context-band
claudeLine under the prompt input, a band above the prompt on the desktop: context meter, cache expiry, single-call streak, 5h limit, session time, turns and cost, top context contributors, graphify rebuild
DDD/TDD kit: skills, agents, hooks, presets, business knowledge base, cctoolkit command
Plugin cctoolkit from marketplace cctoolkit in pierrebelin/claude-code-toolkit. Commands read from the repo's manifest — 2 days ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
tests-contract-testsCreate or modify xUnit HTTP contract tests with Verify and WebApplicationFactory. Use when a route or a public HTTP contract changes; not for business rules nor an E2E lifecycle.
tests-e2e-testsCreate or modify xUnit E2E tests through Aspire and the client SDK for a complete business lifecycle. Use only when the plan selects a scenario of at least two operations; never for a single endpoint.
tests-integration-testsCreates EF Core repository/persistence integration tests with the Builder pattern and SQL Server Testcontainers. Seeding through the DbContext directly.
tests-unit-testsCreate or modify xUnit unit tests for .NET application handlers/services with a fixture and hand-written doubles. Use for business rules, query results and command events; never to test an aggregate directly.
askUse when the user asks how the product behaves or why (business rule, use case, decision, handler guarantee), or before changing a handler outside the kit's flow. Answers from the knowledge base via `cctoolkit ask`, each fact cited by id.
business-specUse for a short, testable business spec of a feature once its business decisions are clarified. Reads the knowledge base, writes the feature's delta with global ids. No technical design.
fix-bugUse when the user brings a bug (ticket, failing behaviour) to fix: checks it is not already fixed, diagnoses the cause in a read-only subagent, settles with the user whether it is a bug or a spec gap, writes a one-batch fix plan, then launches the run-fix workflow (RED, GREEN, diff audit, knowledge
implement-tddUse to implement a .NET/DDD batch or a whole plan under strict TDD: launches the run-lot workflow (run-plan for a plan) and relays its report; replays a delivered batch or plan read-only (run-replay).
kit-initRun once per repo after enabling cctoolkit, or to reconfigure it: stack, preset, language, kit.config.json, rules, preset skills, settings, statusline, doctor.
knowledge-mergeUse to bring a delivered feature into the knowledge base: after run-plan staged its merge, after a plan run batch by batch, or --partial for an abandoned plan. Writes only on confirmation.
knowledge-syncUse to build the business knowledge base, or align it with code changed outside the kit's flow (hotfix, refactor, another developer), or when reminded it may be behind. Run before committing.
learnRun when doctor prints `NOTE learn`: turns gaps recurring across /verify-ddd-tdd verdicts into a rule, audit criterion or mechanical check. `memory` audits the auto-memory instead.
plan-implementationUse when a validated business spec must become a DDD technical plan split into batches before coding. Traces RM/CU, DDD decisions and targeted test scenarios.
quality-reportProduces the periodic quality report of the main branch (.NET): asks the Stryker mode, launches the run-audit workflow, relays the report.
verify-ddd-tddUse after /implement-tdd, before the next batch: audits a .NET batch (correctness, reuse, simplification, cost, plan conformance, test policy, TDD evidence). Fast by default, full on request; `diff` audits any change set (hotfix, fix, change outside a plan) on its diff alone.
adversarial-reviewerTries to refute a spec, a plan or a batch sheet before code is written, when /business-spec or /plan-implementation delegates it. Reading only; returns closed questions ranked Blocking or Major.
ddd-tdd-auditorAudits a .NET/DDD batch without ever modifying it when /verify-ddd-tdd is invoked. Reading, searching and running validations only.
knowledge-extractorDrafts one bounded context of the knowledge base from the code when /knowledge-sync delegates it — staged drafts with provisional ids, never the base itself.
knowledge-mergerDrafts the merge of a delivered feature into the knowledge base when /knowledge-merge or the run-plan workflow delegates it — the spec's delta rewritten in the base's format, in the merge staging, never the base itself.
tdd-cycleWrites the RED tests then the GREEN code of one TDD cycle in a single agent when the run-lot workflow runs a light batch; a checkpoint checked on the tree separates the two phases.
tdd-implementerWrites the minimal production code that turns a red test green when /implement-tdd delegates the GREEN phase, then cleans up and states the access cost.
tdd-test-authorWrites the RED tests for a .NET/DDD behaviour when /implement-tdd delegates the test-first phase.
bash "${CLAUDE_PLUGIN_ROOT}/hooks/bash-dispatch.sh"
bash "${CLAUDE_PLUGIN_ROOT}/hooks/explore-guard.sh"
bash "${CLAUDE_PLUGIN_ROOT}/hooks/implement-tdd-guard.sh"
bash "${CLAUDE_PLUGIN_ROOT}/hooks/read-bounds.sh"
bash "${CLAUDE_PLUGIN_ROOT}/hooks/tdd-scope-guard.sh"
bash "${CLAUDE_PLUGIN_ROOT}/hooks/tdd-scope-guard.sh"
bash "${CLAUDE_PLUGIN_ROOT}/hooks/handler-claude-md-check.sh"
bash "${CLAUDE_PLUGIN_ROOT}/hooks/knowledge-reminder.sh"
bash "${CLAUDE_PLUGIN_ROOT}/hooks/run-notes.sh"
bash "${CLAUDE_PLUGIN_ROOT}/hooks/implement-tdd-guard.sh"
bash "${CLAUDE_PLUGIN_ROOT}/hooks/clear-nudge.sh"
bash "${CLAUDE_PLUGIN_ROOT}/hooks/session-cleanup.sh"
bash "${CLAUDE_PLUGIN_ROOT}/tools/doctor" --quiet || true
bash "${CLAUDE_PLUGIN_ROOT}/hooks/worktree-graphify-link.sh"
bash "${CLAUDE_PLUGIN_ROOT}/hooks/windows-env.sh"
bash "${CLAUDE_PLUGIN_ROOT}/hooks/graphify-autosync.sh"
bash "${CLAUDE_PLUGIN_ROOT}/hooks/tdd-scope-guard.sh"
bash "${CLAUDE_PLUGIN_ROOT}/hooks/subagent-report-shape.sh"
bash "${CLAUDE_PLUGIN_ROOT}/hooks/context-log.sh"
Line under the prompt input, a band above the prompt on the desktop: context meter, cache expiry, single-call streak, 5h limit, session time, turns and cost, top context contributors, graphify rebuild
Side pane browsing the business knowledge base: contexts, use cases and their rules, decisions, ADRs, history, a staged merge or sync; and following a /business-spec: decisions and answers, open questions, use cases, business rules, sections, unfolded inline on click; read-only, no model context spent
Side pane following a run-lot run, or a run-plan run with a plan view and navigation between its batches: phases as columns, agents (model, duration, tokens per agent, slowness, stalls, retries, interruptions), estimated end, batch sheet, audit verdict and rounds, run outcome with the knowledge-base merge a plan staged, end toast; steers the run: entries to validate, notes, dependency graph
Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Harness-native ECC operator layer - 71 agents, 314 skills, 98 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
200 skills · 98 commands · 71 agents · 1 MCP server · hooks
Comprehensive toolkit for developing Claude Code plugins. Includes 7 expert skills covering hooks, MCP integration, commands, agents, and best practices. AI-assisted plugin creation and validation.
7 skills · 1 command · 3 agents
Production-grade engineering skills covering every phase of software development: spec, plan, build, verify, review, and ship.
25 skills · 4 agents
CMEM Pro for the Claude app - hooks stream tool use to cmem.ai and inject observations into new sessions and agents
3 skills · 1 MCP server · hooks
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.