tamirs-superpowers

Plugin tamirs-superpowers from marketplace tamirs-marketplace in Tamircohen28/tamirs-marketplace. Commands read from the repo's manifest — 6 days ago.

Skills (32)

• run-tamirs-superpowers

  Use when running, validating, or testing the tamirs-superpowers Claude Code plugin — checks JSON validity, shellcheck hooks, SKILL.md frontmatter, statusline output, hook wiring, and absence of hardcoded paths or internal references. Trigger phrases: ''run the plugin health check'', ''validate the p

• field-notebook-ui

  Use when a UI, explainer, dashboard, diagram or artifact should carry this repo's engineer's field-notebook look — warm stone-paper, hand-annotated margins, graph-paper grid. Trigger on: "field-notebook style", "warm stone-paper aesthetic", "the usual notebook look", "make it look like the field not

• diagnose-refusal

  Use when a coding-agent session refused, blocked, filtered, or returned HTTP 403/401/429 instead of

• targeted-debug

  Use when the user pastes a stack trace, traceback, panic, crash log, or error message with a

• decision

  Use when the user must pick between options — an agent has finished work and needs them to choose how to proceed, the user was told "waiting for your decision about X", or they say "display decision", "what''s the decision on/about X", "show me my options for X", "let me choose", "walk me through th

• deliver-dev

  Use when an integrated objective must become a delivery — ''deliver this objective'', ''ship it'', ''open the PR for objective X'', ''all tasks are done, create the PR'', ''turn the integration branch into a PR'', ''run the pre-PR gates'', ''review the combined diff and ship''. Not for driving an al

• diagnose-objective

  Use when an orchestrated objective failed, stalled or looks wrong and you need to know why from its state files — ''why did objective X fail'', ''diagnose the objective'', ''what happened to task-003'', ''the orchestration stalled'', ''a worker never handed off'', ''the integration branch is missing

• orchestrate-dev

  Use when an implementation request is bigger than one unit of work — a spec or plan file, a multi-part feature, a review doc with several items, ''implement all of this'', ''build X end to end'', ''do these N things'', ''orchestrate this'', ''run these in parallel'', ''split this across agents''. A

• plan-dev

  Use when informal work — a task, a feature request, a spec, a review doc, a list of features to implement — must become a structured plan before any code is written. Invoke for: ''plan this'', ''plan-dev'', ''break into phases'', ''break this into phases'', ''create issues for this'', ''decompose th

• pr-dev

  Use when an open PR must be driven to completion — ''finish this PR'', ''address review comments'', ''land the PR'', ''ship/land/close the PR'', ''drive PR #N to merge'', ''fix CI and merge'', ''clean up this PR'', ''the checks are red, get it green and merged'', ''pr-dev 42''.

• start-dev

  Use when a task must be implemented, built, coded or shipped — from a GitHub issue number, free-text task description, or spec file. Triggers: ''implement issue #N'', ''start coding X'', ''build the feature'', ''work on this spec'', ''create a PR for this'', ''ship issue #N'', ''code up the feature'

• switch-dev

  Use when switching AI coding platforms mid-task without losing context — Claude Code, Cursor, Codex, Gemini CLI, OpenCode. Triggers: switch agent, hand off issue, resume issue, rate limited — switch platform, continue on Cursor, continue on Gemini, continue in OpenCode, pick up where I left off, upd

• worker-dev

  Use when executing exactly ONE task inside an objective already planned by orchestrate-dev — ''run task-002'', ''do your assigned task'', ''implement task-001 of objective X'', ''work this task and hand off'', ''resume task-003'', or a task-NNN.json exists under .dev-files/objectives/. A whole user

• changelog-review

  Use when a Claude Code plugin project needs auditing against live official docs — hooks.json,

• dark-terminal-doc

  Use when a single-file HTML technical document should carry a dark developer / terminal aesthetic — monospace, terminal-green on near-black. Trigger on: "dark terminal doc", "terminal-style HTML", "developer-terminal aesthetic", "make it look like a terminal", "dark developer-facing HTML page", or a

• docs-review

  Use when README.md and docs/** need a full documentation audit — a sweep for broken links, stale

• platform-sync

  Use when this repo may have fallen behind the AI coding platforms it targets — Claude Code, Codex CLI, Cursor, Gemini CLI, OpenCode. Triggers: 'what new features am I missing', 'am I up to date with the latest docs', 'check my repo against the latest docs', 'is my plugin using current best practices

• mcp-builder

  Use when building or scaffolding an MCP (Model Context Protocol) server wrapping a REST API, database, or service as tools for an MCP client. Triggers on: ''build an MCP server'', ''create MCP tools'', ''write an MCP server for'', ''integrate X with Claude via MCP'', ''expose API via MCP'', ''add MC

• mcp-pagination

  Internal guardrail invoked by mcp-builder only — audits MCP tool schemas with list_*, search_*, find_*, get_all_* or SQL-executing operations for missing pagination, limit, offset or cursor parameters and unbounded results. Not for general MCP questions, single-item getters, or mutation-only tools.

