@rune-kit/rune 2.8.0 → 2.11.0

package/skills/watchdog/SKILL.md

@@ -1,168 +1,168 @@
----
-name: watchdog
-description: Post-deploy monitoring. Checks if deployed app is healthy — HTTP status, response times, error detection, and smoke test report.
-metadata:
-  author: runedev
-  version: "0.2.0"
-  layer: L3
-  model: sonnet
-  group: monitoring
-  tools: "Read, Bash, Glob, Grep"
-  emit: incident.detected
-  listen: deploy.complete
----
-
-# watchdog
-
-## Purpose
-
-Post-deploy monitoring. Receives a deployed URL and list of expected endpoints, runs health checks, measures response times, detects errors, and returns a structured smoke test report.
-
-## Called By (inbound)
-
-- `deploy` (L2): post-deploy monitoring setup
-- `launch` (L1): monitoring as part of launch pipeline
-- `incident` (L2): current system state check during incident triage
-
-## Calls (outbound)
-
-None — pure L3 utility.
-
-## Executable Instructions
-
-### Step 1: Receive Target
-
-Accept input from calling skill:
-- `base_url` — deployed application URL (e.g. `https://myapp.com`)
-- `endpoints` — list of paths to check (e.g. `["/", "/health", "/api/status"]`)
-
-If no endpoints provided, default to: `["/", "/health", "/ready"]`
-
-### Step 2: Health Check
-
-For each endpoint, run an HTTP status check using `Bash`:
-
-```bash
-curl -s -o /dev/null -w "%{http_code}" https://myapp.com/health
-```
-
-- 2xx → HEALTHY
-- 3xx → REDIRECT (note final destination)
-- 4xx → CLIENT_ERROR (flag as alert)
-- 5xx → SERVER_ERROR (flag as critical alert)
-- Connection refused / timeout → UNREACHABLE (flag as critical)
-
-### Step 3: Response Time
-
-For each endpoint, measure latency using `Bash`:
-
-```bash
-curl -s -o /dev/null -w "%{time_total}" https://myapp.com/health
-```
-
-Thresholds:
-- < 500ms → FAST
-- 500ms–2000ms → ACCEPTABLE
-- > 2000ms → SLOW (flag as alert)
-
-### Step 4: Performance Signal Analysis
-
-After collecting response times from Step 3, analyze for patterns that indicate root causes:
-
-- **Consistently 2x+ slower than baseline** (or > 2000ms with no apparent load): flag with `PERF_WARN — investigate N+1 query or missing DB index`
-- **Endpoint cluster degradation**: if 3+ endpoints share a pattern (all auth endpoints slow, all /api/* slow): flag `PERF_WARN — connection pool saturation likely`
-- **Spike after deploy**: compare with previous watchdog run if available — if an endpoint that was FAST is now SLOW, flag `PERF_REGRESSION — correlate with recent git diff`
-
-If no previous baseline exists, skip spike detection and note `INFO: no baseline — first run`.
-
-Output performance signals into a `perf_signals` list (separate from `alerts`).
-
-### Step 5: Error Detection
-
-Scan responses for problems:
-- 4xx/5xx HTTP codes → log endpoint + status code
-- Response time > 2s → log endpoint + measured time
-- Connection timeout (curl exits non-zero) → UNREACHABLE
-- Empty response body on non-204 endpoints → flag as WARNING
-
-Collect all flagged issues into an `alerts` list.
-
-### Step 6: Report
-
-Output the following report structure:
-
-```
-## Watchdog Report: [base_url]
-
-### Smoke Test Results
-- [endpoint] — [HTTP status] ([response_time]s) — [HEALTHY|REDIRECT|CLIENT_ERROR|SERVER_ERROR|UNREACHABLE]
-
-### Alert Rules Applied
-- Response time > 2s → alert
-- Any 4xx on non-auth endpoint → alert
-- Any 5xx → critical alert
-- Unreachable → critical alert
-
-### Alerts
-- [CRITICAL|WARNING] [endpoint] — [reason]
-
-### Performance Signals
-- [PERF_WARN|PERF_REGRESSION|INFO] [endpoint] — [diagnosis]
-
-### Summary
-- Total endpoints checked: [n]
-- Healthy: [n]
-- Alerts: [n]
-- Perf Signals: [n]
-- Overall status: ALL_HEALTHY | DEGRADED | DOWN
-```
-
-If no alerts and no perf signals: output `Overall status: ALL_HEALTHY`.
