new-routine SKILL.md skillA
new-routine from kahl-d/jaja is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add kahl-d/jaja/new-routine@git:20261023.9f9eaf2Pins git:20261023.9f9eaf2 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- kahl-d/jaja
- Path
.agents/skills/new-routine/SKILL.md- Versions recorded
- 1
- Latest version
- git:20261023.9f9eaf2, committed Oct 23, 2026
- Size
- 1,695 bytes
- Repository stars
- 6
- License
- MIT
Use when something must happen on a schedule (cloud, GitHub Actions or the desktop app) or the owner asks to automate a recurring job. Interview, routine spec from template, receipt folder, budget line, watchdog wiring, lint, dry run.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# New routine Today is !`date +%F`. Request: `$ARGUMENTS` ## Procedure 1. **Interview**: what must be true after each run? Must it run while the Mac sleeps (cloud), is it deterministic with no connectors (actions), or does it need local files or Apple apps (desktop)? Which skill, role or script does the work? Which connectors, truly? What is the "needs you" sentinel? Owner and budget? 2. **Classify** `runs_on` and `engine`; check `routines/` for an existing routine that already covers it. 3. **Scaffold** `routines/<name>.yaml` from `templates/routine.yaml` with every key; `enabled: false` until the dry run passes; `last_reviewed` = today. Never give an unattended routine a send-capable connector. 4. **Wire**: create the runtime's `logs/runs/<name>/` receipt folder; add the budget line to the budgets policy; the watchdog reads the spec on the next sweep. Installation of the live copy (cloud routine, desktop task or Actions workflow) is manual until an installer exists; record the install command in the spec's comment. 5. **Lint**: `python3 scripts/kernel/lint.py`. 6. **Dry run**: execute the action once by hand and write the first receipt …
Read the whole file at its exact version.
How to install
mdr add kahl-d/jaja/new-routine@sha256:4168d6e66b7c31abThe line at the top of this page pins the label git:20261023.9f9eaf2, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_cg643kahdxefgau5)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Oct 23, 2026.
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (1695 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
kahl-d/jaja · 6 stars · license MIT · pushed 2026-10-23 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_cg643kahdxefgau5 GET https://markdownregistry.com/api/v1/resolve?ref=kahl-d/jaja/new-routine GET https://markdownregistry.com/api/v1/blob/4168d6e66b7c31ab0921988d9436e7f902a775dbcd22608b8c43634fe4cb5493
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.