run-without-you

alirezarezvani/claude-skills · agent-launcher/skills/run-without-you/SKILL.md

Phase 4 of building a Claude Managed Agent — make it run without you. Turn a graded agent into a recurring scheduled deployment (POSIX-cron), an event-driven curl trigger, or confirmed on-demand use, then finalize the versioned roadmap. Use when the user says "run it every morning", "put it on a schedule", "nightly", "weekly", "automate this", "make it recurring", or when the orchestrator routes phase=run-without-you. deployment_builder.py builds the POST /v1/deployments payload (initial_events must include user.message; optionally nests a user.define_outcome so each firing self-grades); cron_validator.py validates the 5-field cron + IANA timezone and prints the wall-clock DST note; next_directions_writer.py writes NEXT-DIRECTIONS.md. No tool makes API calls — the deployment is created via BYOK curl. Distinct from grade-iterate (the in-session loop) and wrap-up (closeout).

Software EngineeringMIT★ 25441⑂ 3598commit 19392f7

Install skillView source on GitHub

What this skill does

Phase 4 — Run Without You (the recurring loop)

A scheduled deployment fires a fresh session on a cron cadence — the agent runs without you. Each firing can carry its own outcome, nesting the bounded grade→iterate loop inside every recurring run.

See ../../references/loops-and-workflows.md.

Choose the trigger

| Answer | Shape | Tool | |---|---|---| | "every morning / weekly / nightly" | recurring cron deployment | deployment_builder.py + cron_validator.py | | "when X happens" | event-driven curl (documented, not scheduled) | deployment_builder.py (message only) | | "only when I ask" | on-demand (no deployment) | none — just re-send a user.message |

Workflow (recurring)

Validate the schedule.
```
python3 scripts/cron_validator.py --cron "0 9 * * *" --timezone Europe/Berlin
```
Invalid cron/timezone → exit 1. Read the DST note: wall-clock semantics mean spring-forward times are skipped and fall-back times fire twice — avoid 02:00–03:00 in DST zones if exactly-once matters.
Build the deployment payload.
```
python3 scripts/deployment_builder.py \
  --sheet ./my-agent/build-sheet.json --agent-id agent_123 --env-id env_456 \
  --nest-outcome --out ./my-agent/payloads/deployment.json
```
--nest-outcome includes the rubric so each firing self-grades. The tool prints the BYOK curl to create it and to test it once with the manual run endpoint before trusting the schedule.
Test before you trust. Fire one manual run, read the verdict, only then leave the cron in place. Pin the agent version in the deployment once it passes.

Finalize the roadmap.

python3 scripts/next_directions_writer.py \
  --sheet ./my-agent/build-sheet.json --loop-shape cron-loop --last-verdict satisfied --out-dir ./my-agent

Advance + hand to wrap-up. goal_state.py set --phase wrap-up, then invoke the wrap-up skill.

Hard rules

Test with a manual run first. Never commit a schedule you haven't fired once.
Safety rails on by default. always_ask MCP, limited networking where you can, read_only untrusted memory, max_iterations per firing, workspace spend limit. There is no spend cap inside CMA.
DST is wall-clock. Surface the note; pick safe times.
≤1,000 deployments/org.

Forcing-question library (recommend + cite)

"Cadence, event, or on-request?" Recommend: on-request v0 → cadence once graded. Cite: loops-and-workflows.md.
"Should each firing self-grade?" Recommend: yes — nest the outcome. Cite: loops-and-workflows.md (nesting rule).
"Which timezone, and is the time DST-safe?" Recommend: avoid 02:00–03:00 in DST zones. Cite: cma-primitives.md (wall-clock DST).
"Did you fire one manual run first?" Recommend: always. Cite: this SKILL.

Tools

scripts/deployment_builder.py — POST /v1/deployments payload (+ test-run curl).
scripts/cron_validator.py — 5-field cron + IANA tz + DST note.
scripts/next_directions_writer.py — write/refresh NEXT-DIRECTIONS.md.

