ashlr-plugin 1.36.4

package/commands/ashlr-help.md

@@ -0,0 +1,86 @@
+---
+name: ashlr-help
+description: List every ashlr slash command with a one-line description, grouped by category.
+---
+
+Print the following table verbatim inside a fenced code block so column alignment renders correctly. No preamble, no trailing summary beyond the one-line pointer at the bottom.
+
+```
+ashlr slash commands
+
+─── Tier 0: Start here ────────────────────────────────────────────────────
+  /ashlr-start     First-run wizard (doctor + perms + demo + genome + pro)
+  /ashlr-savings   Session + lifetime token-savings report with cost
+  /ashlr-dashboard Rich dashboard — bar charts, sparklines, annual projection
+  /ashlr-doctor    Under-10-second health check of your ashlr install
+  /ashlr-help      This screen
+
+─── Tier 1: Daily use ─────────────────────────────────────────────────────
+  /ashlr-resume    Resume your last session — files, branch, suggested next
+  /ashlr-handoff   Generate a context-pack for the next session
+  /ashlr-brief     Tunable response-shortening (lite/standard/concise) —
+                   30–55% output-token reduction with auto-clarity exceptions
+  /ashlr-eco-mode  Toggle eco mode (auto-compact, genome-grep, smart routing)
+  /ashlr-tier      Three-phase tiered delegation: explore → code → plan
+  /ashlr-update    Update the plugin to the latest version from git
+  /ashlr-allow     Auto-approve every ashlr MCP tool in settings.json
+  /goal            Register an objective → plan milestones → advance next as a
+                   sandboxed proposal-only run (review via `ashlr inbox`)
+  /loop            Run the goal-aware fleet conductor over enrolled repos —
+                   one tick or --watch continuous; proposal-only, kill-switch gated
+
+─── Tier 2: Genome / team ─────────────────────────────────────────────────
+  /ashlr-genome-init       Initialize .ashlrcode/genome/ in the current project
+  /ashlr-genome-push       Push local genome to team cloud (auto at SessionEnd)
+  /ashlr-genome-loop       Inspect + control the auto propose/consolidate loop
+  /ashlr-genome-keygen     Generate the X25519 keypair for team-cloud genome v2
+  /ashlr-genome-rewrap     Re-wrap team-genome DEK for a new or rotated member
+  /ashlr-genome-team-init  Initialize a team-cloud genome (admin, once per repo)
+  /ashlr-team-invite        Invite a teammate to your ashlr team by email
+  /ashlr-upgrade            Terminal-native free → Pro / Team checkout (90 seconds)
+
+─── Tier 3: Power ─────────────────────────────────────────────────────────
+  /ashlr-spawn         Spawn a named delegation pattern (triage-issues,
+                       refactor-files, codebase-explain, pr-review-sweep,
+                       parallel-test-fix)
+  /ashlr-parallelize   Run the same task on N files in parallel sub-agents
+  /ashlr-orchestrate   Expand a goal into a task graph, preview the DAG,
+                       and run it (Pro 3 nodes / Team 10, local-only MVP)
+  /ashlr-orchestrate-status
+                       Inspect past /ashlr-orchestrate runs — list recent
+                       or drill into a single graph by id
+  /ashlr-budget        Set/check/clear a session spend cap ($X or tokens=N)
+  /ashlr-tour          60-second guided walkthrough on the current project
+  /ashlr-benchmark     Run token-savings benchmark against the current project
+  /ashlr-settings      View or change ashlr-plugin settings
+  /ashlr-hook-timings  Per-hook latency report (p50 / p95 / max)
+  /ashlr-report-crash  Upload a recent crash dump to the maintainer (opt-in)
+  /ashlr-status        Plugin + MCP server + genome status report
+  /ashlr-ollama-setup  Diagnose + guide local Ollama install for summarization
+  /ashlr-compact       Recompress stale tool results from the conversation
+
+─── MCP tools (call directly, or via hook redirect) ───────────────────────
+  ashlr__websearch     Token-efficient web search — dedup by domain, snip snippets,
+                       synthesize summary for >3 results. Replaces WebSearch.
+  ashlr__task_list     Compact task list — filter by status/owner, limit rows (default 30),
+                       column view (taskId/status/subject/ageMin). Replaces TaskList.
+  ashlr__task_get      Compact single task — snipCompacts descriptions >2KB.
+                       Replaces TaskGet.
+  ashlr__notebook_edit Compact Jupyter cell edit output (only edited cell + neighbors).
+                       Replaces NotebookEdit.
+  ashlr__write         Compact file-write acknowledgement (no echo of content).
+                       Replaces Write.
+
+─── Status-line legend ────────────────────────────────────────────────────
+  ashlr ·   brand label + activity dot (dim idle, pulses on save event)
+  ⠀⠄⠇⣿    heartbeat glyph — braille wave when active, dim dot when idle
+  7d ▁▂▃▅  7-day sparkline; tallest cell = busiest day
+  ctx:NN%   context-window pressure  green<60  yellow<80  orange<95  red 95+
+  session   tokens saved this terminal session
+  lifetime  tokens saved across all sessions
+  tip:…     rotating daily hint (disable: /ashlr-settings set statusLineTips false)
+```
+
+After the block, print exactly one line:
+
+> Tip: run /ashlr-savings any time to see your running totals.

