Routine Contract
The operating contract for any scheduled or unattended agent session — a cron job, a Routine, a CI-triggered agent, a nightly sweep. Use when writing, reviewing, debugging or scheduling automation that runs without a human present, and whenever a scheduled job reports success but you cannot find what it produced. Defines preflight, why unattended sessions must not call orchestration tools that require user opt-in, the three-bullet digest that makes output durable, and why a run that persists nothing must exit non-zero rather than report green.
Install
/plugin marketplace add frankxai/claude-skills-libraryThe repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.
npx skills add frankxai/claude-skills-library --skill routine-contractgit clone --depth 1 https://github.com/frankxai/claude-skills-library.git /tmp/claude-skills-library
mkdir -p ~/.claude/skills
cp -r /tmp/claude-skills-library/packs/routine-contract/skills/routine-contract ~/.claude/skills/routine-contractPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Routine contract An unattended agent session fails differently from an interactive one. Nobody reads its transcript, so a plausible-sounding report is indistinguishable from work. This is the contract that closes that gap. ## The failure this prevents On 2026-09-06 an audit of a production fleet found **all seven scheduled routines reporting `SUCCEEDED` while committing nothing** — for weeks. Not degraded: zero durable output. The receipts directory one routine claimed to write had never existed. Another had fired every Friday since a repair and produced no file. No routine had ever pushed a commit. Two faults, both structural: 1. **The work sat behind an orchestration tool that requires explicit user opt-in.** A cron prompt is not a user asking, so the call was declined, the agent wrote a reasonable-looking summary, and the turn ended cleanly. 2. **The prompts ended in "report your findings"** — into a run-history page that is discarded with the container. Nothing ever asserted the output existed, so status tracked narration rather than work. **`SUCCEEDED` means the turn ended without throwing.** It has never meant the job was done. Run durations were the tell: 76 seconds for a three-domain research scan, 65 for a thirteen-model benchmark. Nothing of that shape finishes that fast. ## The four rules ### 1. Preflight before work, not after First command, before any scanning, drafting or model calls:
Details
- Skill name
routine-contract- Repository
- frankxai/claude-skills-library
- Path
packs/routine-contract/skills/routine-contract/SKILL.md- License
- MIT
- Repo updated
- 18 November 2026
FAQ
What does the Routine Contract skill do?
The operating contract for any scheduled or unattended agent session — a cron job, a Routine, a CI-triggered agent, a nightly sweep. Use when writing, reviewing, debugging or scheduling automation that runs without a human present, and whenever a scheduled job reports success but you cannot find what it produced. Defines preflight, why unattended sessions must not call orchestration tools that require user opt-in, the three-bullet digest that makes output durable, and why a run that persists nothing must exit non-zero rather than report green.
How do I install the Routine Contract skill?
Claude Code plugin: /plugin marketplace add frankxai/claude-skills-library. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Routine Contract popular?
It lives in frankxai/claude-skills-library, which has 48 GitHub stars and 6 forks.
Related skills
Acos Meta
48frankxai/claude-skills-library
ACOS self-description and configuration skill. Documents how ACOS works, how to extend it, how to add new skills/commands/agents, and how to debug the hook system. Use when building new ACOS capabilities, understanding the system architecture, or onboarding to ACOS for the first time.
Acos Visual Gen
48frankxai/claude-skills-library
Generate research-grounded visuals using the InfoGenius pipeline. Use when creating infographics, diagrams, educational visuals, or any image that benefits from factual accuracy. Supports 8 visual styles (3D, technical, minimalist, photorealistic, futuristic, vintage, cartoon, standard) and 4 audience levels.
Agent Harness Construction
48frankxai/claude-skills-library
Shape an agent's tools, observations, and recovery without adding a second coordinator. Use when defining a tool, a skill, a hook, or a worktree lane.
Assess Form
45pjt222/agent-almanac
Evaluate a system's current structural form, identify transformation pressure, and classify transformation readiness. Covers structural inventory, pressure mapping, rigidity assessment, change capacity estimation, and readiness classification for architectural metamorphosis. Use before any significant architectural change to understand the starting point, when a system feels stuck without clear reasons, when external pressure from growth or tech debt is mounting, or as periodic health checks for long-lived systems.
Product Management Expert
48frankxai/claude-skills-library
Product management expertise for strategy, discovery, prioritization, roadmaps, PRDs, metrics, and stakeholder communication. Use when defining what to build, why, and how to measure success.
Audit Decisions
41wolverin0/claude-skills
Standardize remediation decisions, baseline-policy entries, and legal-review banners for accepted, deferred, or policy-blocked audit findings.
Browse the most popular Claude skills, all marketing, sales & business skills, or write your own with the skills generator.