hjemmesidekongen/ai

claude-core

Foundation plugin - planning, brainstorming, verification, tracing, memory governance, debugging, learning pipelines, and workplace integrations.

claude-core

The foundation of the hjemmesidekongen/ai methodology - the infrastructure that makes structured AI-assisted development possible. Without it, the other plugins have nothing to stand on: no state management, no verification protocol, no learning pipeline.

Version: 0.3.0 · 40 skills · 13 commands · 12 agents · 23 hooks

What It Does

claude-core turns Claude Code from a stateless Q&A tool into a stateful development environment. It remembers what you decided, tracks what you're working on, verifies that work is actually done, and learns from how you use it.

Commands

CommandWhat It Does
/brainstorm:startOpen-ended exploration. Claude acts as a sparring partner, challenges assumptions, pushes back on weak reasoning.
/brainstorm:decideExtract structured decisions from a brainstorm session. Each decision gets user confirmation before it's saved.
/plan:createConvert a task into a wave-based plan. Resolves dependencies via topological sort, assigns model tiers, sets up verification gates.
/plan:executeRun the plan wave-by-wave with parallel agent dispatch and verification between waves.
/plan:statusSee where you are - wave progress, task status, errors, recovery options.
/plan:resumePick up an interrupted plan from exactly where it stopped.
/full-review5-phase code review with 2 parallel reviewers per phase. Severity gates between phases.
/autopilot-runAutonomous iteration loop. Give it a task, it works through iterations until completion, respecting stop hooks and verification gates.
/autopilot-cancelStop the loop and get an iteration report.

Key Concepts

Verification & Safety

No task gets marked "done" without proof.

verification-gate enforces a 5-step protocol: identify the proof command, run it, read the full output, verify it matches expectations, and only then claim completion. Inference-based completion ("it should work") is explicitly banned.

plan-verifier runs two stages after each wave: Stage 1 checks mechanical spec compliance (files exist, schemas valid, ownership correct). Stage 2 runs quality review with judgment calls. Both must pass.

Hooks enforce this at the system level:

  • verification-gate-stop prevents premature completion claims
  • check-wave-complete blocks plan advancement without verification
  • scope-guard prevents modifications to out-of-scope files

Cross-Session Continuity

Claude Code forgets everything when you start a new session. claude-core doesn't.

session-handoff creates structured handoff documents capturing: current state, blockers, open questions, and actionable next steps. When you resume, it loads the handoff, classifies staleness (FRESH, SLIGHTLY_STALE, STALE, VERY_STALE), and verifies assumptions still hold.

PreCompact snapshot - before Claude Code compresses context, a hook saves the full session state to .ai/context/snapshot.yml. On session start, another hook restores it. Your working context survives compaction automatically.

Learning Pipeline

claude-core observes how you work and extracts patterns:

  1. observation-recorder (hook) - captures tool call patterns automatically during every session
  2. instinct-extractor - reads observations, identifies recurring patterns (3+ occurrences), extracts them as "instincts" with confidence weights
  3. instinct-evolve - reviews mature instincts (confidence ≥0.75, evidence ≥3) and proposes promotion to CLAUDE.md rules, MEMORY.md entries, or new skills

The pipeline is self-correcting: contradictions decay confidence, and instincts that don't recur expire naturally.

Debugging & Investigation

Three skills that enforce evidence-first debugging:

root-cause-debugging - 4 mandatory phases: Investigate, Pattern Analysis, Hypothesis, Implement. You can't jump to a fix without understanding the problem first. If 3+ fixes fail, it escalates.

hypothesis-generator - generates 3 competing hypotheses, investigates each in parallel, and synthesizes evidence. Eliminates confirmation bias by forcing you to consider alternatives before committing to one explanation.

reasoning-trace-optimizer - analyzes trace-light.log for reasoning degradation: context loss, tool confusion, instruction drift, goal abandonment, circular reasoning. Produces specific diagnosis with actionable fixes.

Component Reference

Planning & Execution Skills

The planning engine handles dependency ordering, file-ownership isolation (so parallel agents don't conflict), and automatic verification gates between waves.