package/commands/ashlr-hook-timings.md

@@ -0,0 +1,30 @@
+---
+name: ashlr-hook-timings
+description: Show per-hook latency report (p50/p95/max) from hook-timings.jsonl.
+argument-hint: "[--hours N] [--compare] [--flags-only]"
+---
+
+Run the hook timings report and render its output to the user.
+
+```sh
+bun run "${CLAUDE_PLUGIN_ROOT}/scripts/hook-timings-report.ts" $ARGUMENTS
+```
+
+Capture stdout and display it verbatim inside a fenced code block (```) so column alignment renders correctly.
+
+The report covers:
+- Header: total records, time window, overall median latency.
+- Per-hook table: calls, p50, p95, max, error%, block%.
+- Flagging lines for hooks where p95 > 200ms (⚠ threshold exceeded) or max >= 1s.
+- If no records yet: a single plain-text prompt to enable hooks.
+
+**Flags:**
+- `--hours N` — narrow or widen the time window (default: 24h).
+- `--compare` — show trend indicators (↓ improved / ↑ regressed) next to each hook's p95, comparing the current window against the previous equal-length window. A hook is "improved" when p95 dropped ≥20%, "regressed" when it grew ≥20%.
+- `--flags-only` — output only the slow-hook warning lines (compact alert mode). Useful for scripting or quick checks. Exits silently when no flags exist.
+
+After the verbatim block, add **at most one** short line:
+- If the output contains "no records yet": "No timings recorded yet — run a few tool calls with hooks enabled."
+- Otherwise: say nothing extra. The report speaks for itself.
+
+Do not paraphrase the numbers.

package/commands/ashlr-leaderboard.md

@@ -0,0 +1,50 @@
+---
+name: ashlr-leaderboard
+description: Opt in or out of the public ashlr savings leaderboard at plugin.ashlr.ai/community. Opt-in is OFF by default; when on, your GitHub handle and total tokens/$ saved are shown publicly (never your email). Requires a signed-in account that syncs stats (Pro/Team).
+argument-hint: "on | off | status"
+---
+
+Toggle participation in the **public savings leaderboard** shown at
+`https://plugin.ashlr.ai/community`. Opt-in is **OFF by default** — nothing about
+you is published until you explicitly run `/ashlr-leaderboard on`.
+
+## Usage
+
+```
+/ashlr-leaderboard on        # opt IN — your GitHub handle + savings appear publicly
+/ashlr-leaderboard off       # opt OUT — removed from the public board on next sync
+/ashlr-leaderboard status    # show your current setting
+```
+
+## What gets published when you opt in
+
+- Your **GitHub handle** (e.g. `octocat`) and avatar.
+- Your **lifetime tokens saved** and the **dollar equivalent** (at the published
+  $3/MTok rate — the same number `/ashlr-savings` shows you).
+
+**Never published:** your email, your code, your prompts, file paths, or any
+per-session detail. Only the aggregate handle + savings figure.
+
+## How to apply this
+
+The setting lives in `~/.ashlr/config.json` under the `leaderboard` key:
+
+- **`on`** → set `{ "leaderboard": "public" }`
+- **`off`** → set `{ "leaderboard": "off" }`
+- **`status`** → read the key and report: `public` (opted in), `off` (opted out),
+  or unset (default — opted out).
+
+Read the existing `~/.ashlr/config.json` (create it as `{}` if missing), merge the
+`leaderboard` key without disturbing other keys (e.g. `telemetry`), and write it
+back. Then tell the user the change takes effect on the **next stats sync**
+(session end), and confirm what is/isn't published.
+
+## Requirements & notes
+
+- The leaderboard ranks developers whose stats sync to the cloud, which means a
+  **signed-in account** (Pro/Team — see `/ashlr-tier`). Free users with only
+  local stats won't appear even when opted in, because their savings never leave
+  their machine. Mention this if the user isn't signed in.
+- Opting out removes you from the board after the next sync propagates the flag.
+- This is the same privacy posture as `/ashlr-brief` and telemetry: explicit,
+  reversible, and off until you choose otherwise.

