@damian87/omp 0.9.2 → 0.12.0

package/.github/copilot-instructions.md

@@ -13,6 +13,22 @@ Default behaviours installed with this repo. Override per project as needed.
 - Read the diff before committing.
 - If unsure about scope, ask.
 
+## Cost/token discipline
+Cost data is local, best-effort, and estimated. `omp cost [--today] [--session <id>]`
+summarizes prompt/tool token estimates from the hook ledger; it is not provider billing.
+
+The cost hooks apply when this plugin's `hooks/hooks.json` is active in a Copilot CLI
+session. They give session-wide visibility for skills invoked inside that session, not
+standalone coverage for copied skills, raw shell scripts, or external CLIs.
+
+Before rerunning noisy commands or failed edits, inspect the latest output and narrow the
+next attempt. Prefer bounded summaries for large logs. Oversized postToolUse output is
+minimized before it re-enters model context, with raw output preserved on disk and savings
+recorded in the cost ledger. Diagnostics (errors, stack traces, assertions) are preserved
+inline; other trimmed detail must be recovered by re-reading the raw file path noted in the
+hook output (an extra tool call), so full fidelity depends on the model following that pointer.
+Budget gates and retry-cost guidance are not current live behavior.
+
 ## Skills
 Slash commands under `.github/skills/<name>/SKILL.md` are auto-discovered by Copilot. See `omp list` for the catalog active in this project.
 

package/.github/skills/create-skill/SKILL.md

@@ -25,13 +25,13 @@ Skills are modular, self-contained packages that extend agent capabilities by pr
 ### Three-Level Loading System
 
 1. **Metadata (name + description)** - Always in context (~100 words)
-2. **SKILL.md body** - When skill triggers (<200 lines, ideally <500 lines for optimal performance)
+2. **SKILL.md body** - When skill triggers (under 200 lines; split overflow into `references/`)
 3. **Bundled resources** - As needed by agent (unlimited)
 
 ### Why Progressive Disclosure Matters
 
-- 85% reduction in initial context load
-- Activation times drop from 500ms+ to under 100ms
+- Smaller initial context load
+- Faster activation — the agent loads the body only when the skill triggers
 - Agent loads only what's needed, when it's needed
 - Skills remain maintainable and focused
 

package/.github/skills/daily-log/SKILL.md

@@ -23,7 +23,7 @@ The SessionStart hook injects a one-line breadcrumb, e.g.:
 
 ```
 [DAILY LOG] Goal: <today's goal>
-N entries logged in the last 7 days — run `omp daily-log read` to load if relevant.
+N entries logged in the last 7 days — run `omp daily-log read --days 7` to load if relevant.
 ```
 
 If the breadcrumb looks relevant to what the user is asking for — same feature, an open

package/.github/skills/jira-ticket/SKILL.md

@@ -16,21 +16,24 @@ Use `/jira-ticket` when work tracking is requested.
 ## Operations
 
 ### Create
-- Build from an approved plan or implementation slice
+- Build from an approved plan or implementation slice (a plan file or markdown)
 - Include: Summary, Description, Acceptance Criteria
-- If Jira config is available, create via API; otherwise output a dry-run payload
+- Render the payload with `omp jira render <plan-file>` — this **never** writes to Jira. To create/comment/update, run `omp jira apply <plan-file-or-ticket-key>`, which defaults to **dry-run** and only writes when Jira is configured with `JIRA_MODE=live`, the user has explicitly confirmed, and the CLI has explicit body/field support for the operation you need.
 
 ### Comment
 - Add implementation evidence, verification results, or status updates
 - Format for readability (use Jira wiki markup, not Markdown)
+- Draft the comment payload and preview via dry-run only; do not run live comment writes from this skill until the CLI accepts an explicit comment body/body file.
 
 ### Safe update
 - Only update known simple fields (summary, description, labels)
+- Draft update fields and preview via dry-run only; do not run live update writes from this skill until the CLI accepts explicit update fields.
 - Do not guess transitions, issue links, project keys, or secrets
 
 ## Rules
 
-- If Jira config is missing, always output a **dry-run payload** — never fail silently
+- Always preview with `omp jira render` or `omp jira apply … --dry-run` (the default); live writes require explicit user confirmation plus CLI support for the exact payload being written
+- If Jira config is missing, the commands stay in dry-run and print the payload — never fail silently
 - Do not guess project keys, transitions, or credentials
 - Keep acceptance criteria testable and specific
 - Include file paths and evidence when commenting with implementation details

package/.github/skills/omp-autopilot/SKILL.md

@@ -32,7 +32,7 @@ Run `/research-codebase` to understand current state. Skip if you already have f
 
 ### Phase 2 — Plan
 
-Run `/ralplan` to produce an implementation plan with acceptance criteria. If a consensus plan already exists from a prior `/ralplan`, skip this phase.
+Run `/ralplan` to produce an implementation plan with acceptance criteria. If a plan already exists from a prior `/ralplan`, skip this phase.
 