SkillPurpose
brainstorm-sessionOpen-ended brainstorm
brainstorm-decision-writerExtract decisions from brainstorms
brainstorm-decision-readerLoad past decisions for context
plan-engineTask to wave plan conversion
plan-verifierTwo-stage wave verification

Code Review Skills

/full-review runs a 5-phase review with 2 parallel reviewers per phase:

  1. Code quality & best practices
  2. Architecture & design patterns
  3. Security vulnerabilities
  4. Performance optimization
  5. Testing coverage & documentation

Severity gates between phases - critical findings in Phase 1 block progression to Phase 2. Final consolidated report deduplicates across all reviewers.

parallel-reviewer dispatches 4 specialized reviewers (security, performance, architecture, testing) simultaneously for faster targeted review.

Component Tooling Skills

Create, review, and maintain plugin components:

CreateReview
hook-creatorhook-reviewer
skill-creatorskill-reviewer
command-creatoragent-reviewer
agent-creatorplugin-reviewer
plugin-creatorcomponent-reviewer
mcp-creator-

Creators enforce correct frontmatter, naming conventions, and registration. Reviewers are read-only - they produce verdicts, never modifications.

Workplace Integrations

Five MCP-based skills for connecting to your existing tools:

SkillServiceWhat You Can Do
jira-basicsJiraRead tickets, search with JQL, transition status, add comments
confluence-basicsConfluenceSearch pages, read content, navigate space hierarchies
slack-basicsSlackRead channels, search messages, post updates, reply to threads
bitbucket-basicsBitbucketCreate PRs, check pipeline status, manage branches
outlook-basicsMicrosoft 365Search emails, read threads, check calendar

Each integration requires its MCP server configured. All degrade gracefully when the server isn't available - clear error messages, never fabricated data.

Architecture & Documentation Skills

SkillPurpose
c4-architectureGenerate C4 model diagrams (context, container, component, deployment) as Mermaid
mermaid-diagrams7 diagram types: class, sequence, flowchart, ERD, state, git graph, gantt
doc-checkpointAfter any task, compares changes against documentation files and produces a checklist of what needs updating
auto-docAutomatically syncs CLAUDE.md structure trees, component counts, and ecosystem.json entries
reducing-entropyDeletion-first mindset for codebase health: measure success by how much code remains

Writing & Communication Skills

SkillPurpose
writing-clearly-and-conciselyStrunk's 18 rules applied to technical writing, with AI anti-pattern detection
prompt-optimizerSharpen vague prompts into precise instructions. Two modes: auto-sharpen (hook-triggered) and builder (/prompt:create)

Hooks

claude-core runs 23 hooks across 6 event types:

EventCountPurpose
PreToolUse5Prevent direct pushes, validate scope, gate TDD/planning, detect compaction
PostToolUse6Debug output, protect CLAUDE.md, trace operations, record observations
PreCompact1Snapshot session state before context compression
SessionStart2Restore session state, check memory health
Stop8Verify completion, check documentation, clear caches
UserPromptSubmit1Grade prompt quality

Hooks are the safety net. They prevent you from pushing to main, skipping verification, modifying out-of-scope files, or claiming work is done when it isn't.

Agents

12 specialized agents, each with a specific role and model tier:

AgentTierRole
plugin-validatorsonnetFull plugin structure validation
skill-auditorsonnet8-dimension quality scoring (120-point scale)
security-auditorsonnetInfrastructure security: injection, secrets, unsafe eval
component-reviewersonnetPre-commit validation for new components
architect-revieweropusPlugin boundary and coupling analysis
refactoring-specialistsonnetBehavior-preserving code transformations
knowledge-synthesizersonnetCross-session pattern mining
tdd-orchestratorsonnetRed-green-refactor cycle enforcement
context-managersonnetToken-budgeted context assembly for multi-agent dispatch
error-detectivesonnetRead-only error investigation and root cause analysis
incident-respondersonnetPost-investigation fix coordination and post-mortems
agent-reviewersonnet5-dimension agent quality review

All review/audit agents are read-only. They produce verdicts. They never modify code.

See also

  • dev-engine - the multi-agent development pipeline that builds on claude-core
  • taskflow - task management that uses claude-core's MCP and session infrastructure
  • Architecture - how the three plugins relate and share data

On this page