levara-run-long-task SKILL.md skillA

levara-run-long-task from stek0v/levara is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add stek0v/levara/levara-run-long-task@git:20261008.9a87687

Pins git:20261008.9a87687 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
stek0v/levara
Path
.agents/skills/levara-run-long-task/SKILL.md
Versions recorded
2
Latest version
git:20261008.9a87687, committed Oct 8, 2026
First version recorded
Aug 5, 2026
Size
5,078 bytes
Repository stars
10
License
MIT

Run or resume long-horizon work through Levara Task Runtime with measurable Definition of Done, atomic step leases, checkpoints, receipts, blockers, and durable-memory promotion. Use for multi-step coding, research, data, monitoring, migration, or scheduled work that must survive compaction or continue across agents. Do not use for one-shot questions or tasks without a verifiable outcome.

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

# Levara long task

Use Levara as the operational source of truth. Treat chat history and generated Markdown as views, not task state.

## Select the mode

- `start`: create a Task and plan its first verifiable steps.
- `resume`: bootstrap an existing `task_id` and continue its next eligible step.
- `monitor`: inspect an existing Task; make no changes when no new action is possible.
- `recover`: bootstrap after compaction, restart, expired lease, or agent handoff.
- `finish`: validate, request an independent audit when required, then complete.

## Initialize

1. Select the project collection. On legacy `/mcp`, call `set_context` in the same session; latest `/mcp/2026-07-28` hides and rejects it, so pass collection explicitly on every collection-aware call.
2. Call `wake_up(collection="<project>", max_tokens=300)`. Ignore graph entities unless `scope_status=exact`.
3. For `start`, call `task_open` with a non-empty collection, room, objective, authority, risk level, idempotency key, and structured Definition of Done.
4. For other modes, require a stable `task_id` and call `task_bootstrap`.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add stek0v/levara/levara-run-long-task@sha256:a9206a165051cab7

The line at the top of this page pins the label git:20261008.9a87687, 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_a6utk3m4kuzpqczu.svg)](https://markdownregistry.com/a/art_a6utk3m4kuzpqczu)

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

Versions

The registry has recorded 2 versions of this file, between Aug 5, 2026 and Oct 8, 2026, about one every 64 days.

versioncommittedcommitsizeaudit
git:20261008.9a87687 latest2026-10-08 9a87687 5,078 BA view · diff
git:20260805.18451882026-08-05 1845188 3,948 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 (5078 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

stek0v/levara · 10 stars · license MIT · pushed 2026-10-21 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_a6utk3m4kuzpqczu
GET https://markdownregistry.com/api/v1/resolve?ref=stek0v/levara/levara-run-long-task
GET https://markdownregistry.com/api/v1/blob/a9206a165051cab774317faa2502ab9a4b79a7955d30fdff2acc90015acf711e

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 stek0v/levara

levara-audit-task SKILL.md skill
stek0v/levara · .agents/skills/levara-audit-task/SKILL.md · Independently audit a Levara long-horizon Task against its original objective, authority, Definition of Done, steps…
git:20260805.1845188 · audit A · 10 stars
levara-memory-workflow SKILL.md skill
stek0v/levara · .agents/skills/levara-memory-workflow/SKILL.md · Automatically restore and curate durable project context through a Levara MCP server. Use implicitly for substantial…
git:20261008.9a87687 · audit A · 10 stars
openspec-apply-change SKILL.md skill
stek0v/levara · .agents/skills/openspec-apply-change/SKILL.md · Implement tasks from an OpenSpec change. Use when the user wants to start implementing, continue implementation, or…
v1.0 · audit A · 10 stars
openspec-archive-change SKILL.md skill
stek0v/levara · .agents/skills/openspec-archive-change/SKILL.md · Archive a completed OpenSpec change in the experimental workflow. Use when the user wants to finalize and archive a…
v1.0 · audit A · 10 stars
openspec-explore SKILL.md skill
stek0v/levara · .agents/skills/openspec-explore/SKILL.md · Enter OpenSpec explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying…
v1.0 · audit A · 10 stars
openspec-propose SKILL.md skill
stek0v/levara · .agents/skills/openspec-propose/SKILL.md · Propose a new OpenSpec change with all artifacts generated in one step. Use when the user wants to quickly describe…
v1.0 · audit A · 10 stars
openspec-sync-specs SKILL.md skill
stek0v/levara · .agents/skills/openspec-sync-specs/SKILL.md · Sync delta specs from an OpenSpec change to main specs. Use when the user wants to update main specs with changes from…
v1.0 · audit A · 10 stars
openspec-update-change SKILL.md skill
stek0v/levara · .agents/skills/openspec-update-change/SKILL.md · Update an OpenSpec change by revising its existing planning artifacts and keeping them coherent with one another. Use…
v1.0 · audit A · 10 stars
AGENTS.md AGENTS.md file
stek0v/levara · AGENTS.md
git:20261008.9a87687 · audit B · 10 stars
CLAUDE.md CLAUDE.md file
stek0v/levara · CLAUDE.md
git:20260905.3de3ac0 · audit A · 10 stars
AGENTS.md@webui AGENTS.md file
stek0v/levara · webui/AGENTS.md
git:20261008.9a87687 · audit A · 10 stars
CLAUDE.md@webui CLAUDE.md file
stek0v/levara · webui/CLAUDE.md
git:20260607.3a2d86f · audit A · 10 stars

Every file in stek0v/levara

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