levara-audit-task SKILL.md skillA
levara-audit-task from stek0v/levara is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add stek0v/levara/levara-audit-task@git:20260805.1845188Pins git:20260805.1845188 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-audit-task/SKILL.md- Versions recorded
- 1
- Latest version
- git:20260805.1845188, committed Aug 5, 2026
- Size
- 2,055 bytes
- Repository stars
- 10
- License
- MIT
Independently audit a Levara long-horizon Task against its original objective, authority, Definition of Done, steps, receipts, workspace revision, blockers, and memory candidates. Use before completing high-risk tasks, when DoD requires independent review, or when asked to verify long-task completeness. Do not implement fixes, mutate the plan, claim steps, promote memories, or complete the Task.
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
# Audit a Levara task Act as a read-only verifier. Do not trust executor summaries without receipts. ## Workflow 1. Call `task_bootstrap` for the supplied `task_id` with enough budget to include all criteria and steps. 2. Call `task_validate(mode=completion)` and independently inspect every returned deficiency. 3. Compare each required criterion with a passing, current receipt. 4. Check that command receipts have exit code 0, artifact receipts have URI and digest, and reviewer/source receipts identify what was actually examined. 5. Treat evidence from a different workspace revision as stale. 6. Check authority boundaries, active blockers, active leases, incomplete steps, and failed attempts hidden by later summaries. 7. Review pending memory candidates: reject speculation, temporary state, code paths, undated events, and discoveries without evidence. 8. Record the audit as a `reviewer` receipt only when an existing audit criterion is present. Otherwise return the audit findings without mutating Task state. ## Verdict Return one of: - `pass`: every required criterion is current and evidenced; no critical finding remains. …
Read the whole file at its exact version.
How to install
mdr add stek0v/levara/levara-audit-task@sha256:cf476e4ce8cda81aThe line at the top of this page pins the label git:20260805.1845188, 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_qabwfuh7ttksgcvz)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Aug 5, 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 (2055 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
stek0v/levara · 10 stars · license MIT · pushed 2026-10-21 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_qabwfuh7ttksgcvz GET https://markdownregistry.com/api/v1/resolve?ref=stek0v/levara/levara-audit-task GET https://markdownregistry.com/api/v1/blob/cf476e4ce8cda81a664093f0bff0a91bb230ae63c694640f9357bb946d6f72ff
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.