interlinked

interlinked — overview & skill router

For the internal, default-off claims --receipt-shadow observer and its explicit receipt links, use interlinked-observability and docs/internal/jev.md. It logs comparisons only; it does not enable claim evaluation in public Stop hooks or alter a model decision.

For experimental metrics decisions measurements, ThinkThen/Clef/Jev adapters, calibration audits, relational ledgers and [interlinked:decision-metrics] advice, load interlinked-quality-gates. For Qwen embedding retrieval/resource policy, also load interlinked-semantic-index. These unvalidated judgments are advisory; they do not participate in deterministic PreToolUse blocking.

For repeated implementation advice (repeated_implementation), load interlinked-verify. This is an advisory AST comparison for Python and JS/TS, reported after a changeset and in the Stop/verification review. It is not a hard gate.

Use interlinked-harness for opt-in decision/edit shadows, interlinked-verify for the optional TypeScript scheduler and heuristic false-positive filter, and interlinked-observability for simulation filtering, shadow file touches and reservation joins. These predictors remain disabled by default; passing implementation tests does not establish cross-repository calibration or authorize promotion into guard policy.

Use interlinked-verify for tests contracts import|inspect|run: portable executable examples, expected-value provenance and retained previous expectations. Use interlinked-spec-audit for preparing explicit documentation examples. Contract review is advisory; configured acceptance is separate from agent-authored proposals.

For provider edit normalization and Stop delivery, use interlinked-harness; for native qualification, use interlinked-setup; for re-entry/translation evidence, use interlinked-observability. Early test-readiness guidance is covered by interlinked-verify. Provider-specific capabilities remain available.

Use interlinked-verify for tests readiness and bounded tests review, including Python test setup and the distinction between tools present, assertions executed, and requirements covered. Use interlinked-simplification for the advisory Python cleanup/forwarding family.

Interlinked is a local control plane for AI coding agents. A local daemon ("the harness") hooks into Claude Code, Codex, Copilot CLI, Gemini CLI, Cursor, OpenCode, and Pi — and on every tool call the runner exposes to its hook surface it enforces deterministic policy (block/allow in milliseconds, no model in the decision path), fails closed on what causes incidents (destructive commands, secrets, unvetted deps), and writes a replayable local activity log. It is offline-first — no required cloud dependency or remote telemetry. Activity is recorded locally; an optional authenticated server provides multi-agent coordination and configured sync.

Runner registration is not a claim of identical native APIs. OpenCode and Pi use managed plugin/extension bridges and lack dedicated native MCP, subagent, and worktree lifecycle hooks; load interlinked-setup for activation/trust and interlinked-harness for ask/Stop behavior.

If you're an agent working in a repo with a .interlinked/ directory, you are being guarded by it. This skill orients you and points to the right focused skill.