package/commands/ashlr-ollama-setup.md

@@ -0,0 +1,39 @@
+---
+name: ashlr-ollama-setup
+description: Diagnose and guide local Ollama install so `/ashlr-genome-init --summarize` works reliably. Recommends a fast 3B model and smoke-tests it.
+---
+
+> **Pro tip:** Pro and Team users can skip Ollama entirely — the plugin auto-routes summarization to the hosted cloud LLM (xAI Grok 4.3) once `~/.ashlr/pro-token` is present. See `/ashlr-upgrade`. Ollama remains the recommended path for free tier and offline use.
+
+Run the guided Ollama setup script and relay its output.
+
+Steps:
+
+1. If the user asked for "automatic", "auto", "just install it", "yes", or
+   passed a `--yes` / `-y` / `auto` argument, include `--yes` in the command
+   below. Otherwise omit it — the script will print the exact `ollama pull`
+   command for the user to run themselves.
+
+2. Run this via Bash:
+
+   ```
+   bun run ${CLAUDE_PLUGIN_ROOT}/scripts/ollama-setup.ts [--yes]
+   ```
+
+   If `$CLAUDE_PLUGIN_ROOT` is unset, resolve the plugin root the same way
+   other ashlr commands do (walk up from this command file to find
+   `.claude-plugin/plugin.json`).
+
+3. Relay the script's stdout verbatim inside a fenced code block. Do not
+   paraphrase or truncate — each line carries a glyph (`✓` pass, `✗` fail,
+   `⚠` warn, `ℹ` info) and any `fix:` line is copy-pasteable.
+
+4. If the script exits non-zero:
+   - `1` means a user-actionable issue (Ollama not installed, daemon not
+     running, or a model needs to be pulled). The output already contains
+     the exact next command — do not invent your own instructions.
+   - `2` means an internal error. Ask the user to file an issue with the
+     output block.
+
+5. If the script exits `0`, confirm briefly that `/ashlr-genome-init
+   --summarize` will now use the recommended model. No other preamble.

package/commands/ashlr-orchestrate-status.md

@@ -0,0 +1,72 @@
+---
+name: ashlr-orchestrate-status
+description: Inspect past /ashlr-orchestrate runs — list recent runs or drill into a single graph by id.
+---
+
+## Description
+
+`/ashlr-orchestrate-status` reads the local orchestration result cache under `~/.ashlr/orchestrations/` and renders either a flat table of recent runs (default) or a per-node tree for a single graph. Each `/ashlr-orchestrate` invocation persists a `result.json` here best-effort, so this command works fully offline with no network or telemetry side-effects.
+
+The cache is pruned to the 50 most-recent runs on every write, so disk usage stays bounded without manual cleanup.
+
+## Usage examples
+
+```bash
+# Show a table of the 10 most-recent runs
+/ashlr-orchestrate-status
+
+# Drill into a single run by graph-id
+/ashlr-orchestrate-status g-abc12345
+
+# Dump raw JSON (list mode or detail mode) for piping to jq
+/ashlr-orchestrate-status --json
+/ashlr-orchestrate-status --json g-abc12345
+
+# Show more than 10 rows
+/ashlr-orchestrate-status --last 25
+```
+
+## Output
+
+List mode prints a fixed-width table with one row per run, newest first:
+
+```
+graph-id                  ok      startedAt               tokens    goal
+------------------------  ------  ----------------------  --------  ------------------------
+g-1727-mfa                ok      2026-05-22T18:04:12.0…  24000     refactor the auth flow t…
+g-1727-retry              fail    2026-05-22T17:11:03.4…  16000     harden retry logic in se…
+g-1727-docs               ok      2026-05-22T15:48:51.9…  12000     document the orchestrat…
+
+3 of 3 runs shown
+```
+
+Detail mode renders a per-node tree:
+
+```
+Run g-1727-mfa
+  goal:       refactor the auth flow to add MFA
+  tier:       pro
+  ok:         true
+  startedAt:  2026-05-22T18:04:12.013Z
+  finishedAt: 2026-05-22T18:04:13.821Z
+  duration:   1808ms
+  tokens:     24000
+  nodes:
+    ├─ [ok]   node-explore       (refactorer, 412ms, 8000 tokens)
+    ├─ [ok]   node-implement     (refactorer, 1083ms, 8000 tokens)
+    └─ [ok]   node-verify        (test-writer, 313ms, 8000 tokens)
+```
+
+When the cache is empty: `No orchestration runs yet — use /ashlr-orchestrate to start.` (exit 0).
+When an id is given but not found: `No run found with id <graph-id>` (exit 1).
+Malformed `result.json` files are skipped with a one-line stderr warning.
+
+## Invocation
+
+Run via Bash:
+
+```sh
+bun run ${CLAUDE_PLUGIN_ROOT}/scripts/cli-orchestrate-status.ts "$ARGUMENTS"
+```
+
+Pass `$ARGUMENTS` through verbatim. Print the stdout inside a fenced code block so the table aligns.

