task_auto_check SKILL.md skillA
task_auto_check from theafh/ai-modules is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add theafh/ai-modules/task_auto_check@v1.0.26Pins v1.0.26 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- theafh/ai-modules
- Path
plugins/ai_dev/skills/task_auto_check/SKILL.md- Versions recorded
- 15
- Latest version
- v1.0.26, committed Nov 6, 2026
- First version recorded
- Jul 19, 2026
- Size
- 52,536 bytes
- Repository stars
- 39
- License
- MIT
Autonomously drive one task from open or checked to ready through task_check, verifier-approved body repairs, and final mechanical task-lint cleanup. Use when a user asks to auto-fix readiness issues, make a task ready, refresh a stale task against the current codebase, or run an autonomous readiness loop without implementing the task. A task whose premise the code invalidates stops the loop and surfaces deferral as the user's option.
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
# task_auto_check <task_auto_check_skill> <role> task_auto_check is the opt-in autonomous readiness loop for one task file. It freezes the task's current title and Goal, runs one committed-intent drift check, uses `task_check` as the only readiness gate, and runs `auto_dryrun_task` before the gate of every ordinary repair round so the implementer's seat reads the task before anything is judged ready, then asks modular `auto_*_task` agents to propose and verify minimal task-body repairs until the task becomes `ready` or no verified intent-preserving repair remains. Before reporting ordinary stop results, it finalizes the target file with the base task linter and applies mechanically fixable lint repairs. It prepares a task for `task_implement`; it never implements the task's work and never closes or archives it. </role> <when_to_activate> Activate when the user points at one task and asks for the task itself to be made implementation-ready: - "Auto-check this task until it is ready." - "Make `<task>` ready without implementing it." - "Run the autonomous readiness loop on `<task>`." - "Fix the readiness issues from task_check if they are safe." …
Read the whole file at its exact version.
How to install
mdr add theafh/ai-modules/task_auto_check@sha256:08b48c58a85f23a2The line at the top of this page pins the label v1.0.26, 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_rxzzsxjq7tkhd4ph)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 15 versions of this file, between Jul 19, 2026 and Nov 6, 2026, about one every 8 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.0.26 latest | 2026-11-06 | e76347a | 52,536 B | A | view · diff |
| v1.0.25 | 2026-10-27 | af74b47 | 52,512 B | A | view · diff |
| v1.0.24 | 2026-10-26 | 2036d82 | 46,649 B | A | view · diff |
| v1.0.23 | 2026-10-26 | 415fbbb | 46,649 B | A | view · diff |
| v1.0.22 | 2026-10-12 | 075d007 | 44,875 B | A | view · diff |
| v1.0.21 | 2026-10-12 | e348822 | 41,721 B | A | view · diff |
| v1.0.20 | 2026-10-11 | b011c11 | 36,662 B | A | view · diff |
| v1.0.19 | 2026-10-08 | 27b3f7e | 36,189 B | A | view · diff |
| v1.0.18 | 2026-09-18 | 490d6b3 | 35,973 B | A | view · diff |
| v1.0.17 | 2026-09-07 | d93963b | 31,766 B | A | view · diff |
| v1.0.16 | 2026-09-05 | e04ae6b | 31,048 B | A | view · diff |
| v1.0.15 | 2026-09-05 | a750d17 | 31,097 B | A | view · diff |
| v1.0.14 | 2026-08-23 | 7aac972 | 31,119 B | A | view · diff |
| v1.0.13 | 2026-07-21 | 30b7173 | 29,250 B | A | view · diff |
| v1.0.12 | 2026-07-19 | 4f5b0b5 | 29,193 B | A | view |
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 (52536 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
theafh/ai-modules · 39 stars · license MIT · pushed 2026-11-08 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_rxzzsxjq7tkhd4ph GET https://markdownregistry.com/api/v1/resolve?ref=theafh/ai-modules/task_auto_check GET https://markdownregistry.com/api/v1/blob/08b48c58a85f23a2518b8116c25a3fd9b874371a4dedc6dc23cd451a4e19ad1c
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.