MCP server Claude CodeCodexCursor +2
MCP server "h1b-search" as configured in aryaminus/h1b-job-search-mcp. Runs ${HOME}/path/to/mcp-server-template/src/server.py with python. Needs 1 environment variable to run.
Instructions file CodexOpenCode
AGENTS.md instructions for aryaminus/controlkeel, covering controlkeel governance, issue and pr quality, planning and architecture, project commands and phoenix v1.8.
Skill Claude CodeCodex
Attach ControlKeel to agents, verify MCP connectivity, confirm native skills availability, and choose the right distribution target for each client.
Skill Claude CodeCodex
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.
Skill Claude CodeCodex
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 ckreviewsubmit.
Skill Claude CodeCodex
Settle types, module shape, and boundaries before implementation. Trigger: 'architect this', 'design module structure', 'settle types first'. For multi-module changes.
Skill Claude CodeCodex
Run, inspect, import, and export ControlKeel benchmark suites and multi-subject matrices. Use this when comparing governed and external agents or validating policy changes.
Skill Claude CodeCodex
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.
Skill Claude CodeCodex
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.
Skill Claude CodeCodex
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'.
Skill Claude CodeCodex
Enable ControlKeel governance for Cloudflare Agents with policy gates, budget enforcement, PII detection, and secure execution.
Skill Claude CodeCodex
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.
Skill Claude CodeCodex
DEPRECATED — use security-review instead (it now covers all of this — regulated flows, policy packs, domain controls). Kept as a thin alias for search (compliance/GDPR/SOC2/HIPAA) so existing ckskilllist queries still surface security-review.
Skill Claude CodeCodex
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.
Skill Claude CodeCodex
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.
Skill Claude CodeCodex
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.
Skill Claude CodeCodex
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.
Skill Claude CodeCodex
Strict maintainability review: abstraction quality, file size, spaghetti growth, code-judo simplification. Trigger: 'deep quality review', 'thermo-nuclear review', 'harsh maintainability audit'.
Skill Claude CodeCodex
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.
Skill Claude CodeCodex
DEPRECATED — use security-review instead (it now covers all domain-pack audits — HR, legal, marketing, sales, real-estate, government, insurance, logistics, manufacturing, e-commerce, nonprofit). Kept as a thin alias so ckskilllist for those domains still surfaces security-review.
Skill Claude CodeCodex
Close a governed work session — the unified session-close path (validation + proof + findings + budget + digest + learning) that ends with the handoff delegation step when work remains. Prefer this over bare handoff for any end-of-shift wrap-up. Use when the user asks to wrap up, stop for the day, or leave work ready…
Skill Claude CodeCodex
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.
Skill Claude CodeCodex
Persist session state and hand off in-progress work to a background agent — the delegation step of end-of-shift. Use when work outgrows the current session or must continue unattended; for a full session close (validation + proof + findings + budget + digest + learning before handoff) prefer end-of-shift.
Skill Claude CodeCodex
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'.