package/commands/ashlr-orchestrate.md

@@ -0,0 +1,83 @@
+---
+name: ashlr-orchestrate
+description: Distributed-orchestration MVP — expand a goal into a task graph, preview the DAG, confirm, and run it (Pro / Team only).
+---
+
+## Description
+
+> **Experimental MVP — stub executor by default.** Each node currently runs a
+> Bun subprocess that echoes `STUB-NODE: <id>` rather than calling a real AI
+> model. No actual work is performed on your codebase. Set
+> `ASHLR_ORCHESTRATE_REAL_LLM=1` to route nodes through the configured LLM
+> provider (requires `ANTHROPIC_API_KEY` or a Pro token with cloud-LLM access).
+> The real executor is read-only in this MVP — it produces a plan summary but
+> does not write files or run commands.
+
+`/ashlr-orchestrate` takes a free-text goal, auto-expands it into a small task graph (DAG of explore/implement/verify nodes scoped to a directory), shows you a dry-run preview, and on confirmation walks the graph in dependency order. Each node runs in its own sandbox so a failure in one branch doesn't poison the rest. This is the Q1 '27 distributed-orchestration MVP — local-only, capped at 3 nodes on Pro and 10 on Team. Free is blocked with a pointer to `/ashlr-upgrade`.
+
+The flow is:
+
+1. Tier check (free → blocked, helpful upgrade message).
+2. Either auto-expand the goal into a graph **or** load a graph you wrote / edited as YAML (`--yaml <path>`).
+3. Render the DAG to stdout as a dry-run preview (goal, scope, tier, node count, per-node description + deps + scope + model).
+4. Prompt `y` / `n` / `e`:
+   - `y` runs it.
+   - `n` cancels with exit 0.
+   - `e` writes the current graph as YAML to `~/.ashlr/orchestrate-edit-<id>.yaml`, prints the path, and exits so you can hand-edit + re-run with `--yaml`.
+5. After the run, print a summary: total wall-clock, total tokens, per-node ok/fail.
+
+`--auto-confirm` skips the prompt. `--dry-run` runs the graph in dry-run mode (no real subprocesses spawn).
+
+## Usage examples
+
+```bash
+# Goal-only — auto-expand against the current directory
+/ashlr-orchestrate "refactor the auth flow to add MFA"
+
+# Goal + explicit scope (limits the agents to one subtree)
+/ashlr-orchestrate "harden retry logic" --scope ./servers
+
+# Run a hand-edited or pre-saved YAML graph
+/ashlr-orchestrate --yaml ./.ashlr/my-graph.yaml --auto-confirm
+```
+
+## Tier gates
+
+| Tier  | Behavior                                                     |
+| ----- | ------------------------------------------------------------ |
+| free  | Blocked. Prints "Orchestration requires Pro or Team. Run /ashlr-upgrade." and exits 1. |
+| pro   | Local-only. Max **3** agents per graph.                      |
+| team  | Local-only this MVP. Max **10** agents per graph. (Remote workers ship in v1.34.) |
+
+Free users are never silently downgraded — they're stopped before any expand call so no tokens are spent.
+
+## Output
+
+The dry-run preview is a flat list of nodes in declaration order, each tagged with its dependency edges (`← explore`), scope, and model tier. After it prints:
+
+```
+Press y to execute, n to cancel, e to edit YAML.
+```
+
+On `e`, the YAML path is printed and the command exits without running. On `y` (or with `--auto-confirm`), the runner walks the graph in topo order and emits a final block:
+
+```
+Run summary
+  ok:        true
+  duration:  812ms
+  tokens:    24000
+  nodes:
+    [ok]  explore     (212ms, 8000 tokens)
+    [ok]  implement   (483ms, 8000 tokens)
+    [ok]  verify      (117ms, 8000 tokens)
+```
+
+## Invocation
+
+Run via Bash:
+
+```sh
+bun run ${CLAUDE_PLUGIN_ROOT}/scripts/cli-orchestrate.ts "$ARGUMENTS"
+```
+
+Pass `$ARGUMENTS` through verbatim — the CLI parses `--scope`, `--yaml`, `--auto-confirm`, and `--dry-run` itself. Print the stdout in a fenced code block so the DAG preview renders with column alignment.