 ### Phase 3 — Execute
 
@@ -73,3 +73,7 @@ Before claiming done:
 - [ ] Lint clean (if applicable)
 - [ ] `/verify` or `/ultraqa` produced PASS evidence
 - [ ] No uncommitted work left behind
+
+## Cost/token note
+
+This skill can drive multiple tool calls or long-running output. Use `omp cost [--today] [--session <id>]` for local hook-ledger estimates only; it is not provider billing. Keep injected summaries concise and prefer bounded output when rerunning noisy commands.

package/.github/skills/ralph/SKILL.md

@@ -21,16 +21,18 @@ Use `/ralph` when one owner should complete one clear task end-to-end.
 
 ## Input
 
-Accept a plan from `/ralplan`, a ticket, or a concrete task description. If a `/ralplan` consensus plan exists, use its acceptance criteria as your definition of done.
+Accept a plan from `/ralplan`, a ticket, or a concrete task description. If a `/ralplan` plan exists, use its acceptance criteria as your definition of done.
 
 ## Steps
 
-1. **Start** from the plan or task. State what "done" looks like before writing code.
+1. **Register the loop** — run `omp ralph start "<task>" --max-iterations 10`. This tracks the loop so `omp ralph status` and `/team` nudges can see it and the iteration cap is enforced. State what "done" looks like before writing code.
 2. **Implement** one slice at a time, in plan order.
 3. **Verify after each slice** — run tests, lint, type-check. Do not batch verification to the end.
 4. **Fix** any failures immediately before moving to the next slice.
-5. **Repeat** until all slices complete with evidence, or a blocker is hit.
-6. **Final verification** — run the full test suite one last time after all slices.
+5. **Tick the loop** — run `omp ralph tick` after each slice. If it reports the iteration cap is reached, stop and report.
+6. **Repeat** until all slices complete with evidence, or a blocker is hit.
+7. **Final verification** — run the full test suite one last time after all slices.
+8. **End the loop** — run `omp ralph cancel` once done or blocked, so the tracked state is cleared.
 
 ## Circuit breaker
 

package/.github/skills/research-codebase/SKILL.md

@@ -22,7 +22,7 @@ Respond: "I'm ready to research the codebase. What area or question should I inv
 
 ### 1. Read mentioned files
 
-If the user references specific files, read them with `view` in the **main context** before anything else.
+If the user references specific files, read them directly in the **main context** before anything else.
 
 ### 2. Scope the tech stack
 
@@ -32,14 +32,14 @@ Detect from `package.json`, config files, directory structure, and project conve
 
 | Tier | When | Agent strategy |
 |------|------|----------------|
-| **Small** | Single file/component, narrow question | Main agent reads directly. No subagents. |
-| **Medium** | Cross-file, single area (e.g. "how does auth work") | 1–2 `explore` agents for locate + analyse |
-| **Large** | Cross-cutting, multi-area (e.g. "map the entire API layer") | Parallel locator → analyser → pattern-finder (see `reference/agent-prompts.md`) |
+| **Small** | Single file/component, narrow question | Read and search directly (glob/grep/read). No delegation. |
+| **Medium** | Cross-file, single area (e.g. "how does auth work") | Locate with glob/grep, then read and analyse the hits directly. |
+| **Large** | Cross-cutting, multi-area (e.g. "map the entire API layer") | Sweep area-by-area (locate → analyse → find patterns), or delegate areas to parallel `omp team` workers (see `reference/agent-prompts.md`). |
 
 ### 4. Research
 
-- Track subtasks via SQL `todos` table
-- For medium/large: read `reference/agent-prompts.md` for subagent prompt templates
+- Track subtasks in a markdown checklist as you go
+- For large: read `reference/agent-prompts.md` for `omp team` worker prompt templates
 - **MUST GATE**: Before writing findings, show file:line evidence for every claim
 
 ### 5. Synthesise & write document
@@ -56,3 +56,7 @@ Show concise summary to user with key file references. Ask if they have follow-u
 ### 7. Follow-ups
 