• cleanup

  Use when the user wants to clean up, tidy, or reset a GitHub repo — even if they name only one part. Triggers: repo cleanup, repo housekeeping, prune merged branches, delete stale remote branches, tidy my worktrees, drive all open PRs to merge-ready, wipe build and cache artifacts, reset local check

• github-policy

  Use when a repository''s branch protection, rulesets, required checks, or PR-run cancellation may not match the canonical policy — never set up, hand-configured, or a merge blocked or allowed unexpectedly. Triggers: github-policy, branch protection, ruleset audit, required approvals, organization ru

• multi-agent-repo

  Use when auditing or setting up a repository for multi-agent development across Claude Code, Claude Desktop, Cursor, Codex, Gemini CLI, and OpenCode. Triggers: multi-agent repo, audit agent setup, AGENTS.md gaps, make this repo work with Claude and Cursor, add Codex, Gemini CLI or OpenCode support,

• repo-scaffold

  Use when creating a brand-new GitHub repository from scratch with production-ready infrastructure. Triggers: ''scaffold a repo'', ''create a new repo'', ''set up a new project'', ''new github repo'', ''bootstrap a project'', ''forge a repo'', ''/repo-scaffold'', ''start a new repo'', ''initialize a

• repo-standards

  Use when auditing or polishing a repository to Tamir Cohen standards — README badges, Makefile install/update/uninstall, docs tree, CI/CD, changelog and versioning policy, branch protection, employer IP scan, repo hygiene, multi-agent setup. Triggers: repo standards, polish this repo, prepare this f

• capture-config

  Use when a hand-edit to a global, machine-level agent config should become permanent everywhere — the user edited ~/.claude/settings.json, ~/.claude/CLAUDE.md, ~/.codex/AGENTS.md, ~/.cursor/, ~/.gemini/ or ~/.config/opencode/ by hand and says ''make this permanent'', ''save this to the repo'', ''kee

• find-skill

  Use when the user asks ''find a skill for X'', ''is there a plugin that does Y'', ''what skill should I use for Z'', ''recommend an agent for W'', ''compare skills for ...'', or ''search for a Claude Code skill''. Trigger words: find plugin, mcp server for, skill discovery.

• notify-setup

  Use when the user wants Claude Code to reach them on their phone, or phone notifications have stopped arriving — ''notify me on my phone when Claude needs me'', ''send notifications to my phone'', ''set up push notifications'', ''set up Pushover'', ''ping me when Claude needs input'', ''I keep missi

• plugin-config

  Use when the user types /plugin-config to view or change how much the plugin''s skills do without asking — the permission level (supervised, standard, unattended), a per-skill or per-group level, an allow/ask/deny for one action, resetting overrides, trusting a repository''s .tamirs-superpowers/perm

• retro

  Use when a session should become durable rules, hooks or memory — the user asks ('/retro', 'run a retrospective', 'postmortem', 'what went wrong this session', 'find friction', 'capture lessons', 'lessons learned'), OR a session is wrapping up after friction (repeated failures, rework, multiple corr

• session-report

  Use when the user asks what they are spending on Claude or where the tokens went. Triggers: ''session report'', ''token usage'', ''how many tokens'', ''what did that cost'', ''am I burning tokens'', ''cache hit rate'', ''why is this session so expensive'', ''which project costs most'', ''show my usa

• skill-creator

  Use when creating or improving an Agent Skill (SKILL.md) for Claude Code, Cursor, Codex, Gemini CLI or OpenCode, fixing a skill that isn''t triggering, or running skill evals/benchmarks. Triggers: ''make this a skill'', ''turn this into a skill'', ''write a SKILL.md'', ''my skill isn''t triggering''

• usage-capture

  Use when local Claude Code or OpenCode LLM requests should be recorded or inspected on this machine — daily JSONL usage logs, API body sidecars, latency bottlenecks. Triggers: 'usage capture', 'enable usage capture', 'local usage log', 'record LLM requests', 'LLM latency', 'which model was used', 'r

Subagents (10)

• architecture-reviewer

  Reviews architecture for unnecessary complexity, tight coupling, and layering violations, and proposes concrete simplifications. Use when adding a subsystem, before a large refactor, or when code feels over-engineered.

• debugging-specialist

  Root-cause analysis for bugs, test failures, and unexpected behavior — reproduces, isolates, and finds the true cause before proposing a fix. Use for any non-trivial bug or a failure that recurred.

• implementer

  Executes exactly one scoped task — changes code inside its scope, runs targeted validation, commits, and returns a structured handoff. Ends at commit, never at a pull request. Use for a single unit of implementation work inside a larger objective.

• integrator

  Assembles completed worker branches into one integration branch, resolves conflicts, runs integration-level validation, and applies fixes review demands. Use once an objective's tasks are done and their branches must become one coherent change.