package/commands/ashlr-parallelize.md

@@ -0,0 +1,63 @@
+---
+name: ashlr-parallelize
+description: Spawn N parallel sub-agents — one per file — each applying the same task instruction. Merges results into a unified report.
+argument-hint: "`<task>` `<file1>` [file2] [file3] ... [--code]"
+---
+
+Spawn one sub-agent per file, all running the same task in parallel, then merge their outputs.
+
+## Usage
+
+```
+/ashlr-parallelize <task> <file1> [file2] [file3] ... [--code]
+```
+
+- `<task>` — the instruction to apply to each file (quoted string or unquoted phrase ending before the first file path).
+- `<file1> [file2] ...` — one or more file paths (contain `/` or `.` or start with `__`).
+- `--code` — optional flag. When present, use `ashlr:ashlr:code` (sonnet) agents instead of the default `ashlr:ashlr:explore` (haiku) agents. Use `--code` when the task requires edits; omit for read-only analysis.
+
+## Examples
+
+```
+/ashlr-parallelize "explain what this module exports" src/utils.ts src/helpers.ts src/types.ts
+/ashlr-parallelize "find all TODO comments and summarize them" hooks/pretooluse-read.ts hooks/pretooluse-bash.ts
+/ashlr-parallelize --code "add JSDoc to all exported functions" servers/read-server.ts servers/grep-server.ts
+```
+
+## Steps
+
+1. Parse `$ARGUMENTS`:
+   - Detect `--code` flag (remove from argument list before further parsing).
+   - Determine `subagent_type`: `ashlr:ashlr:code` if `--code`, else `ashlr:ashlr:explore`.
+   - Split remaining tokens: file-path-like tokens (contain `/`, `.`, or start with `__`) → file list; everything before the first file path → task string.
+   - If no files are found, error: "No files specified. Usage: /ashlr-parallelize `<task>` `<file1>` [file2] ..."
+   - If task string is empty, error: "No task specified. Usage: /ashlr-parallelize `<task>` `<file1>` [file2] ..."
+
+2. For each file, construct an agent prompt:
+   ```
+   Task: <task>
+
+   File: <file_path>
+
+   Focus exclusively on this file. Do not read other files unless they are direct imports needed to answer the task. Keep your response under 300 words. Cite file:line for every claim.
+   ```
+
+3. Spawn all agents in parallel via the Agent tool — one per file — each with `subagent_type` as determined in step 1.
+
+4. Wait for all agents to complete.
+
+5. Print merged report:
+   ```
+   ## /ashlr-parallelize — <N> agents · task: <task>
+
+   ### <file1>
+   <agent 1 output>
+
+   ### <file2>
+   <agent 2 output>
+
+   ---
+   Agents: <N> · subagent_type: <type> · files: <list>
+   ```
+
+Reuses agent definitions from `agents/ashlr-explore.md` (default) and `agents/ashlr-code.md` (--code).

