feat: Claude Code Monitor — lanes, pipelines and a merged workspace

Internal SmartGift build of a Claude Code monitoring dashboard.

Lanes: a durable unit of parallel agent work, one per working directory,
tracked across session restarts. Managed lanes are git worktrees the
dashboard provisions and can reset or remove behind a three-check destroy
guard and a counted preflight; adopted lanes are directories you already
own and are never destroyable.

Pipelines: a lane moves through pipeline stages. A stage the agent declares
with evidence renders green; a stage inferred from the tool-event stream
renders dashed amber and never counts as done. Detection is forward-only
within a 30-minute window, and never writes the declared stage.

Workspace: one page at /run with a lane grid, the selected lane's pipeline,
and a full Claude console behind a disclosure.

plugins/ccam-sessions/commands/find-session.md

@@ -0,0 +1,32 @@
+---
+description: Search Agent Monitor sessions by cwd, model, or status and print the top matches.
+argument-hint: "[query]"
+---
+
+Search Claude Code sessions tracked by the Agent Monitor and print the top matches.
+
+The query is **$ARGUMENTS** — any mix of a project / cwd substring, a model
+(`opus`/`sonnet`/`haiku` or a model-id fragment), and a status
+(`active`/`working`/`completed`/`error`). If empty, just show the most recent sessions.
+
+Fetch the session list (each carries an inline `cost` field):
+
+```
+curl -s "http://localhost:4820/api/sessions?limit=200"
+```
+
+Then:
+
+1. Filter in-memory: keep sessions whose `cwd` contains the project term (case-insensitive),
+   whose `model` contains the model term, and whose `status` equals the status term —
+   apply only the terms present in `$ARGUMENTS`.
+2. Sort matches by `cost` descending if the query mentions cost/expensive, otherwise by
+   `started_at` descending (most recent first).
+3. Print the top 10 as a numbered list, one line each:
+   `<rank>. <id short> — <status> — <model> — <cwd basename> — $<cost to 4dp> — <started_at>`
+4. End with the match count and the summed cost of the shown matches.
+
+Currency as USD to 4 decimal places. If nothing matches, say so and list the distinct
+cwds/models that DO exist (from the returned data) so the user can refine — do not invent
+results. If the dashboard is unreachable, tell the user to start it with `npm start` from
+the repo root.

plugins/ccam-sessions/commands/recent.md

@@ -0,0 +1,27 @@
+---
+description: List the N most recent Claude Code sessions from the Agent Monitor.
+argument-hint: "[N]"
+---
+
+List the most recent Claude Code sessions tracked by the Agent Monitor.
+
+`N` = **$ARGUMENTS** (default `10` if empty).
+
+Fetch the most recent sessions (the API returns them most-recently-updated first):
+
+```
+curl -s "http://localhost:4820/api/sessions?limit=$ARGUMENTS"
+```
+
+This returns a session list; each entry has id, status, model, cwd, started_at,
+ended_at, cost, and metadata (turn_count, total_turn_duration_ms).
+
+Then print the sessions as a numbered list, one line each, in the order returned:
+
+`<rank>. <id short> — <status> — <model> — <cwd basename> — <turn_count> turns — $<cost to 4dp> — <started_at>`
+
+After the list, print the summed cost of the listed sessions and a one-line status
+tally (e.g. `7 completed · 2 active · 1 error`).
+
+Currency as USD to 4 decimal places. Keep it terse, no preamble. If the dashboard is
+unreachable, tell the user to start it with `npm start` from the repo root.

plugins/ccam-sessions/commands/replay.md

@@ -0,0 +1,31 @@
+---
+description: Summarize one Agent Monitor session by id — header plus a concise transcript recap.
+argument-hint: "[session-id]"
+---
+
+Produce a concise recap of one Claude Code session tracked by the Agent Monitor.
+
+The session id is **$ARGUMENTS**. If empty, resolve the latest:
+`curl -s "http://localhost:4820/api/sessions?limit=1"` and use its `id`.
+
+Fetch the session header and its transcript:
+
+```
+curl -s "http://localhost:4820/api/sessions/$ARGUMENTS"
+curl -s "http://localhost:4820/api/sessions/$ARGUMENTS/transcript"
+```
+
+The first returns the session detail (status, model, cwd, started_at, ended_at, cost,
+metadata: turn_count, thinking_blocks, total_turn_duration_ms). The second returns the
+ordered transcript messages (user / assistant / tool).
+
+Then print, concisely:
+
+1. **Header** — one block: `id · model · status · cwd basename · turn_count turns · $<cost to 4dp> · <started_at → ended_at>`.
+2. **Recap** — 5–10 bullets walking the conversation in order: the user's goal, the key
+   assistant actions and tools used, any tool failures, and how it ended. Summarize each
+   message in one line; do not paste large payloads (truncate past ~200 chars with `…`).
+
+Currency as USD to 4 decimal places. If the transcript is empty, say the session has no
+stored transcript rather than inventing turns. If the dashboard is unreachable, tell the
+user to start it with `npm start` from the repo root.