 If the user has follow-ups, read `reference/follow-up.md` for the append protocol.
+
+## Cost/token note
+
+This skill can drive multiple tool calls or long-running output. Use `omp cost [--today] [--session <id>]` for local hook-ledger estimates only; it is not provider billing. Keep injected summaries concise and prefer bounded output when rerunning noisy commands.

package/.github/skills/research-codebase/reference/agent-prompts.md

@@ -1,8 +1,8 @@
-# Subagent Prompt Templates
+# Worker Prompt Templates
 
-Use these templates when spawning `explore` agents via the `task` tool. Only used for **medium** and **large** research tasks.
+Use these templates when delegating research areas to parallel `omp team` workers. Only needed for **large** research tasks; for small/medium, run these roles directly in the main agent with glob/grep/read.
 
-## Agent roles
+## Worker roles
 
 ### Locator — find WHERE files and components live
 
@@ -31,8 +31,8 @@ Do not evaluate consistency or suggest changes — only document occurrences.
 
 ## Guidelines
 
-- Each agent is stateless — provide complete context in the prompt
-- Remind every agent: "You are documenting, not evaluating"
-- Run independent explorations in parallel
-- For web research (only if user explicitly asks), use a `research` agent instead of `explore`
-- **Wait for ALL agents to complete before synthesising**
+- Each worker is stateless — provide complete context in the prompt
+- Remind every worker: "You are documenting, not evaluating"
+- Run independent explorations in parallel across team panes
+- For web research (only if user explicitly asks), do it in the main agent
+- **Collect all worker outputs before synthesising**

package/.github/skills/schedule/SKILL.md

@@ -69,3 +69,7 @@ omp schedule add --id nightly-tests --cron "0 2 * * *" \
   --prompt "Run the test suite; if anything fails, open an issue with the log." \
   --allow-all-tools --max-runs 7
 ```
+
+## Cost/token note
+
+This skill can drive multiple tool calls or long-running output. Use `omp cost [--today] [--session <id>]` for local hook-ledger estimates only; it is not provider billing. Keep injected summaries concise and prefer bounded output when rerunning noisy commands.

package/.github/skills/slack/SKILL.md

@@ -57,6 +57,7 @@ The CLI returns a structured result:
 - Success: `posted to <channel> (ts=<ts>[, opened IM])` — relay that.
 - Failure: `notify failed [<CODE>]: <reason>` — surface the code + reason so the user
   can act. Common codes:
+  - `MISSING_TEXT` — the message body was empty; pass a non-empty `--text`.
   - `MISSING_TOKEN` — run `omp env init` to set `SLACK_BOT_TOKEN`.
   - `MISSING_TARGET` — pass `--target` or run `omp env init` to set `SLACK_HOME_CHANNEL`.
   - `BAD_TARGET` / `BAD_HOME_CHANNEL` — the ID is malformed; show the user the expected shape.

package/.github/skills/team/SKILL.md

@@ -48,6 +48,8 @@ Write a temporary file at `/tmp/team-lanes-<timestamp>.json`:
 ### Step 2 — Launch
 
 ```bash
+# Installed-plugin path (in a dev checkout the script is at the repo-relative
+# .github/skills/team/scripts/team-launch.sh instead):
 bash ~/.copilot/installed-plugins/oh-my-copilot/oh-my-copilot/.github/skills/team/scripts/team-launch.sh \
   --session "team-<name>" --lanes <lanes-file>
 ```
@@ -76,7 +78,7 @@ Choose this only when the user explicitly wants the team to run in the backgroun
 ### Launch
 
 ```bash
-omp team <N>:copilot "<task description>"
+omp team <N>:copilot "<task description>" --name <name>
 ```
 
 The runtime automatically:
@@ -89,9 +91,9 @@ The runtime automatically:
 ### Monitor and cleanup
 
