launch

Name: launch
Author: Rune-kit

80stars21forks

How to install launch?

rune-kit/rune/launch

$curl -o .claude/agents/launch.md https://raw.githubusercontent.com/Rune-kit/rune/HEAD/agents/launch.md

Installs into the current project.

Summary

Deploy + marketing orchestrator. Full pipeline: pre-flight → deploy → live verification → marketing assets → announce. Use when shipping to production.

Files · 1

View on GitHub

agents/launch.md

1	# launch
2
3	## Purpose
4
5	Orchestrate the full deployment and marketing pipeline. Launch coordinates testing, deployment, live site verification, marketing asset creation, and public announcement. One command to go from "code ready" to "product live and marketed."
6
7	<HARD-GATE>
8	- ALL tests must pass before any deploy attempt. Zero exceptions. Block deploy if any of: tests failing, TypeScript errors present, build fails, or sentinel CRITICAL issues detected.
9	</HARD-GATE>
10
11	## Triggers
12
13	- `/rune launch` — manual invocation
14	- Called by `team` when delegating launch tasks
15
16	## Calls (outbound)
17
18	- `test` (L2): pre-deployment full test suite
19	- `audit` (L2): pre-launch health check — full 7-phase quality gate
20	- `deploy` (L2): push to target platform
21	- `incident` (L2): if post-launch health check fails → triage and contain
22	- `retro` (L2): post-launch retrospective — what went well, what didn't
23	- `browser-pilot` (L3): verify live site screenshots and performance
24	- `marketing` (L2): create launch assets (landing copy, social, SEO)
25	- `watchdog` (L3): setup post-deploy monitoring
26	- `video-creator` (L3): create launch/demo video content
27	- L4 extension packs: domain-specific launch patterns when context matches (e.g., @rune/devops for infrastructure, @rune/ecommerce for storefront)
28
29	## Called By (inbound)
30
31	- User: `/rune launch` direct invocation
32	- `team` (L1): when team delegates launch phase
33
34	---
35
36	## Execution
37
38	### Step 0 — Artifact Readiness Check
39
40	Before starting the pipeline, verify that prerequisite artifacts exist. Scan using `Glob` — do NOT hardcode paths, use discovery patterns.
41
42	```
43	REQUIRED ARTIFACTS:
44	Source code: Glob */.{ts,tsx,js,jsx,py,rs,go} — at least 1 match
45	Build config: Glob {package.json,Cargo.toml,pyproject.toml,go.mod} — at least 1 match
46	Tests: Glob */.{test,spec}.* OR */test_.* — at least 1 match
47
48	RECOMMENDED ARTIFACTS (warn if missing, don't block):
49	Design system: Glob .rune/design-system.md — if frontend project
50	Deploy config: Glob {vercel.json,netlify.toml,Dockerfile,fly.toml,.github/workflows/*} — any 1
51	README: Glob README.md
52	Environment: Glob .env.example OR .env.production — warn about secrets if .env found
53
54	BLOCKING CONDITIONS:
55	❌ No source code found → STOP: "Nothing to deploy"
56	❌ No build config found → STOP: "No project config detected — cannot determine build/deploy"
57	❌ No tests found → WARN: "No tests detected — pre-flight will run build-only verification"
58	```
59
60	Report artifact status before proceeding:
61	```
62	## Artifact Check
63	- Source: ✅ [N] files ([language])
64	- Build config: ✅ [file]
65	- Tests: ✅ [N] test files \| ⚠️ No tests found
66	- Deploy config: ✅ [platform] \| ⚠️ Not found (will detect in Phase 2)
67	- Design system: ✅ .rune/design-system.md \| ⚠️ Not found (run /rune design first for UI projects)
68	```
69
70	### Step 1 — Initialize TodoWrite
71
72	```
73	TodoWrite([
74	{ content: "PRE-FLIGHT: Run full test suite and verification", status: "pending", activeForm: "Running pre-flight checks" },
75	{ content: "DEPLOY: Detect platform and push to production", status: "pending", activeForm: "Deploying to production" },
76	{ content: "VERIFY LIVE: Check live URL and setup monitoring", status: "pending", activeForm: "Verifying live deployment" },
77	{ content: "MARKET: Generate landing copy and social assets", status: "pending", activeForm: "Generating marketing assets" },
78	{ content: "ANNOUNCE: Present all marketing assets to user", status: "pending", activeForm: "Preparing announcement" }
79	])
80	```
81
82	---
83
84	### Phase 1 — PRE-FLIGHT
85
86	Mark todo[0] `in_progress`.
87
88	```
89	REQUIRED SUB-SKILL: rune:verification
90	→ Invoke `verification` with scope: "full".
91	→ verification runs: type check, lint, unit tests, integration tests, build.
92	→ Capture: passed count, failed count, coverage %, build output.
93	```
94
95	<HARD-GATE>
96	Block deploy if ANY of:
97	[ ] Tests failing (failed count > 0)
98	[ ] TypeScript errors present
99	[ ] Build fails
100	[ ] sentinel CRITICAL issues detected (invoke rune:sentinel if not already run)
101
102	If any check fails:
103	→ STOP immediately
104	→ Report: "PRE-FLIGHT FAILED — deploy blocked"
105	→ List all failures with file + line references
106	→ Do NOT proceed to Phase 2
107	</HARD-GATE>
108
109	Mark todo[0] `completed` only when ALL checks pass.
110
111	---
112
113	### Phase 2 — DEPLOY
114
115	Mark todo[1] `in_progress`.
116
117	2a. Detect deployment platform.
118
119	```
120	Bash: ls package.json
121	Read: package.json (check "scripts" for deploy, build, start commands)
122
123	Platform detection (in order):

