All mods

MIDDLEWARE TUNNEL stage 4: Telemetry: records the call and its result for the ledger

Interactive UI probe: ui.render components, toast, status, log, pane, command register

Interception probe: deny, rewrite, replace result, delay, throw, register tool, classify

Permission override, subagent visibility, agent.spawn model rewrite, turn.step routing, prompt context injection

Spike: does $.session.compact() work from a plugin, and what does the session.compact event carry?

Spike: does a tool.describe rewrite reach the model, does agent.offer hide a type, does prompt.suggest fire?

Spike: safe-boundary handoff (bundle written at turn.complete from the runtime bus) and $.turn.abort semantics

CLAUDE RUNTIME X-RAY: wildcard inspector with filters (/xray all|tools|subagents|session|usage|ui|errors|unknown|off), a HUD above the prompt, and a black-box timeline file

COSTCLAW LIVE: per-request cost, cache decay and repeated-read detection while the session runs, and it serves the Nth identical Read of an unchanged file from its own cache instead of paying for it

PRODUCTION GUARD: ambient project/environment context + a transport-independent policy core (DashClaw evidence classifier + offlocal policy engine) enforced natively on tool.call and tool.check. Blocks, asks, or contains before the command runs. /prodguard

SUBAGENT SUPERVISOR: routing-and-budget Mod. Rewrites a spawn's model onto the capability graph instead of denying it, keeps a measured per-agent-type token ledger in $.store, caps tool calls per subagent, and shows live subagents + the last routing decision above the prompt. /supervisor prints the routing log and the ledger.

Cheap, fast, typed AI judgments inside Claude Code via the jevctl CLI (verify, screen, find, classify, extract, rerank, match, route, ask, batch), plus verbatim Jev-guided context compaction that replaces the built-in summary.

pi agent for claude: a pi subagent type whose model steps run the pi CLI, so pi subagents and agent-team teammates live in Claude Code's own agent UI, streamed live.

Per-session context-window observability. A mod writes each session's context-window figures to a snapshot file and tells Claude its context zone (smart, acceptable or dumb, from bands in zones.json) at each crossing, approach and compaction, noting a zone is not a decay signal; the operator gets the continuation menu. It draws a band row and answers a status tool. Optional blocking mode gates...

Shared rate-limit guard for loop lanes and Claude: a hooks module writes the subscription rate-limit windows to a fixed machine-scope file and tells Claude where they stand at boundaries, a StopFailure hook records rate-limit stops reactively, and a reader contract fixes how consuming sessions pause and resume.

Hands the small judgments in a session to TypeSafe's Jev, a System One model that returns typed answers instead of generating text: what kind of request each prompt is, which model tier a subagent needs, whether an edit breaks a rule already written in your CLAUDE.md or AGENTS.md, and which transcript blocks survive compaction. Kept blocks carry over verbatim — no LLM writes a summary.

Claude Fables: turns what the agent is doing into little animated cartoons above the prompt, written live by Sonnet or Haiku.

Read-only probe: lists system prompt sections and reminder types into /tmp/roof-probe-log.json

Replace Claude Code's built-in reminders with your own words: silence four nags, rename 'the user' in template sentences, drop the CLAUDE.md preamble.

A rail of your session's prompts beside the transcript or above the prompt; hover to read one, click to jump to it.

Shows the Measure plan state and guards edits, commits, and closeouts against the active plan

Records each tool call's permission verdict and wall time so auto-mode classifier cost is measurable from the session index

Drive the herdr terminal workspace manager: panes, tabs, workspaces, and sibling coding agents

Pick a reply's ! suggestion by click or digit to fill it into the shell prompt