package/commands/ashlr-report-crash.md

@@ -0,0 +1,33 @@
+---
+name: ashlr-report-crash
+description: Upload a recent ashlr-plugin crash dump to the maintainer. Opt-in, already-redacted, one report per invocation. Gives the founder faster bug signal when something in the plugin threw.
+---
+
+Run the report-crash script and help the user review what will leave their machine before it uploads.
+
+Steps:
+
+1. Run this command via Bash:
+
+   ```
+   bun run ${CLAUDE_PLUGIN_ROOT}/scripts/report-crash.ts $ARGUMENTS
+   ```
+
+   If `$CLAUDE_PLUGIN_ROOT` is unset, resolve the plugin root by walking up from a known ashlr path until `.claude-plugin/plugin.json` is found (same resolution as `/ashlr-doctor`).
+
+2. Print the script's stdout/stderr verbatim. The script owns the preview, the confirm prompt, and the upload — do not paraphrase. It exits 0 on success, 1 if no crashes found, 2 if the user declined, 3 on network error.
+
+3. If the user is unsure whether to upload, recommend `--dry-run` first: it shows exactly the JSON that would leave the machine without sending anything.
+
+Flags (forwarded via `$ARGUMENTS`):
+
+| Flag | Purpose |
+|---|---|
+| `--dump <path>` | Upload a specific `~/.ashlr/crashes/YYYY-MM-DD.jsonl` file instead of the most recent record |
+| `--all` | Upload every record from the last 7 days (default: 1 most-recent) |
+| `--dry-run` | Preview only — print what would be sent, do not upload |
+| `--stdout` | Print the redacted record(s) to stdout so the user can paste into a GitHub issue |
+| `--yes` | Skip the "confirm before upload" prompt |
+| `--endpoint <url>` | Override the upload endpoint (defaults to `$ASHLR_CRASH_UPLOAD_URL` or production) |
+
+Privacy posture: dumps are already redacted at write time by `servers/_crash-dump.ts` (Authorization headers, `sk-*`/`gh*_*` tokens, 40-char hex, key/value pairs named `token`/`apiKey`/`secret`/`password`/`cookie`). The upload path does **not** add anything beyond what's already on disk plus `pluginVersion` and `process.platform`. No cwd, no paths beyond the crash args that were already in the tool call at crash time, no stdin/stdout of any command.

package/commands/ashlr-resume.md

@@ -0,0 +1,72 @@
+---
+name: ashlr-resume
+description: Resume your last coding session — shows what you were doing, which files were active, and suggested next steps.
+argument-hint: "[<branch-name>]"
+---
+
+Show a compact summary of the most recent ashlr session so you can pick up
+exactly where you left off.
+
+## Usage
+
+```
+/ashlr-resume
+/ashlr-resume <branch-name>
+```
+
+- **No argument** — summarizes the single most recent session regardless of branch.
+- **With a branch name** — finds the most recent session whose timestamp overlaps
+  commits on that branch (cross-references via `git log`), then labels the
+  output with that branch.
+
+## What it shows
+
+```
+Last session (yesterday, 2h ago — saved 4.3M tokens ≈$12.90):
+  Branch:   feature/auth-flow
+  Work dir: myapp  (12 reads, 4 edits)
+            __tests__  (5 reads, 3 edits)
+  Patterns: ashlr__grep ×7, Grep ×2
+  Bash:     Bash ×18, ashlr__bash ×3
+  Calls:    42 tool invocations
+
+Resume? Suggested next steps based on the trail:
+  - Re-open myapp (last edits in this session)
+  - Re-run: Bash (used ×18 last session)
+  - Continue on branch: feature/auth-flow
+```
+
+## Behavior
+
+- Reads `~/.ashlr/session-log.jsonl` (active file) plus up to two rotated
+  backups (`.jsonl.1`, `.jsonl.2`). Read-only — never modifies the log.
+- If the log is missing or empty, prints "No prior sessions found — you're
+  starting fresh."
+- Token savings figures come from `session_end` events written at session close.
+  If no `session_end` is present, tokens-saved shows as 0.
+
+## Limitations
+
+The session log records **tool names and working directories**, not individual
+file paths or the content of grep patterns / bash commands. As a result:
+
+- "Work dir" shows the repository directory rather than specific file paths.
+- "Patterns" shows which grep tools were invoked (and how many times), not the
+  actual search strings.
+- "Bash" shows call counts for bash-family tools, not the specific commands run.
+
+Individual argument capture is not part of the session-log schema (v1) by design
+— arguments may contain secrets. A future schema version may add opt-in argument
+hinting.
+
+## Implementation
+
+```sh
+bun run ${CLAUDE_PLUGIN_ROOT}/scripts/session-resume.ts [<branch>]
+```
+
+Print the script's stdout verbatim. The output is designed to be read directly;
+do not paraphrase or reformat it.
+
+If the script fails, fall back to:
+`/ashlr-resume failed — check ~/.ashlr/session-log.jsonl exists and is readable.`