-
-## Output Format
-
-```
-## Watchdog Report: [base_url]
-### Smoke Test Results
-- / — 200 (0.231s) — HEALTHY
-- /health — 200 (0.089s) — HEALTHY
-- /api/status — 500 (1.203s) — SERVER_ERROR
-
-### Alerts
-- CRITICAL /api/status — HTTP 500
-
-### Summary
-- Total: 3 | Healthy: 2 | Alerts: 1
-- Overall status: DEGRADED
-```
-
-## Constraints
-
-1. MUST report with specific metrics — not vague "performance seems slow"
-2. MUST include baseline comparison when available
-3. MUST NOT generate false alarms — precision over recall
-4. MUST separate perf signals from error alerts — they are different severity channels
-5. MUST NOT call `perf` skill — watchdog is a detector, not a diagnoser
-
-## Sharp Edges
-
-Known failure modes for this skill. Check these before declaring done.
-
-| Failure Mode | Severity | Mitigation |
-|---|---|---|
-| curl timeout treated as slow (not unreachable) | HIGH | Non-zero curl exit code = UNREACHABLE, not a response time measurement |
-| PERF_REGRESSION reported without baseline | MEDIUM | Only flag regression if a previous run exists — otherwise INFO: first run |
-| All endpoints flagged SLOW because test env is slow | MEDIUM | Note environment context — add `ENV: non-production detected` if URL contains dev/staging/localhost |
-| Perf signal without actionable diagnosis | LOW | Every PERF_WARN must include a hypothesis (N+1, pool saturation, etc.) |
-
-## Done When
-
-- All specified endpoints checked (HTTP status + response time measured)
-- All 4xx/5xx → `alerts` list, all SLOW → `alerts` list
-- Performance patterns analyzed → `perf_signals` list (or INFO: first run)
-- Structured Watchdog Report emitted with Alerts + Performance Signals + Summary
-- Overall status is ALL_HEALTHY, DEGRADED, or DOWN (never ambiguous)
-
-## Cost Profile
-
-~500-1500 tokens input, ~300-800 tokens output. Sonnet for configuration quality.
+---
+name: watchdog
+description: Post-deploy monitoring. Checks if deployed app is healthy — HTTP status, response times, error detection, and smoke test report.
+metadata:
+  author: runedev
+  version: "0.2.0"
+  layer: L3
+  model: sonnet
+  group: monitoring
+  tools: "Read, Bash, Glob, Grep"
+  emit: incident.detected
+  listen: deploy.complete
+---
+
+# watchdog
+
+## Purpose
+
+Post-deploy monitoring. Receives a deployed URL and list of expected endpoints, runs health checks, measures response times, detects errors, and returns a structured smoke test report.
+
+## Called By (inbound)
+
+- `deploy` (L2): post-deploy monitoring setup
+- `launch` (L1): monitoring as part of launch pipeline
+- `incident` (L2): current system state check during incident triage
+
+## Calls (outbound)
+
+None — pure L3 utility.
+
+## Executable Instructions
+
+### Step 1: Receive Target
+
+Accept input from calling skill:
+- `base_url` — deployed application URL (e.g. `https://myapp.com`)
+- `endpoints` — list of paths to check (e.g. `["/", "/health", "/api/status"]`)
+
+If no endpoints provided, default to: `["/", "/health", "/ready"]`
+
+### Step 2: Health Check
+
+For each endpoint, run an HTTP status check using `Bash`:
+
+```bash
+curl -s -o /dev/null -w "%{http_code}" https://myapp.com/health
+```
+
+- 2xx → HEALTHY
+- 3xx → REDIRECT (note final destination)
+- 4xx → CLIENT_ERROR (flag as alert)
+- 5xx → SERVER_ERROR (flag as critical alert)
+- Connection refused / timeout → UNREACHABLE (flag as critical)
+
+### Step 3: Response Time
+
+For each endpoint, measure latency using `Bash`:
+
+```bash
+curl -s -o /dev/null -w "%{time_total}" https://myapp.com/health
+```
+
+Thresholds:
+- < 500ms → FAST
+- 500ms–2000ms → ACCEPTABLE
+- > 2000ms → SLOW (flag as alert)
+
+### Step 4: Performance Signal Analysis
+
+After collecting response times from Step 3, analyze for patterns that indicate root causes:
+
+- **Consistently 2x+ slower than baseline** (or > 2000ms with no apparent load): flag with `PERF_WARN — investigate N+1 query or missing DB index`
+- **Endpoint cluster degradation**: if 3+ endpoints share a pattern (all auth endpoints slow, all /api/* slow): flag `PERF_WARN — connection pool saturation likely`
+- **Spike after deploy**: compare with previous watchdog run if available — if an endpoint that was FAST is now SLOW, flag `PERF_REGRESSION — correlate with recent git diff`
+
+If no previous baseline exists, skip spike detection and note `INFO: no baseline — first run`.