 ```bash
-omp team status <team-name>       # check progress
+omp team status <name>            # check progress (same <name> passed to --name)
 tmux attach -t omp-team-<name>    # watch panes live
-omp team shutdown <team-name>     # kill when done
+omp team shutdown <name>          # kill when done
 ```
 
 ## Prerequisites
@@ -125,3 +127,7 @@ Use `/ralplan` before `/team` to produce the plan. Use `/verify` after completio
 - Each pane is an independent session — no shared state
 - Workers can message each other via `omp team api send-message` (runtime mode only)
 - If tasks depend on each other, use `/ralph` instead
+
+## Cost/token note
+
+This skill can drive multiple tool calls or long-running output. Use `omp cost [--today] [--session <id>]` for local hook-ledger estimates only; it is not provider billing. Keep injected summaries concise and prefer bounded output when rerunning noisy commands.

package/.github/skills/team/scripts/team-launch.sh

@@ -45,7 +45,9 @@ fi
 if command -v omp &>/dev/null; then
   AGENT_CMD="omp --madmax"
 elif command -v copilot &>/dev/null; then
-  AGENT_CMD="copilot"
+  # --yolo = all permissions (tools+paths+urls) so worker panes never block on a
+  # trust/permission dialog. Matches the bypass `omp --madmax` grants.
+  AGENT_CMD="copilot --yolo"
 else
   echo "Neither omp nor copilot CLI found" >&2; exit 1
 fi
@@ -78,9 +80,11 @@ wait_for_ready() {
       return 0
     fi
 
-    # Auto-accept folder trust dialog
+    # Auto-accept folder trust dialog. Use the `Enter` key NAME, not C-m:
+    # Copilot CLI >=1.0.61 ignores a literal carriage return (C-m) for TUI
+    # selection/submit, so C-m left the trust dialog open and the agent hung.
     if (( accepted == 0 )) && echo "$txt" | grep -q 'Do you trust'; then
-      tmux send-keys -t "$pane" C-m
+      tmux send-keys -t "$pane" Enter
       accepted=1
       echo "    ↳ Auto-accepted folder trust for $pane"
     fi
@@ -142,10 +146,12 @@ for i in $(seq 0 $((LANE_COUNT - 1))); do
   LANE_NAME=$(jq -r ".[$i].name" "$LANES_FILE")
   PANE_ID="${PANE_IDS[$i]}"
 
-  # -l = literal (no key interpretation), then C-m = Enter as a separate call
+  # -l = literal (no key interpretation), then submit. Use the `Enter` key NAME,
+  # not C-m: Copilot CLI >=1.0.61 ignores a literal carriage return, so C-m left
+  # the prompt sitting unsent in the input buffer and the agent never started.
   tmux send-keys -t "$PANE_ID" -l "$LANE_PROMPT"
   sleep 0.3
-  tmux send-keys -t "$PANE_ID" C-m
+  tmux send-keys -t "$PANE_ID" Enter
 
   echo "  📨 Sent to $PANE_ID ($LANE_NAME)"
 done

package/.github/skills/ultraqa/SKILL.md

@@ -20,6 +20,8 @@ Use `/ultraqa` after implementation when shallow checks are not enough.
 
 ## Steps
 
+Register the QA run first: `omp ultraqa start "<goal>" --max-cycles 5`. This tracks the cycle count and enforces the cap, and lets `omp ultraqa status`/`cancel` see the run.
+
 ### Cycle 1 (and each subsequent cycle)
 
 Number every cycle explicitly: "Cycle 1", "Cycle 2", etc.
@@ -33,13 +35,14 @@ Number every cycle explicitly: "Cycle 1", "Cycle 2", etc.
 
 ### After each cycle
 
+- Record the outcome: `omp ultraqa cycle fail` (issues found) or `omp ultraqa cycle pass` (clean). This increments the counter and reports when the cap is reached.
 - If issues found → fix and start next cycle
-- If clean → report PASS and stop
+- If clean → report PASS and run `omp ultraqa cancel` to clear the run
 - Track which issues were found and fixed per cycle
 
 ## Early exit conditions
 
-- **5 cycles reached** — stop, report remaining issues as known gaps
+- **5 cycles reached** (enforced by `omp ultraqa cycle`) — stop, report remaining issues as known gaps
 - **Same failure 3 consecutive cycles** — stop, this is a design issue not a bug. Report it for `/ralplan`
 - **Critical regression found** — stop immediately, report before fixing anything else
 

package/.github/skills/ultrawork/SKILL.md

@@ -21,17 +21,17 @@ Use `/ultrawork` when there are many independent, low-conflict work items that c
 
 ## Composition
 
-Ultrawork is the **parallelism primitive** in the skill stack:
+Ultrawork is the **batch-execution** branch of `/omp-autopilot` Phase 3 — a sibling of `/ralph` (single linear task) and `/team` (parallel panes), not nested inside them:
 ```
-/omp-autopilot → /ralph (persistence) → /ultrawork (parallelism)
+/omp-autopilot → /ralph  OR  /team  OR  /ultrawork
 ```
-Ralph wraps ultrawork when a persistent verify loop is needed around batched work.
+Pick `/ultrawork` when the work is many independent mechanical items. It can also be invoked directly.
 
 ## Steps
 
 ### 1. Inventory
 
-List all tasks. For each, note the files it touches. Flag any collisions.
+Register the batch so the run is tracked and `/team` nudges can see it: `omp ultrawork start "<objective>" --task-count <n>`. Then list all tasks. For each, note the files it touches. Flag any collisions.
 
 ### 2. Dependency check
 
@@ -51,7 +51,7 @@ Process each wave. For each task in the wave:
 
 ### 4. Report
 
-Summarise: completed, failed, blocked.
+Summarise: completed, failed, blocked. Then clear the tracked state with `omp ultrawork cancel`.
 
 ## Stop conditions
 
@@ -71,3 +71,7 @@ Summarise: completed, failed, blocked.
 - `Completed` — items done with evidence
 - `Failed/blockers` — items that couldn't be completed and why
 - `Verification` — test/lint/build results per wave
+
+## Cost/token note
+
+This skill can drive multiple tool calls or long-running output. Use `omp cost [--today] [--session <id>]` for local hook-ledger estimates only; it is not provider billing. Keep injected summaries concise and prefer bounded output when rerunning noisy commands.

package/.github/skills/weighted-consensus/SKILL.md

@@ -70,9 +70,10 @@ omp council "<question>" [--models a,b,c | model:role:weight,...] \
 - Timed-out members that produced valid JSON before the kill signal are
   automatically recovered as survivors — they are not dropped.
 
-If `omp council` is not found (the published `omp` predates this feature), fall
-back to the local build from the repo root: `node dist/src/cli.js council "<question>" ...`
-(run `npm run build` first if `dist/` is stale).
+If `omp council` is not found (the published `omp` predates this feature),
+update the global CLI: `npm i -g @damian87/omp@latest`, then re-run `omp council`.
+(The `node dist/src/cli.js council` build only resolves from inside the
+oh-my-copilot repo, so it is not a portable fallback for an arbitrary project.)
 
 ### Step 3 — Present the result
 
@@ -126,3 +127,7 @@ default roster is used.
 
 Pair with `/code-review` (pass a review rubric + the diff as context) for a
 multi-model review verdict, or with `/ralplan` to weigh competing plans.
+
+## Cost/token note
+
+This skill can drive multiple tool calls or long-running output. Use `omp cost [--today] [--session <id>]` for local hook-ledger estimates only; it is not provider billing. Keep injected summaries concise and prefer bounded output when rerunning noisy commands.

package/README.md

@@ -55,7 +55,7 @@ That's it.
 - **Persistent execution** — Ralph, UltraQA, and Ultrawork keep going until the goal is verified
 - **File-state coordination** — workers swap typed messages over an outbox/inbox cursor with atomic `O_EXCL` task locks; no broker or daemon to babysit
 - **Chat bridge** — `omp gateway` runs long-lived chat connectors (Slack today, more next) so you can DM Copilot from anywhere
-- **Lifecycle hooks** — `SessionStart`, `UserPromptSubmit`, `PreToolUse`, `PostToolUse`, `SessionEnd`, `Error`
+- **Lifecycle hooks** — `sessionStart`, `userPromptSubmitted`, `preToolUse`, `postToolUse`, `postToolUseFailure`, `sessionEnd`, `errorOccurred`
 - **Doctor included** — `omp doctor` verifies plugin manifest, skills discovery, hooks, and the underlying `copilot` CLI in one shot
 
 ---
@@ -84,6 +84,7 @@ That's it.
 
 - **Context & history as CLI subcommands** — `omp state` (key-value with TTL), `omp project-memory` (notes + directives), `omp trace` (per-session timeline + summary), `omp goal` / `omp memory sync` (managed repo context), `omp daily-log`
 - **Lightweight Copilot context** — managed instructions keep only the repo goal plus on-demand memory commands; set `OMP_DISABLE_INSTRUCTIONS_MEMORY=1` to skip writing the managed block entirely
+- **Estimated cost ledger** — `omp cost [--today] [--session <id>]` summarizes local prompt/tool token estimates recorded by hooks. These are best-effort estimates, not provider billing.