package/commands/ashlr-savings.md

@@ -0,0 +1,24 @@
+---
+name: ashlr-savings
+description: Show estimated tokens and cost saved by the ashlr-plugin this session and lifetime.
+---
+
+Call the `ashlr__savings` MCP tool and show its output to the user **verbatim** inside a fenced code block (```) so the ASCII bar charts and column alignment render correctly.
+
+The tool already returns a rich multi-line report covering:
+- Session age and pricing model in use
+- Two-column summary (this session vs all-time): calls, tokens saved, estimated dollar cost saved
+- Per-tool breakdown for the current session (calls, tokens, proportional bar, percentage)
+- A 7-day sparkline of daily tokens-saved (scaled to the busiest day)
+- Pro upgrade nudge telemetry (when the user has crossed the 50k threshold at least once): `shown N · clicked M · rate P%`. Pro/Team users see the same stats labeled "historical" — no live nudge renders anymore.
+
+After the verbatim block, add **at most one** short line:
+- If session `calls` is 0: "No ashlr__read/grep/edit calls yet — try those in place of the built-ins to start accumulating savings."
+- If session `calls` is non-zero and lifetime `calls` is under 20: "Still warming up — numbers get more meaningful after a few dozen calls."
+- Otherwise: say nothing extra. The report speaks for itself.
+
+Pricing note (only surface if the user asks how the dollar figure is derived): the report uses Claude Sonnet 4.5 input pricing ($3.00 per million tokens) by default. Override with the `ASHLR_PRICING_MODEL` env var (`sonnet-4.5` | `opus-4` | `haiku-4.5`).
+
+Do not paraphrase the numbers — the user wants the exact tool output, not a rewritten summary.
+
+Want a richer view? `/ashlr-dashboard` renders a multi-panel dashboard with ANSI colors, per-tool bar charts, 7-day and 30-day sparklines, top projects, and a projected-annual-savings extrapolation.

package/commands/ashlr-settings.md

@@ -0,0 +1,50 @@
+---
+name: ashlr-settings
+description: View or change ashlr-plugin settings.
+---
+
+Settings for the ashlr-plugin live in `~/.claude/settings.json` under the `ashlr` key. All toggles default to `true` unless stated otherwise.
+
+```json
+{
+  "ashlr": {
+    "attribution": true,
+    "statusLine": true,
+    "statusLineSession": true,
+    "statusLineLifetime": true,
+    "statusLineTips": true,
+    "editBatchingNudge": true
+  }
+}
+```
+
+| Key | Default | What it controls |
+|-----|---------|------------------|
+| `attribution` | `true` | `commit-attribution` hook appends `Assisted-By: ashlr-plugin` to git commits |
+| `statusLine` | `true` | Master toggle for the status-line integration |
+| `statusLineSession` | `true` | Show this session's savings in the status line |
+| `statusLineLifetime` | `true` | Show lifetime savings in the status line |
+| `statusLineTips` | `true` | Rotate short tips in the status line |
+| `editBatchingNudge` | `true` | Nudge the agent to batch multiple edits to the same file |
+
+> `toolRedirect` was retired in v1.18: the Read/Grep/Edit routing is handled by the `pretooluse-*` hooks and controlled via `ASHLR_HOOK_MODE` (`redirect` | `nudge` | `off`) or `~/.ashlr/settings.json { "toolRedirect": false }` for a full opt-out. The old `~/.claude/settings.json { ashlr: { toolRedirect } }` key is ignored.
+
+## Applying a change
+
+Parse the user's request, read the current settings file with `Read` or `ashlr__read`, apply the change via `Edit` or `ashlr__edit`, and confirm the new value.
+
+Changes to hook-driven toggles (`attribution`, `editBatchingNudge`) take effect on the next tool call. Changes to status-line toggles take effect on the next status-line refresh.
+
+## Status-line install
+
+If the user hasn't installed the status line yet, the settings file won't have a `statusLine.command` entry. Run:
+
+```bash
+bun run ~/.claude/plugins/ashlr-plugin/scripts/install-status-line.ts
+```
+
+That writes a safe, idempotent entry into `~/.claude/settings.json` pointing at `scripts/savings-status-line.ts`. A timestamped backup is made before any write.
+
+## If the user just asked a question
+
+Show the relevant current values without editing anything.