Installation

Copy a source-pinned command for your client. You run it yourself.

Destination: .claude/skills/run-without-you · pinned to the source commit

# Run from your project root
git clone https://github.com/alirezarezvani/claude-skills.git .skillboard-tmp
git -C .skillboard-tmp checkout 19392f7a08264ed00486a251f5b2098321771f94
mkdir -p ".claude/skills"
cp -r ".skillboard-tmp/agent-launcher/skills/run-without-you" ".claude/skills/"
rm -rf .skillboard-tmp

Review the source before running. This copies files into your project; it is not a one-click install and does not verify runtime safety.

New here? Step-by-step setup – from installing the agent to using the skill

Operating systemAgentI already use Claude Code

1
Install Git
Install Git with your package manager (Debian/Ubuntu shown; use dnf/pacman on others). Official download.
```
sudo apt update && sudo apt install -y git
```
2
Install Claude Code
Requires Node.js 18+. Install the CLI globally: Official docs. (command-line tool)
```
npm install -g @anthropic-ai/claude-code
```

Get the skill, pinned to its exact version

Open a terminal and run these steps (they clone the source, check out the exact commit, and copy the skill into place):

# Run from your project root
git clone https://github.com/alirezarezvani/claude-skills.git .skillboard-tmp
git -C .skillboard-tmp checkout 19392f7a08264ed00486a251f5b2098321771f94
mkdir -p ".claude/skills"
cp -r ".skillboard-tmp/agent-launcher/skills/run-without-you" ".claude/skills/"
rm -rf .skillboard-tmp

Destination: .claude/skills/run-without-you

4
Use it in Claude Code
Open Claude Code in your project. It reads skills from the folder above, so run-without-you is now available. Always review the source before using it – static checks cannot prove runtime safety.

Security & Audits

Scanner static-checks@0.1.0 · commit 19392f7a0826. Static checks cannot prove runtime safety – review the source and the exact diff before installing. How checks work.

mediumNetwork fetch
Fetches remote content at runtime, which can change after review.
Evidence: curl· fingerprint 427e4b79b1f0fc90
lowPath traversal reference
References parent-directory traversal, which can escape a target directory.
Evidence: ../· fingerprint fa08499e14d0113b

run-without-you

alirezarezvani/claude-skills · agent-launcher/skills/run-without-you/SKILL.md

Software EngineeringMIT★ 25441⑂ 3598commit 19392f7

Install skillView source on GitHub

What this skill does

Phase 4 — Run Without You (the recurring loop)

See ../../references/loops-and-workflows.md.

Choose the trigger

Workflow (recurring)

Validate the schedule.
```
python3 scripts/cron_validator.py --cron "0 9 * * *" --timezone Europe/Berlin
```
Invalid cron/timezone → exit 1. Read the DST note: wall-clock semantics mean spring-forward times are skipped and fall-back times fire twice — avoid 02:00–03:00 in DST zones if exactly-once matters.
Build the deployment payload.
```
python3 scripts/deployment_builder.py \
  --sheet ./my-agent/build-sheet.json --agent-id agent_123 --env-id env_456 \
  --nest-outcome --out ./my-agent/payloads/deployment.json
```
--nest-outcome includes the rubric so each firing self-grades. The tool prints the BYOK curl to create it and to test it once with the manual run endpoint before trusting the schedule.
Test before you trust. Fire one manual run, read the verdict, only then leave the cron in place. Pin the agent version in the deployment once it passes.

Finalize the roadmap.

python3 scripts/next_directions_writer.py \
  --sheet ./my-agent/build-sheet.json --loop-shape cron-loop --last-verdict satisfied --out-dir ./my-agent

Advance + hand to wrap-up. goal_state.py set --phase wrap-up, then invoke the wrap-up skill.

