

• security-engineer-smythe

  Use for security audits, auth/crypto/input validation reviews, dependency scanning, secret detection, or validating plans before presenting to user. Smythe identity; follows security-best-practices.

• technical-writer-trillian

  Use for creating, maintaining, or reviewing documentation — READMEs, API docs, tutorials, guides, changelogs, ADRs. Trillian identity; follows technical-writing.

• ux-designer-diziet

  Use at project start for requirements, domain analysis, stakeholder mapping, or during design for UI flows, interaction patterns, usability, accessibility, and validating plans before presenting to user. Diziet identity; follows product-design.

Hooks (3)

• PreToolUse

  bash ${CLAUDE_PLUGIN_ROOT}/hooks/cargo-discipline.sh

• SessionStart

  bash ${CLAUDE_PLUGIN_ROOT}/hooks/session-start.sh

• SessionStart

  python3 ${CLAUDE_PLUGIN_ROOT}/scripts/origin_freshness.py

Similar plugins