 - **File-state worker coordination** — outbox JSONL + byte cursor, atomic `O_EXCL` task locks, optimistic CAS on claim
 - **Idle nudge** — content-based pane idle detection that pokes stuck workers
 - **Mode-state loops** — single source of truth per loop (Ralph/Ultrawork/UltraQA state files)
@@ -195,6 +196,7 @@ omp ralph start "<task>" [--max-iterations N]
 omp ultrawork start "<objective>" [--task-count N]
 omp ultraqa start "<goal>" [--max-cycles N]
 omp council "<question>" [--models a,b,c] [--context @file] [--json]   # multi-model council
+omp cost [--today] [--session <id>]            # summarize estimated hook-ledger tokens
 omp comms status | send | recv | ask        # drive a running copilot tmux session
 omp gateway serve [--only slack]            # run chat connectors (today: slack)
 omp gateway status [--json]                 # per-connector readiness (no sockets)
@@ -272,6 +274,7 @@ omp grows in vertical slices. Items aren't pinned to specific semver versions
 - **Slack outbound — `omp gateway notify`** — stateless REST `chat.postMessage` from any process (cron `--notify-target`, in-session `/slack <message>`, ad-hoc `omp gateway notify --text "..."`). Default destination from `SLACK_HOME_CHANNEL`; explicit `--target slack:C…/G…/D…/U…` overrides; `U…` auto-resolves to a DM via `conversations.open`.
 - **Weighted-consensus council** — multi-model council with role weights + minority report. Via `omp council` or `/weighted-consensus`.
 - **Suggest** — `omp suggest "<task>"` recommends a slash-skill workflow without launching one.
+- **Estimated cost ledger** — hook-driven prompt/tool token estimates are visible through `omp cost`; oversized `postToolUse` output is minimized before it re-enters model context, with raw output preserved on disk (diagnostics kept inline; other trimmed detail is recoverable by re-reading the raw path the hook reports — an extra tool call, so best with capable models). Budget gates and retry-cost guidance remain next-step optimization work, not shipped behavior yet.
 
 ### Up next
 

package/dist/src/cli.js

@@ -26,7 +26,7 @@ function printResult(result, json) {
     }
 }
 function help() {
-    return `oh-my-copilot\n\nRun \`omp\` with no arguments to launch copilot (permissions bypass OFF).\nUse \`omp help\` to show this list.\n\nCommands:\n  (no args)                                     launch copilot (bypass OFF by default)\n  version [--json]\n  list [--json]\n  setup [--dry-run] [--scope project|user] [--plugin-root <dir>] [--json]\n  doctor [--json] [--copilot-bin <path>] [--skip-copilot]\n  launch -- <args...>\n  --madmax [args...]                          (bare-flag launch with permissions bypass; alias of --yolo)\n  team <N:role> "<task>" [--name <name>] [--json]\n  team status <name> [--json]\n  team shutdown <name> [--json]\n  team api claim-task --input '<json>' [--json]\n  team api transition-task-status --input '<json>' [--json]\n  team api send-message --input '<json>' [--json]\n  team api broadcast --input '<json>' [--json]\n  team api mailbox-list --input '<json>' [--json]\n  team api mailbox-mark-delivered --input '<json>' [--json]\n  council "<question>" [--models a,b,c|m:role:weight] [--context <text|@file>] [--rubric <text|@file>] [--synth <model>] [--probe] [--timeout <ms>] [--synth-timeout <ms>] [--min-survivors <n>] [--max-concurrency <n>] [--tmp-dir <dir>] [--json]\n  comms status [--session <name>] [--json]      (is copilot on + online? auto-discovers session)\n  comms send --text "<prompt>" [--force] [--session <name>] [--json]\n  comms recv [--wait] [--lines <n>] [--timeout <ms>] [--session <name>] [--json]\n  comms ask --text "<prompt>" [--force] [--lines <n>] [--timeout <ms>] [--session <name>] [--json]\n  gateway serve [--only <name>[,<name>]]        (run all configured connectors; today: slack)\n  gateway status [--json] [--only <name>[,...]] (per-connector readiness; no sockets opened)\n  gateway doctor [--json] [--only <name>[,...]] (alias for 'gateway status')\n  gateway notify --text "<msg>" [--target slack:C\\|D\\|G\\|U... [:thread_ts]] [--thread-ts <ts>] [--json]\n                                                (one-shot outbound Slack post; falls back to SLACK_HOME_CHANNEL)\n  slack