• orchestrator

  Owns a multi-task objective end to end — builds the task graph, dispatches roles in dependency order, tracks handoffs, and drives integration to a single delivery. Use when a request needs more than one unit of work or more than one specialist role.

• performance-reviewer

  Finds performance bottlenecks and concrete optimization opportunities (hot paths, N+1 queries, unnecessary work, bundle/render cost). Use when something is slow or before shipping a perf-sensitive path.

• research-agent

  Verifies library/API/framework details against current documentation before you rely on them — prevents outdated-pattern and hallucinated-API mistakes. Use when unsure of an API signature, config option, version behavior, or best-practice pattern.

• security-reviewer

  Reviews changes for vulnerabilities, leaked secrets, and over-broad permissions. Use before merging anything touching auth, input handling, secrets/env, IAM/permissions, or external I/O.

• spec-reviewer

  Reviews the combined integrated diff for completeness and correctness against the stated objective — did it do what was asked, all of it, and nothing extra. Use before delivery, after integration, and whenever scope drift is a risk.

• test-engineer

  Generates focused tests, analyzes coverage gaps, and adds regression tests for fixed bugs. Use after implementing a feature/fix, or when coverage of a critical path is thin.

MCP servers (1)

• github

  runs: ${CLAUDE_PLUGIN_ROOT}/scripts/github-mcp.sh

Hooks (30)

• PreToolUse

  bash "${CLAUDE_PLUGIN_ROOT}"/hooks/permission-guard.sh

• PreToolUse

  bash "${CLAUDE_PLUGIN_ROOT}"/hooks/permission-guard.sh

• PreToolUse

  bash "${CLAUDE_PLUGIN_ROOT}"/hooks/permission-intent.sh

• PreToolUse

  bash "${CLAUDE_PLUGIN_ROOT}"/hooks/protect-other-branches.sh

• PreToolUse

  bash "${CLAUDE_PLUGIN_ROOT}"/hooks/enforce-worktree-edits.sh

• PreToolUse

  bash "${CLAUDE_PLUGIN_ROOT}"/hooks/guard-sensitive-files.sh

• PreToolUse

  bash "${CLAUDE_PLUGIN_ROOT}"/hooks/skill-creator-guard.sh

• PreToolUse

  python3 "${CLAUDE_PLUGIN_ROOT}/hooks/docker-guard.py"

• PreToolUse

  bash "${CLAUDE_PLUGIN_ROOT}"/hooks/guard-sensitive-files.sh

• PostToolUse

  bash "${CLAUDE_PLUGIN_ROOT}"/hooks/permission-approved.sh

• PostToolUse

  bash "${CLAUDE_PLUGIN_ROOT}"/hooks/plugin-reload-reminder.sh

• PostToolUse

  bash "${CLAUDE_PLUGIN_ROOT}"/hooks/validate-report-links.sh

• SessionStart

  bash "${CLAUDE_PLUGIN_ROOT}"/hooks/show-changelog.sh

• SessionStart

  bash "${CLAUDE_PLUGIN_ROOT}"/hooks/session-init.sh

• SessionStart

  bash "${CLAUDE_PLUGIN_ROOT}"/hooks/usage-capture-ensure.sh

• SessionEnd

  bash "${CLAUDE_PLUGIN_ROOT}"/hooks/session-end.sh

• SessionEnd

  bash "${CLAUDE_PLUGIN_ROOT}"/hooks/handoff-reminder.sh

• SessionEnd

  bash "${CLAUDE_PLUGIN_ROOT}"/hooks/release-agent-claims.sh

• UserPromptSubmit

  bash "${CLAUDE_PLUGIN_ROOT}"/hooks/capture-task-slug.sh

• UserPromptSubmit

  bash "${CLAUDE_PLUGIN_ROOT}"/hooks/goal-condition-lint.sh

• UserPromptSubmit

  bash "${CLAUDE_PLUGIN_ROOT}"/hooks/goal-compact-reminder.sh

• UserPromptSubmit

  bash "${CLAUDE_PLUGIN_ROOT}"/hooks/scope-decompose-reminder.sh

• UserPromptSubmit

  bash "${CLAUDE_PLUGIN_ROOT}"/hooks/ensure-exit.sh

• UserPromptSubmit

  bash "${CLAUDE_PLUGIN_ROOT}"/hooks/skill-suggest.sh

• UserPromptSubmit

  bash "${CLAUDE_PLUGIN_ROOT}"/hooks/permission-intent.sh

• UserPromptExpansion

  bash "${CLAUDE_PLUGIN_ROOT}"/hooks/permission-intent.sh

• WorktreeCreate

  bash "${CLAUDE_PLUGIN_ROOT}"/hooks/worktree-create.sh

• WorktreeRemove

  bash "${CLAUDE_PLUGIN_ROOT}"/hooks/worktree-remove.sh

• DirectoryAdded

  bash "${CLAUDE_PLUGIN_ROOT}"/hooks/directory-added.sh

• Notification

  bash "${CLAUDE_PLUGIN_ROOT}"/hooks/notify.sh

Similar plugins