alive:system-cleanup SKILL.md skillA

alive:system-cleanup from alivecontext/alive is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add alivecontext/alive/alive:system-cleanup@git:20260511.5023f6d

Pins git:20260511.5023f6d in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
alivecontext/alive
Path
plugins/alive/skills/system-cleanup/SKILL.md
Versions recorded
5
Latest version
git:20260511.5023f6d, committed May 11, 2026
First version recorded
Apr 20, 2026
Size
21,248 bytes
Repository stars
131
License
MIT

The world feels messy. Stale tasks, orphan folders, v2 remnants, unsaved sessions — entropy is accumulating and needs to be addressed before it compounds. Scans across all walnuts, then surfaces issues one at a time.

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

# Tidy

System maintenance. Root health first, then one walnut at a time. Surfaces issues with recommended fixes — the human picks.

Not a dashboard (that's world). Not a search (that's find). Not session history (that's alive:session-history). Pure maintenance.

---

## v3 Architecture Reference

Walnut structure is flat under `_kernel/`:

```
walnut-name/
  _kernel/
    key.md
    log.md
    insights.md
    tasks.json
    now.json
    completed.json
  bundle-a/
    context.manifest.yaml
    raw/
  bundle-b/
    context.manifest.yaml
```

There is NO `_kernel/_generated/` subdirectory. There is NO `bundles/` container directory. Bundles sit as direct children of the walnut root alongside `_kernel/`.

Task operations go through `tasks.py`, never by reading/writing task files directly:
- `tasks.py list --walnut {path}` — all active tasks as JSON
- `tasks.py list --walnut {path} --status active` — filter by status
- `tasks.py summary --walnut {path}` — structured summary with counts

Projection rebuilds go through `project.py`:
- `project.py --walnut {path}` — rebuilds `_kernel/now.json`

---

## Three-Phase Flow

```
Phase 1: Root Audit (system-level, 7 checks — parallel subagents)
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add alivecontext/alive/alive:system-cleanup@sha256:738be21d87b414e2

The line at the top of this page pins the label git:20260511.5023f6d, 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.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_gxg4zjbw7yfaf73r.svg)](https://markdownregistry.com/a/art_gxg4zjbw7yfaf73r)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 5 versions of this file, between Apr 20, 2026 and May 11, 2026, about one every 5 days.

versioncommittedcommitsizeaudit
git:20260511.5023f6d latest2026-05-11 5023f6d 21,248 BA view · diff
git:20260422.a18add92026-04-22 a18add9 21,111 BA view · diff
git:20260420.7174cae2026-04-20 7174cae 21,008 BA view · diff
git:20260420.730d8842026-04-20 730d884 20,899 BA view · diff
git:20260420.f565c812026-04-20 f565c81 20,898 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (21248 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

GitHub

alivecontext/alive · 131 stars · license MIT · pushed 2026-10-02 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_gxg4zjbw7yfaf73r
GET https://markdownregistry.com/api/v1/resolve?ref=alivecontext/alive/alive:system-cleanup
GET https://markdownregistry.com/api/v1/blob/738be21d87b414e2288339d0d7a08565a5112f34ac5b7a77506368af2e3c6c39

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.

More from alivecontext/alive

alive-health SKILL.md skill
alivecontext/alive · hermes/cron-templates/alive-health/SKILL.md · Flag walnuts past their rhythm -- health check for the world
v1.0.0 · audit A · 131 stars
alive-inbox SKILL.md skill
alivecontext/alive · hermes/cron-templates/alive-inbox/SKILL.md · Scan 03_Inbox/ for unrouted files, present routing suggestions
v1.0.0 · audit A · 131 stars
alive-mine SKILL.md skill
alivecontext/alive · hermes/cron-templates/alive-mine/SKILL.md · Nightly scan of session transcripts -- extract decisions, tasks, people, insights
v1.0.0 · audit A · 131 stars
alive-morning SKILL.md skill
alivecontext/alive · hermes/cron-templates/alive-morning/SKILL.md · Morning briefing -- read all walnut states, surface priorities, inbox count, stale walnuts, people nudges
v1.0.0 · audit A · 131 stars
alive-people SKILL.md skill
alivecontext/alive · hermes/cron-templates/alive-people/SKILL.md · Weekly -- cross-reference people mentions, nudge stale contacts
v1.0.0 · audit A · 131 stars
alive-project SKILL.md skill
alivecontext/alive · hermes/cron-templates/alive-project/SKILL.md · Regenerate now.json projections for all walnuts (mechanical, no approval needed)
v1.0.0 · audit A · 131 stars
alive-prune SKILL.md skill
alivecontext/alive · hermes/cron-templates/alive-prune/SKILL.md · Weekly -- suggest log entries for chapter synthesis, flag stale insights
v1.0.0 · audit A · 131 stars
alive-stash-router SKILL.md skill
alivecontext/alive · hermes/cron-templates/alive-stash-router/SKILL.md · Present pending stash items grouped by destination walnut for approval
v1.0.0 · audit A · 131 stars
alive-bundle SKILL.md skill
alivecontext/alive · hermes/hermes-skills/alive-bundle/SKILL.md · Create, manage, and graduate bundles -- the unit of focused work within a walnut
v1.0.0 · audit A · 131 stars
alive-capture SKILL.md skill
alivecontext/alive · hermes/hermes-skills/alive-capture/SKILL.md · Capture external content into a walnut bundle -- emails, transcripts, screenshots, documents, research
v1.0.0 · audit A · 131 stars
alive-cleanup SKILL.md skill
alivecontext/alive · hermes/hermes-skills/alive-cleanup/SKILL.md · System maintenance -- stale tasks, orphan folders, unsaved sessions, world health check
v1.0.0 · audit A · 131 stars
alive-create SKILL.md skill
alivecontext/alive · hermes/hermes-skills/alive-create/SKILL.md · Scaffold a new walnut -- venture, experiment, person, life area, project
v1.0.0 · audit A · 131 stars

Every file in alivecontext/alive

Browse by kind, by grade A, or by owner.