cron-hygiene
cron-hygiene audits scheduled skills weekly to detect architectural inefficiencies, particularly cron jobs running in main session mode that accumulate full conversation history on each invocation. Use this skill to identify and remediate expensive configurations, enforce isolated session modes, and apply output constraints that prevent runaway token costs in recurring automation tasks.
git clone --depth 1 https://github.com/ArchieIndian/openclaw-superpowers /tmp/cron-hygiene && cp -r /tmp/cron-hygiene/skills/openclaw-native/cron-hygiene ~/.claude/skills/cron-hygieneSKILL.md
# cron-hygiene
Cron jobs running in `main` session mode inherit the full conversation history — re-sending thousands of tokens of context on every invocation. A cron running every 5 minutes in main session mode can turn a $10/month setup into $80+ (issue #20092). This skill audits all configured cron skills weekly and enforces hygiene standards.
## Difference from context-budget-guard
`context-budget-guard` monitors live session token usage in real-time. `cron-hygiene` is about the structural problem: cron jobs that are *architecturally wasteful* because they're configured in the wrong session mode.
## Cron Wakeup Behaviour
Runs every Monday at 09:00 (`cron: "0 9 * * 1"`). On each wakeup:
1. Read the list of registered cron skills from OpenClaw config
2. For each skill, check its session mode (`main` vs `isolated`)
3. Estimate cost impact: crons in `main` mode × frequency × estimated context size
4. Flag violations and surface recommendations
## Hygiene rules
| Rule | Check | Severity |
|---|---|---|
| Session isolation | Cron skills should use `isolated` session mode | High |
| Reply conciseness | Cron output should be < 500 tokens | Medium |
| Frequency sanity | Crons running < 10min apart need justification | Medium |
| Dead crons | Cron skills with no state update in 7+ days | Low |
| Overlapping crons | Two skills scheduled at the same time | Low |
## Weekly report format
```
Cron Hygiene Report — 2026-03-16
────────────────────────────────
5 crons audited | 2 violations | Est. monthly waste: $12.40
HIGH: persistent-memory-hygiene — runs in main session mode
Fix: add sessionMode: isolated to skill config
Est. savings: ~$8.20/month
MEDIUM: long-running-task-management — fires every 15min
Output not constrained (last run: 1,240 tokens)
Recommendation: add reply_token_limit: 200 to skill config
```
## Remediation
To fix a main-session cron manually:
```
python3 audit.py --fix-session <skill-name>
```
This writes `sessionMode: isolated` to the skill's OpenClaw config entry.Syncs agent daily memory and MEMORY.md to an Obsidian vault so notes are human-browsable. Use nightly or on demand.
Structured ideation before any implementation. Use when starting any non-trivial task.
Scaffolds and validates new superpowers skills. Use when creating a new skill for this repository.
Executes plans task-by-task with verification. Use when implementing a plan.
Triggers a secondary verification pass for any agent output containing factual claims, numbers, dates, or named entities before the output is acted on
Crawls a new codebase to infer stack, conventions, and key invariants, then generates a PROJECT.md context file for the agent
Handles PR review feedback by fetching comments, grouping issues, fixing one group at a time, and verifying before replies.
Detects skill name shadowing and description-overlap conflicts that cause OpenClaw to trigger the wrong skill or silently ignore one when two skills compete for the same intent.