controlkeel

Run objective, repeatable improvement work under an immutable verifier and hard iteration, cost, time, and no-progress limits. Use for approved experiments with an automated metric and sandboxed worker.

Write concise, calm technical responses whose structure matches the decision, evidence, or sequence being communicated. Use when drafting substantial plans, reviews, findings, documentation, or completion summaries.

Operate inside a ControlKeel-governed session. Use this before code edits, shell execution, delegation, deploy work, or any task that needs CK validation, findings, budget, proof, or routing context.

Keep a governed session within budget. Use this before long-running agent work, bulk processing, or any task where spend pressure could change the plan.

Close a governed work session with validation, proof, findings, budget, digest, learning, and handoff checks. Use when the user asks to wrap up, stop for the day, or leave work ready for another agent.

Audit tests that may pass without proving the claimed behavior. Use for periodic test-quality reviews or when coverage looks healthy but regressions still escape.

Persist session state and hand off in-progress work to a background agent or delegated execution. Use when work outgrows the current session, context is near limit, or a task needs to continue unattended.

Check install-to-first-finding metrics, funnel stage, findings state, proofs, and approvals before calling a session ready to ship.

Attach ControlKeel to agents, verify MCP connectivity, confirm native skills availability, and choose the right distribution target for each client.

Summarize work completed over a time period using git commits + CK session data. Trigger: 'what did I get done', 'standup', 'weekly summary', 'status update'.

Adversarially challenge the current plan or finding. Assume the direction is wrong and build the strongest case against it. Surfaces blind spots, false assumptions, and unexplored alternatives before execution starts.

Clean AI slop: remove narrative comments, verbosity, hallucinated patterns, padding. Also cleans AI-generated issue/PR text. Trigger: 'unslop', 'clean up AI code', 'remove slop', 'clean up issue description'. Complements aislop detection.

Learn, record, audit, and apply codebase patterns consistently across a repo by comparing current code to canonical local examples stored in CK memory. Use when asked to preserve continuity, learn a pattern, check drift, fix inconsistent implementations, or enforce local conventions.

Settle types, module shape, and boundaries before implementation. Trigger: 'architect this', 'design module structure', 'settle types first'. For multi-module changes.

Design/review CLIs for agent-friendliness: non-interactive flags, layered help, idempotency, dry-run, actionable errors. Trigger: 'agent CLI', 'automation-friendly CLI', 'headless CLI design'.

Auto-mine session for durable memory: user preferences and workspace facts. Trigger: 'learn from this', 'update memory', 'save what we learned', or at session end.

Strict maintainability review: abstraction quality, file size, spaghetti growth, code-judo simplification. Trigger: 'deep quality review', 'thermo-nuclear review', 'harsh maintainability audit'.

Read-only codebase Q&A: trace code paths, answer how/why/where questions without changes. Trigger: 'how does X work', 'why was Y built this way', 'trace the data flow'.

Fan large tasks across parallel agents with planner/worker/verifier roles and structured handoffs. Trigger: 'parallelize', 'fan out', 'orchestrate', or when plan-slice produces 3+ independent slices.

Run security + code quality reviews concurrently, synthesize deduplicated findings. Trigger: 'full review', 'parallel review', 'both reviews', comprehensive pre-merge check.

Prepare PRs for review: clean noisy history, improve descriptions, add reviewer guidance. Trigger: 'make easy to review', 'tidy PR', 'clean up commits', 'annotate diff'.

Reproduce → root-cause → failing test → minimal fix → verify. Trigger: 'fix this bug', 'reproduce and fix', 'TDD fix'. Requires a local test path.

Enable ControlKeel governance for Cloudflare Agents with policy gates, budget enforcement, PII detection, and secure execution.

Interview the user about their goal before any plan or code. Reach shared understanding of what, why, which layers, success criteria, and unknowns. Feed the result into plan-slice or ck_review_submit.

Decompose an aligned goal into independently executable vertical slices with explicit blocking relationships. Each slice must cross all touched system layers — not a single layer. Submit for human approval before any implementation begins.

Verify AI agent code for dangerous patterns including infinite loops, unbounded retries, tool hallucinations, and context overflow. Use before deploying agent workflows or when reviewing agent code.

Run, inspect, import, and export ControlKeel benchmark suites and multi-subject matrices. Use this when comparing governed and external agents or validating policy changes.

Run a structured compliance audit against active ControlKeel policy packs and domain controls. Use this before shipping regulated data flows, external integrations, or document exports.

Audit a session against its domain pack, especially the regulated and operations-heavy packs such as HR, legal, marketing, sales, real-estate, government, insurance, logistics, manufacturing, e-commerce, and nonprofit. Use this when domain-specific policy needs a manual pass.

Use ControlKeel proof bundles, typed memory, workspace snapshots, transcript summaries, and resume packets before closing or resuming work. Activate this when you need durable evidence or historical context.

Run a structured security review before marking a task done. Use this for code, config, architecture, or release reviews that need OWASP, baseline pack, and domain-pack coverage.