+
+Output performance signals into a `perf_signals` list (separate from `alerts`).
+
+### Step 5: Error Detection
+
+Scan responses for problems:
+- 4xx/5xx HTTP codes → log endpoint + status code
+- Response time > 2s → log endpoint + measured time
+- Connection timeout (curl exits non-zero) → UNREACHABLE
+- Empty response body on non-204 endpoints → flag as WARNING
+
+Collect all flagged issues into an `alerts` list.
+
+### Step 6: Report
+
+Output the following report structure:
+
+```
+## Watchdog Report: [base_url]
+
+### Smoke Test Results
+- [endpoint] — [HTTP status] ([response_time]s) — [HEALTHY|REDIRECT|CLIENT_ERROR|SERVER_ERROR|UNREACHABLE]
+
+### Alert Rules Applied
+- Response time > 2s → alert
+- Any 4xx on non-auth endpoint → alert
+- Any 5xx → critical alert
+- Unreachable → critical alert
+
+### Alerts
+- [CRITICAL|WARNING] [endpoint] — [reason]
+
+### Performance Signals
+- [PERF_WARN|PERF_REGRESSION|INFO] [endpoint] — [diagnosis]
+
+### Summary
+- Total endpoints checked: [n]
+- Healthy: [n]
+- Alerts: [n]
+- Perf Signals: [n]
+- Overall status: ALL_HEALTHY | DEGRADED | DOWN
+```
+
+If no alerts and no perf signals: output `Overall status: ALL_HEALTHY`.
+
+## Output Format
+
+```
+## Watchdog Report: [base_url]
+### Smoke Test Results
+- / — 200 (0.231s) — HEALTHY
+- /health — 200 (0.089s) — HEALTHY
+- /api/status — 500 (1.203s) — SERVER_ERROR
+
+### Alerts
+- CRITICAL /api/status — HTTP 500
+
+### Summary
+- Total: 3 | Healthy: 2 | Alerts: 1
+- Overall status: DEGRADED
+```
+
+## Constraints
+
+1. MUST report with specific metrics — not vague "performance seems slow"
+2. MUST include baseline comparison when available
+3. MUST NOT generate false alarms — precision over recall
+4. MUST separate perf signals from error alerts — they are different severity channels
+5. MUST NOT call `perf` skill — watchdog is a detector, not a diagnoser
+
+## Sharp Edges
+
+Known failure modes for this skill. Check these before declaring done.
+
+| Failure Mode | Severity | Mitigation |
+|---|---|---|
+| curl timeout treated as slow (not unreachable) | HIGH | Non-zero curl exit code = UNREACHABLE, not a response time measurement |
+| PERF_REGRESSION reported without baseline | MEDIUM | Only flag regression if a previous run exists — otherwise INFO: first run |
+| All endpoints flagged SLOW because test env is slow | MEDIUM | Note environment context — add `ENV: non-production detected` if URL contains dev/staging/localhost |
+| Perf signal without actionable diagnosis | LOW | Every PERF_WARN must include a hypothesis (N+1, pool saturation, etc.) |
+
+## Done When
+
+- All specified endpoints checked (HTTP status + response time measured)
+- All 4xx/5xx → `alerts` list, all SLOW → `alerts` list
+- Performance patterns analyzed → `perf_signals` list (or INFO: first run)
+- Structured Watchdog Report emitted with Alerts + Performance Signals + Summary
+- Overall status is ALL_HEALTHY, DEGRADED, or DOWN (never ambiguous)
+
+## Cost Profile
+
+~500-1500 tokens input, ~300-800 tokens output. Sonnet for configuration quality.

package/skills/worktree/SKILL.md

@@ -1,140 +1,140 @@
----
-name: worktree
-description: "Git worktree lifecycle management. Creates isolated workspaces for parallel development, manages branches, handles cleanup. Called by team and cook for parallel isolation."
-user-invocable: false
-metadata:
-  author: runedev
-  version: "1.1.0"
-  layer: L3
-  model: haiku
-  group: utility
-  tools: "Read, Bash, Glob, Grep"
----
-
-# worktree
-
-## Purpose
-
-Reusable git worktree lifecycle management. Creates isolated workspaces for parallel agent development, manages branch naming, handles cleanup after merge or abort. Extracted from `team` to be usable by any skill that needs workspace isolation.