Hard rules

Test with a manual run first. Never commit a schedule you haven't fired once.
Safety rails on by default. always_ask MCP, limited networking where you can, read_only untrusted memory, max_iterations per firing, workspace spend limit. There is no spend cap inside CMA.
DST is wall-clock. Surface the note; pick safe times.
≤1,000 deployments/org.

Forcing-question library (recommend + cite)

"Cadence, event, or on-request?" Recommend: on-request v0 → cadence once graded. Cite: loops-and-workflows.md.
"Should each firing self-grade?" Recommend: yes — nest the outcome. Cite: loops-and-workflows.md (nesting rule).
"Which timezone, and is the time DST-safe?" Recommend: avoid 02:00–03:00 in DST zones. Cite: cma-primitives.md (wall-clock DST).
"Did you fire one manual run first?" Recommend: always. Cite: this SKILL.

Tools

scripts/deployment_builder.py — POST /v1/deployments payload (+ test-run curl).
scripts/cron_validator.py — 5-field cron + IANA tz + DST note.
scripts/next_directions_writer.py — write/refresh NEXT-DIRECTIONS.md.

Installation

Copy a source-pinned command for your client. You run it yourself.

Destination: .claude/skills/run-without-you · pinned to the source commit

# Run from your project root
git clone https://github.com/alirezarezvani/claude-skills.git .skillboard-tmp
git -C .skillboard-tmp checkout 19392f7a08264ed00486a251f5b2098321771f94
mkdir -p ".claude/skills"
cp -r ".skillboard-tmp/agent-launcher/skills/run-without-you" ".claude/skills/"
rm -rf .skillboard-tmp

Review the source before running. This copies files into your project; it is not a one-click install and does not verify runtime safety.

New here? Step-by-step setup – from installing the agent to using the skill

Operating systemAgentI already use Claude Code

1
Install Git
Install Git with your package manager (Debian/Ubuntu shown; use dnf/pacman on others). Official download.
```
sudo apt update && sudo apt install -y git
```
2
Install Claude Code
Requires Node.js 18+. Install the CLI globally: Official docs. (command-line tool)
```
npm install -g @anthropic-ai/claude-code
```

Get the skill, pinned to its exact version

Open a terminal and run these steps (they clone the source, check out the exact commit, and copy the skill into place):

# Run from your project root
git clone https://github.com/alirezarezvani/claude-skills.git .skillboard-tmp
git -C .skillboard-tmp checkout 19392f7a08264ed00486a251f5b2098321771f94
mkdir -p ".claude/skills"
cp -r ".skillboard-tmp/agent-launcher/skills/run-without-you" ".claude/skills/"
rm -rf .skillboard-tmp

Destination: .claude/skills/run-without-you

4
Use it in Claude Code
Open Claude Code in your project. It reads skills from the folder above, so run-without-you is now available. Always review the source before using it – static checks cannot prove runtime safety.

Security & Audits

Scanner static-checks@0.1.0 · commit 19392f7a0826. Static checks cannot prove runtime safety – review the source and the exact diff before installing. How checks work.

mediumNetwork fetch
Fetches remote content at runtime, which can change after review.
Evidence: curl· fingerprint 427e4b79b1f0fc90
lowPath traversal reference
References parent-directory traversal, which can escape a target directory.
Evidence: ../· fingerprint fa08499e14d0113b

run-without-you

What this skill does

Phase 4 — Run Without You (the recurring loop)

Choose the trigger

Workflow (recurring)

Hard rules

Forcing-question library (recommend + cite)

Tools

Installation

Install Git

Install Claude Code

Get the skill, pinned to its exact version

Use it in Claude Code

Security & Audits

run-without-you

What this skill does

Phase 4 — Run Without You (the recurring loop)

Choose the trigger

Workflow (recurring)

Hard rules

Forcing-question library (recommend + cite)

Tools

Installation

Install Git

Install Claude Code

Get the skill, pinned to its exact version

Use it in Claude Code

Security & Audits