People who liked this also viewed

6 picks

Type

code-reviewerCode review expert for quality analysis, security vulnerabilities, and production reliabilitySubagentsJul 20263.9k
deployerUse for deployment automation, release management, rollouts, and production deployments.SubagentsJul 2026769
infrastructureCloud infrastructure, Kubernetes, orchestration, and infrastructure as code. Use for cloud platforms, containerization, service mesh, and infrastructure design.SubagentsJul 2026769
monitorUse for monitoring setup, alerting configuration, observability, and performance analysis.SubagentsJul 2026769
sysadminUse for system administration, server configuration, security hardening, and infrastructure management.SubagentsJul 2026769
ebpf-kernel-engineerUse this agent when working with eBPF kernel programs, system-level observability, or kernel programming tasks. Examples include: developing or modifying process.bpf.c and sslsniff.bpf.c programs, optSubagentsJul 2026534

launch

80stars21forks

View on GitHub

How to install launch?

rune-kit/rune/launch

$curl -o .claude/agents/launch.md https://raw.githubusercontent.com/Rune-kit/rune/HEAD/agents/launch.md

Installs into the current project.

Summary

Deploy + marketing orchestrator. Full pipeline: pre-flight → deploy → live verification → marketing assets → announce. Use when shipping to production.

Files · 1

View on GitHub

agents/launch.md

1	# launch
2
3	## Purpose
4
5	Orchestrate the full deployment and marketing pipeline. Launch coordinates testing, deployment, live site verification, marketing asset creation, and public announcement. One command to go from "code ready" to "product live and marketed."
6
7	<HARD-GATE>
8	- ALL tests must pass before any deploy attempt. Zero exceptions. Block deploy if any of: tests failing, TypeScript errors present, build fails, or sentinel CRITICAL issues detected.
9	</HARD-GATE>
10
11	## Triggers
12
13	- `/rune launch` — manual invocation
14	- Called by `team` when delegating launch tasks
15
16	## Calls (outbound)
17
18	- `test` (L2): pre-deployment full test suite
19	- `audit` (L2): pre-launch health check — full 7-phase quality gate
20	- `deploy` (L2): push to target platform
21	- `incident` (L2): if post-launch health check fails → triage and contain
22	- `retro` (L2): post-launch retrospective — what went well, what didn't
23	- `browser-pilot` (L3): verify live site screenshots and performance
24	- `marketing` (L2): create launch assets (landing copy, social, SEO)
25	- `watchdog` (L3): setup post-deploy monitoring
26	- `video-creator` (L3): create launch/demo video content
27	- L4 extension packs: domain-specific launch patterns when context matches (e.g., @rune/devops for infrastructure, @rune/ecommerce for storefront)
28
29	## Called By (inbound)
30
31	- User: `/rune launch` direct invocation
32	- `team` (L1): when team delegates launch phase
33
34	---
35
36	## Execution
37
38	### Step 0 — Artifact Readiness Check
39
40	Before starting the pipeline, verify that prerequisite artifacts exist. Scan using `Glob` — do NOT hardcode paths, use discovery patterns.