serve                                   (deprecated alias for 'gateway serve --only slack')\n  slack doctor [--json]                         (deprecated alias for 'gateway status --only slack')\n  env init [--force]                            (interactive: write ~/.omp/.env with Slack tokens + optional SLACK_HOME_CHANNEL)\n                                                non-interactive: set OMP_INIT_BOT_TOKEN/OMP_INIT_APP_TOKEN/OMP_INIT_HOME_CHANNEL\n                                                (env vars preferred over --bot-token/--app-token/--home-channel flags)\n  (--session is optional when exactly one omp-<digits> tmux session is running)\n${registeredCommandHelpLines().join("\n")}\n  ralph start "<task>" [--max-iterations <n>] [--session-id <id>] [--json]\n  ralph status [--json]\n  ralph tick [--json]\n  ralph cancel [--json]\n  ultrawork start "<objective>" [--task-count <n>] [--summary <s>] [--json]\n  ultrawork status [--json]\n  ultrawork cancel [--json]\n  ultraqa start "<goal>" [--max-cycles <n>] [--json]\n  ultraqa cycle pass|fail|pending [--json]\n  ultraqa status [--json]\n  ultraqa cancel [--json]\n  schedule add --id <id> --cron "<expr>" --prompt "<text>" [--bin copilot] [--model <m>] [--cwd <dir>] [--timeout <ms>] [--max-runs <n>] [--ttl-hours <h>] [--allow-all-tools] [--notify-target slack:<ID>] [--dry-run] [--json]\n  schedule list [--json]\n  schedule status <id> [--json]\n  schedule run-now <id> [--json]\n  schedule remove <id> [--json]\n  goal set "<objective>" [--json]\n  goal read [--json]\n  memory sync [--json]                          (render goal+directives into copilot-instructions.md)\n  daily-log set-goal "<text>" [--json]\n  daily-log add "<text>" [--json]\n  daily-log read [--days <n>] [--json]\n  daily-log prune [--keep-days <n>] [--json]\n  state write <key> <val> [--ttl <s>] | read|delete|status <key> | list | cleanup [--json]\n  project-memory read [<id>] | index | add-note "<title>" [--body "<text>"] | add-directive "<rule>" [--json]\n  trace timeline [<sessionId>] [--limit <n>] | summary [<sessionId>] | add <sessionId> <event> [<json>] [--json]\n  catalog list [--json]\n  catalog validate [--json]\n  catalog capability <id> [--json]\n  project inspect [--json]\n  skill install <skill-dir> [--root <repo>] [--scope project|user] [--dry-run] [--json]\n  lint:skills [--root <repo>]\n  sync:dry-run [--root <repo>]\n  jira:dry-run [--root <repo>]\n  jira render <plan-file> [--root <repo>] [--json]\n  jira apply <ticket-key-or-plan-file> --comment|--update|--transition|--link [--dry-run] [--json]\n`;
+    return `oh-my-copilot\n\nRun \`omp\` with no arguments to launch copilot (permissions bypass OFF).\nUse \`omp help\` to show this list.\n\nCommands:\n  (no args)                                     launch copilot (bypass OFF by default)\n  version [--json]\n  list [--json]\n  setup [--dry-run] [--scope project|user] [--plugin-root <dir>] [--json]\n  doctor [--json] [--copilot-bin <path>] [--skip-copilot] [--hooks]\n  cost [--json] [--session <id>] [--days <n>]\n  launch -- <args...>\n  --madmax [args...]                          (bare-flag launch with permissions bypass; alias of --yolo)\n  team <N:role> "<task>" [--name <name>] [--json]\n  team status <name> [--json]\n  team shutdown <name> [--json]\n  team api claim-task --input '<json>' [--json]\n  team api transition-task-status --input '<json>' [--json]\n  team api send-message --input '<json>' [--json]\n  team api broadcast --input '<json>' [--json]\n  team api mailbox-list --input '<json>' [--json]\n  team api mailbox-mark-delivered --input '<json>' [--json]\n  council "<question>" [--models a,b,c|m:role:weight] [--context <text|@file>] [--rubric <text|@file>] [--synth <model>] [--probe] [--timeout <ms>] [--synth-timeout <ms>] [--min-survivors <n>] [--max-concurrency <n>] [--tmp-dir <dir>] [--json]\n  comms status [--session <name>] [--json]      (is copilot on + online? auto-discovers session)\n  comms send --text "<prompt>" [--force] [--session <name>] [--json]\n  comms recv [--wait] [--lines <n>] [--timeout <ms>] [--session <name>] [--json]\n  comms ask --text "<prompt>" [--force] [--lines <n>] [--timeout <ms>] [--session <name>] [--json]\n  gateway serve [--only <name>[,<name>]]        (run all configured connectors; today: slack)\n  gateway status [--json] [--only <name>[,...]] (per-connector readiness; no sockets opened)\n  gateway doctor [--json] [--only <name>[,...]] (alias for 'gateway status')\n  gateway notify --text "<msg>" [--target slack:C\\|D\\|G\\|U... [:thread_ts]] [--thread-ts <ts>] [--json]\n                                                (one-shot outbound Slack post; falls back to SLACK_HOME_CHANNEL)\n  slack serve                                   (deprecated alias for 'gateway serve --only slack')\n  slack doctor [--json]                         (deprecated alias for 'gateway status --only slack')\n  env init [--force]                            (interactive: write ~/.omp/.env with Slack tokens + optional SLACK_HOME_CHANNEL)\n                                                non-interactive: set OMP_INIT_BOT_TOKEN/OMP_INIT_APP_TOKEN/OMP_INIT_HOME_CHANNEL\n                                                (env vars preferred over --bot-token/--app-token/--home-channel flags)\n  (--session is optional when exactly one omp-<digits> tmux session is running)\n${registeredCommandHelpLines().join("\n")}\n  ralph start "<task>" [--max-iterations <n>] [--session-id <id>] [--json]\n  ralph status [--json]\n  ralph tick [--json]\n  ralph cancel [--json]\n  ultrawork start "<objective>" [--task-count <n>] [--summary <s>] [--json]\n  ultrawork status [--json]\n  ultrawork cancel [--json]\n  ultraqa start "<goal>" [--max-cycles <n>] [--json]\n  ultraqa cycle pass|fail|pending [--json]\n  ultraqa status [--json]\n  ultraqa cancel [--json]\n  schedule add --id <id> --cron "<expr>" --prompt "<text>" [--bin copilot] [--model <m>] [--cwd <dir>] [--timeout <ms>] [--max-runs <n>] [--ttl-hours <h>] [--allow-all-tools] [--notify-target slack:<ID>] [--dry-run] [--json]\n  schedule list [--json]\n  schedule status <id> [--json]\n  schedule run-now <id> [--json]\n  schedule remove <id> [--json]\n  goal set "<objective>" [--json]\n  goal read [--json]\n  memory sync [--json]                          (render goal+directives into copilot-instructions.md)\n  daily-log set-goal "<text>" [--json]\n  daily-log add "<text>" [--json]\n  daily-log read [--days <n>] [--json]\n  daily-log prune [--keep-days <n>] [--json]\n  state write <key> <val> [--ttl <s>] | read|delete|status <key> | list | cleanup [--json]\n  project-memory read [<id>] | index | add-note "<title>" [--body "<text>"] | add-directive "<rule>" [--json]\n  trace timeline [<sessionId>] [--limit <n>] | summary [<sessionId>] | add <sessionId> <event> [<json>] [--json]\n  catalog list [--json]\n  catalog validate [--json]\n  catalog capability <id> [--json]\n  project inspect [--json]\n  skill install <skill-dir> [--root <repo>] [--scope project|user] [--dry-run] [--json]\n  lint:skills [--root <repo>]\n  sync:dry-run [--root <repo>]\n  jira:dry-run [--root <repo>]\n  jira render <plan-file> [--root <repo>] [--json]\n  jira apply <ticket-key-or-plan-file> --comment|--update|--transition|--link [--dry-run] [--json]\n`;
 }
 async function resolveExistingInputPath(value) {
     const { existsSync } = await import("node:fs");
@@ -107,11 +107,20 @@ export async function runCli(argv = process.argv.slice(2)) {
             importMetaUrl: import.meta.url,
             copilotBin: flagValue(argv, "--copilot-bin"),
             skipCopilot: hasFlag(argv, "--skip-copilot"),
+            checkHooks: hasFlag(argv, "--hooks"),
         });
         return json
             ? { ok: report.ok, exitCode: report.ok ? 0 : 1, output: report }
             : { ok: report.ok, exitCode: report.ok ? 0 : 1, message: formatDoctor(report) };
     }
+    if (group === "cost") {
+        const { summarizeCost, formatCostSummary } = await import("./cost/summary.js");
+        const summary = summarizeCost(flagValue(argv, "--root") ?? process.cwd(), {
+            sessionId: flagValue(argv, "--session"),
+            today: hasFlag(argv, "--today"),
+        });
+        return json ? { ok: true, output: summary } : { ok: true, message: formatCostSummary(summary) };
+    }
     if (group === "launch") {
         const dashIndex = argv.indexOf("--");
         const passthrough = dashIndex >= 0 ? argv.slice(dashIndex + 1) : argv.slice(1);