-
-## Triggers
-
-- Called by `team` (L1) for parallel stream isolation
-- Called by `cook` (L1) when user explicitly requests worktree isolation
-- `/rune worktree create <name>` — manual creation
-- `/rune worktree cleanup` — manual cleanup of stale worktrees
-
-## Calls (outbound)
-
-None — pure git operations via Bash.
-
-## Called By (inbound)
-
-- `team` (L1): Phase 2 ASSIGN — create worktrees for parallel streams
-- `cook` (L1): optional isolation for complex features
-- User: direct invocation for manual worktree management
-
-## Operations
-
-### Create Worktree
-
-```
-Input: { name: string, base_branch?: string }
-Default base: current HEAD
-
-Steps:
-1. Bash: git worktree add .claude/worktrees/<name> -b rune/<name> [base_branch]
-2. Verify: Bash: git worktree list | grep <name>
-3. Return: { path: ".claude/worktrees/<name>", branch: "rune/<name>" }
-
-Naming convention:
-  - Branch: rune/<name> (e.g., rune/stream-a, rune/auth-feature)
-  - Path: .claude/worktrees/<name>
-  - Max 3 active worktrees (enforced)
-```
-
-### List Worktrees
-
-```
-Bash: git worktree list
-→ Parse output into: [{ path, branch, commit }]
-→ Filter: only rune/* branches (skip main worktree)
-```
-
-### Cleanup Worktree
-
-```
-Input: { name: string, force?: boolean }
-
-Steps:
-1. Check if branch is merged: Bash: git branch --merged main | grep rune/<name>
-2. If merged OR force:
-   Bash: git worktree remove .claude/worktrees/<name> --force
-   Bash: git branch -d rune/<name>  (or -D if force)
-3. If NOT merged AND NOT force:
-   WARN: "Branch rune/<name> has unmerged changes. Use force=true to remove."
-```
-
-### Cleanup All Stale
-
-```
-Bash: git worktree list --porcelain
-→ For each rune/* worktree:
-  → Check if branch exists: git branch --list rune/<name>
-  → If branch deleted: git worktree prune
-  → If branch merged: cleanup (see above)
-→ Report: removed [N] stale worktrees
-```
-
-## Safety Rules
-
-```
-1. NEVER delete a worktree with uncommitted changes without user confirmation
-2. NEVER force-delete an unmerged branch without user confirmation
-3. MAX 3 active rune/* worktrees — refuse creation if limit reached
-4. ALWAYS use .claude/worktrees/ directory — not project root
-5. ALWAYS prefix branches with rune/ — easy identification and cleanup
-```
-
-## Output Format
-
-```
-## Worktree Report
-- **Action**: create | cleanup | list
-- **Worktrees**: [count active]
-
-### Active Worktrees
-| Name | Branch | Path | Status |
-|------|--------|------|--------|
-| stream-a | rune/stream-a | .claude/worktrees/stream-a | active |
-| stream-b | rune/stream-b | .claude/worktrees/stream-b | merged |
-```
-
-## Constraints
-
-1. MUST use .claude/worktrees/ directory for all worktrees
-2. MUST prefix branches with rune/ namespace
-3. MUST NOT exceed 3 active worktrees
-4. MUST check for uncommitted changes before cleanup
-5. MUST NOT force-delete unmerged branches without explicit user confirmation
-
-## Sharp Edges
-
-| Failure Mode | Severity | Mitigation |
-|---|---|---|
-| Worktree left behind after failed merge | MEDIUM | Cleanup All Stale operation + pre-team-merge tag for recovery |
-| Branch name collision with existing branch | LOW | Check branch existence before creation, append timestamp if collision |
-| Worktree path on Windows with long path | MEDIUM | Use short names, keep under .claude/worktrees/ to minimize path length |
-| Deleting worktree with uncommitted agent work | HIGH | Safety Rule 1: always check for uncommitted changes first |
-
-## Done When
-
-- Worktree created/listed/cleaned up as requested
-- Branch naming follows rune/ convention
-- Active worktree count ≤ 3
-- No stale worktrees left behind
-- Worktree Report emitted
-
-## Cost Profile
-
-~200-500 tokens. Haiku + Bash commands. Fast and cheap.
+---
+name: worktree
+description: "Git worktree lifecycle management. Creates isolated workspaces for parallel development, manages branches, handles cleanup. Called by team and cook for parallel isolation."