41
42	```
43	REQUIRED ARTIFACTS:
44	Source code: Glob */.{ts,tsx,js,jsx,py,rs,go} — at least 1 match
45	Build config: Glob {package.json,Cargo.toml,pyproject.toml,go.mod} — at least 1 match
46	Tests: Glob */.{test,spec}.* OR */test_.* — at least 1 match
47
48	RECOMMENDED ARTIFACTS (warn if missing, don't block):
49	Design system: Glob .rune/design-system.md — if frontend project
50	Deploy config: Glob {vercel.json,netlify.toml,Dockerfile,fly.toml,.github/workflows/*} — any 1
51	README: Glob README.md
52	Environment: Glob .env.example OR .env.production — warn about secrets if .env found
53
54	BLOCKING CONDITIONS:
55	❌ No source code found → STOP: "Nothing to deploy"
56	❌ No build config found → STOP: "No project config detected — cannot determine build/deploy"
57	❌ No tests found → WARN: "No tests detected — pre-flight will run build-only verification"
58	```
59
60	Report artifact status before proceeding:
61	```
62	## Artifact Check
63	- Source: ✅ [N] files ([language])
64	- Build config: ✅ [file]
65	- Tests: ✅ [N] test files \| ⚠️ No tests found
66	- Deploy config: ✅ [platform] \| ⚠️ Not found (will detect in Phase 2)
67	- Design system: ✅ .rune/design-system.md \| ⚠️ Not found (run /rune design first for UI projects)
68	```
69
70	### Step 1 — Initialize TodoWrite
71
72	```
73	TodoWrite([
74	{ content: "PRE-FLIGHT: Run full test suite and verification", status: "pending", activeForm: "Running pre-flight checks" },
75	{ content: "DEPLOY: Detect platform and push to production", status: "pending", activeForm: "Deploying to production" },
76	{ content: "VERIFY LIVE: Check live URL and setup monitoring", status: "pending", activeForm: "Verifying live deployment" },
77	{ content: "MARKET: Generate landing copy and social assets", status: "pending", activeForm: "Generating marketing assets" },
78	{ content: "ANNOUNCE: Present all marketing assets to user", status: "pending", activeForm: "Preparing announcement" }
79	])
80	```
81
82	---
83
84	### Phase 1 — PRE-FLIGHT
85
86	Mark todo[0] `in_progress`.
87
88	```
89	REQUIRED SUB-SKILL: rune:verification
90	→ Invoke `verification` with scope: "full".
91	→ verification runs: type check, lint, unit tests, integration tests, build.
92	→ Capture: passed count, failed count, coverage %, build output.
93	```
94
95	<HARD-GATE>
96	Block deploy if ANY of:
97	[ ] Tests failing (failed count > 0)
98	[ ] TypeScript errors present
99	[ ] Build fails
100	[ ] sentinel CRITICAL issues detected (invoke rune:sentinel if not already run)
101
102	If any check fails:
103	→ STOP immediately
104	→ Report: "PRE-FLIGHT FAILED — deploy blocked"
105	→ List all failures with file + line references
106	→ Do NOT proceed to Phase 2
107	</HARD-GATE>
108
109	Mark todo[0] `completed` only when ALL checks pass.
110
111	---
112
113	### Phase 2 — DEPLOY
114
115	Mark todo[1] `in_progress`.
116
117	2a. Detect deployment platform.
118
119	```
120	Bash: ls package.json
121	Read: package.json (check "scripts" for deploy, build, start commands)
122
123	Platform detection (in order):

People who liked this also viewed

6 picks

Type