cct

Plugin cct from marketplace code-copilot-team in gosha70/code-copilot-team. Commands read from the repo's manifest — yesterday.

Skills (24)

• agent-team-protocol

  Multi-agent delegation rules, three-phase workflow (Plan/Build/Review), model selection, collaboration gates, and Ralph Loop integration.

• auto-build-loop

  Autonomous build driver after SDD spec approval: phase-scoped headless build sessions, driver-owned commits, cross-provider review gates, milestone pauses, and fail-closed escalation — under explicit opt-in autonomy profiles.

• clarification-protocol

  When and how to ask clarifying questions before implementing. Data model review gate and ambiguity resolution rules.

• coding-standards

  Quality gates, prohibited patterns, verification discipline, and self-audit rules for all code generation and review sessions.

• copilot-conventions

  Cross-copilot portable conventions: target alignment, complexity control, minimal changes, git discipline, and project structure.

• copyright-headers

  Copyright header rules for generated source files. Applies the company name from providers.toml to new files.

• design-system

  Derive a unique, domain-fit design direction and enforce design-token + anti-slop discipline. Read/author DESIGN.md before building any UI; override framework defaults so output is bespoke by construction, not generic.

• environment-setup

  Environment variable patterns, config file validation, and setup verification for new project scaffolding.

• infra-verification

  Infrastructure artifact verification: Docker builds, CI workflows, and launcher flags must be executed, not just syntax-checked.

• integration-testing

  Test integration points early. Verify cross-service contracts, API boundaries, and data flow before declaring done.

• memkernel-memory

  MemKernel persistent memory protocol. Self-guarding: activates only when the memkernel MCP server is configured.

• opus-4-7-features

  Optional guidance for sessions using Claude Opus 4.7: adaptive thinking, xhigh effort, prompt caching, /btw side questions.

• origin-confirmation

  Origin-confirmation circuit breaker: machine-checkable origin frontmatter, alignment-check protocol, three gates (plan-approval, build-entry, phase-complete), and interactive escalation on deviation.

• phase-workflow

  Phase transition rules, post-phase verification steps, peer review validation, and commit-gate approval flow.

• provider-collaboration-protocol

  Cross-provider peer review protocol: session flags, review flow, collaboration artifacts, fail-closed enforcement, and CI validation.

• ralph-loop

  Single-agent autonomous iteration loop: PRD-driven, self-verifying, with configurable iteration limits and completion criteria.

• review-loop

  Agent-driven peer review loop: structured findings, dispositions, circuit breakers, commit strategies, sandbox isolation, and plan-phase advisory mode.

• safety

  Non-negotiable safety constraints: destructive action guards, blocked operations, secrets policy, password storage, input validation, and dependency review.

• spec-workflow

  SDD specification protocol: risk-based spec_mode classification, required sections per mode, plan approval gate, and artifact directory conventions.

• stack-constraints

  Stack version pinning and dependency compatibility guards. Prevents silent version drift across project boundaries.

• team-lead-efficiency

  Build team lead efficiency rules: limit sub-agents, polling discipline, no redundant re-work, parallel task launching.

• token-efficiency

  Token economy rules: diff-over-rewrite, context compression, avoid verbose re-explanations, minimize round-trips.

• visual-review

  Closed visual-review loop for generated UI: render the running app, screenshot per breakpoint, run an axe-core a11y gate, critique against the DESIGN.md rubric, triage findings, and iterate to a quality bar with a hard cap. Drives the shippable harness/ runner.

• wiki-first-query

  Wiki-first query convention: consult knowledge/wiki/index.md and the linked pages BEFORE re-reading raw sources for a project topic. The wiki is the canonical project memory layer.

Slash commands (14)

• /cct:auto-build
• /cct:bet
• /cct:cooldown
• /cct:cycle-start
• /cct:hill
• /cct:list-agents
• /cct:origin-check
• /cct:phase-complete
• /cct:promote-lesson
• /cct:ralph-start
• /cct:retro
• /cct:review-decide
• /cct:review-submit
• /cct:shape

Subagents (14)

• build

  Decomposes approved plans into tasks, delegates to sub-agents, integrates results, verifies builds. The only phase that writes code.

• code-simplifier

  Reviews recently changed code for unnecessary complexity. Simplifies conditionals, removes dead code, extracts repeated patterns, and improves readability without changing behavior.

• cooldown-report

  Generates a cooldown report — bug fixes shipped + pitches ready for next betting table. Writes specs/retros/cooldown-after-NN.md.

• cycle-retro

  Generates a cycle retrospective from pitch.md, hill.json, and git log. Writes specs/retros/cycle-NN.md.

• doc-writer

  Generates and updates project documentation after feature work. Updates README, adds JSDoc/docstrings for new functions, and maintains CHANGELOG.

• phase-recap

  Generates a phase recap document summarizing what was built, decisions made, issues encountered, and what's next. Runs at the end of each build phase.

• pitch-shaper

  Takes a rough idea, lists its open decisions for the main session to ask, and produces a Shape-Up pitch with appetite, scopes, rabbit holes, no-gos, and circuit breaker. Writes specs/pitches/<id>/pitch.md.

• plan

  Lists open decisions for the main session to ask, produces implementation plans with files, interfaces, test strategy, and delegation. Writes SDD artifacts to specs/. No application code changes.

• research

  Explores codebase, reads docs, searches the web. No code changes. Returns a research summary with paths, patterns, and risks.

• review

  Holistic review of all changes — correctness, consistency, style, test coverage. Runs tests, checks console, verifies integration. Returns pass/fail report.

• scope-executor

  Executes a single scope of an active Shape-Up pitch. Reads pitch context, updates hill.json, delegates implementation to the build agent. Thin adapter — no inlined build logic.

• security-review

  Scans code for common security vulnerabilities. Checks for hardcoded secrets, injection risks, missing input validation, and exposed debug endpoints. Read-only.

• verify-app

  Runs end-to-end verification of the project. Executes test suite, type checker, linter, and dev server. Reports pass/fail with specific failure details.

• visual-reviewer

  Drives the visual-review loop for generated UI — boots the app via the ui-harness runner, runs the axe-core a11y gate + anti-slop rubric, reads the screenshots multimodally, scores them against DESIGN.md, and reports triaged findings until the design bar is met.

Hooks (7)

• PreToolUse

  "${CLAUDE_PLUGIN_ROOT}"/scripts/protect-files.sh

• PreToolUse

  "${CLAUDE_PLUGIN_ROOT}"/scripts/protect-git.sh

• PostToolUse

  "${CLAUDE_PLUGIN_ROOT}"/scripts/verify-after-edit.sh

• PostToolUse

  "${CLAUDE_PLUGIN_ROOT}"/scripts/auto-format.sh

• Stop

  "${CLAUDE_PLUGIN_ROOT}"/scripts/verify-on-stop.sh

• Notification

  "${CLAUDE_PLUGIN_ROOT}"/scripts/notify.sh

• SessionStart

  "${CLAUDE_PLUGIN_ROOT}"/scripts/reinject-context.sh