+user-invocable: false
+metadata:
+  author: runedev
+  version: "1.1.0"
+  layer: L3
+  model: haiku
+  group: utility
+  tools: "Read, Bash, Glob, Grep"
+---
+
+# worktree
+
+## Purpose
+
+Reusable git worktree lifecycle management. Creates isolated workspaces for parallel agent development, manages branch naming, handles cleanup after merge or abort. Extracted from `team` to be usable by any skill that needs workspace isolation.
+
+## Triggers
+
+- Called by `team` (L1) for parallel stream isolation
+- Called by `cook` (L1) when user explicitly requests worktree isolation
+- `/rune worktree create <name>` — manual creation
+- `/rune worktree cleanup` — manual cleanup of stale worktrees
+
+## Calls (outbound)
+
+None — pure git operations via Bash.
+
+## Called By (inbound)
+
+- `team` (L1): Phase 2 ASSIGN — create worktrees for parallel streams
+- `cook` (L1): optional isolation for complex features
+- User: direct invocation for manual worktree management
+
+## Operations
+
+### Create Worktree
+
+```
+Input: { name: string, base_branch?: string }
+Default base: current HEAD
+
+Steps:
+1. Bash: git worktree add .claude/worktrees/<name> -b rune/<name> [base_branch]
+2. Verify: Bash: git worktree list | grep <name>
+3. Return: { path: ".claude/worktrees/<name>", branch: "rune/<name>" }
+
+Naming convention:
+  - Branch: rune/<name> (e.g., rune/stream-a, rune/auth-feature)
+  - Path: .claude/worktrees/<name>
+  - Max 3 active worktrees (enforced)
+```
+
+### List Worktrees
+
+```
+Bash: git worktree list
+→ Parse output into: [{ path, branch, commit }]
+→ Filter: only rune/* branches (skip main worktree)
+```
+
+### Cleanup Worktree
+
+```
+Input: { name: string, force?: boolean }
+
+Steps:
+1. Check if branch is merged: Bash: git branch --merged main | grep rune/<name>
+2. If merged OR force:
+   Bash: git worktree remove .claude/worktrees/<name> --force
+   Bash: git branch -d rune/<name>  (or -D if force)
+3. If NOT merged AND NOT force:
+   WARN: "Branch rune/<name> has unmerged changes. Use force=true to remove."
+```
+
+### Cleanup All Stale
+
+```
+Bash: git worktree list --porcelain
+→ For each rune/* worktree:
+  → Check if branch exists: git branch --list rune/<name>
+  → If branch deleted: git worktree prune
+  → If branch merged: cleanup (see above)
+→ Report: removed [N] stale worktrees
+```
+
+## Safety Rules
+
+```
+1. NEVER delete a worktree with uncommitted changes without user confirmation
+2. NEVER force-delete an unmerged branch without user confirmation
+3. MAX 3 active rune/* worktrees — refuse creation if limit reached
+4. ALWAYS use .claude/worktrees/ directory — not project root
+5. ALWAYS prefix branches with rune/ — easy identification and cleanup
+```
+
+## Output Format
+
+```
+## Worktree Report
+- **Action**: create | cleanup | list
+- **Worktrees**: [count active]
+
+### Active Worktrees
+| Name | Branch | Path | Status |
+|------|--------|------|--------|
+| stream-a | rune/stream-a | .claude/worktrees/stream-a | active |
+| stream-b | rune/stream-b | .claude/worktrees/stream-b | merged |
+```
+
+## Constraints
+
+1. MUST use .claude/worktrees/ directory for all worktrees
+2. MUST prefix branches with rune/ namespace
+3. MUST NOT exceed 3 active worktrees
+4. MUST check for uncommitted changes before cleanup
+5. MUST NOT force-delete unmerged branches without explicit user confirmation
+
+## Sharp Edges
+
+| Failure Mode | Severity | Mitigation |
+|---|---|---|
+| Worktree left behind after failed merge | MEDIUM | Cleanup All Stale operation + pre-team-merge tag for recovery |
+| Branch name collision with existing branch | LOW | Check branch existence before creation, append timestamp if collision |
+| Worktree path on Windows with long path | MEDIUM | Use short names, keep under .claude/worktrees/ to minimize path length |
+| Deleting worktree with uncommitted agent work | HIGH | Safety Rule 1: always check for uncommitted changes first |
+
+## Done When
+
+- Worktree created/listed/cleaned up as requested
+- Branch naming follows rune/ convention
+- Active worktree count ≤ 3
+- No stale worktrees left behind
+- Worktree Report emitted
+
+## Cost Profile
+
+~200-500 tokens. Haiku + Bash commands. Fast and cheap.