loop-controller SKILL.md skillA
loop-controller from ivy00johns/skill-madness is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add ivy00johns/skill-madness/loop-controller@v1.6.0Pins v1.6.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- ivy00johns/skill-madness
- Path
skills/loops/loop-controller/SKILL.md- Versions recorded
- 5
- Latest version
- v1.6.0, committed Oct 8, 2026
- First version recorded
- Jul 4, 2026
- Size
- 24,175 bytes
- Repository stars
- 11
- License
- MIT
Add a verifiable stop condition and a mandatory guardrail stack to any task so an autonomous loop converges instead of thrashing or burning the budget — the foundation harness every loop skill composes on, so it loads first and then routes to the right primitive (/goal vs /loop vs Stop-hook vs a bash Ralph loop vs a dynamic workflow). Use whenever the agent must keep working until something is provably true — "loop until", "keep going until", "keep the suite green until it passes…
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
# loop-controller > **Why this is a deliberate (`disable-model-invocation`) skill.** A loop edits, > commits, and spends tokens on its own. You want to *type* `/loop-controller` > (or have the orchestrator dispatch it), not have Claude silently start an > autonomous loop because a test happened to fail. The discipline below is what > makes that safe. ## The one rule that governs every loop **A loop is only as good as its stopping condition.** Loops *converge* when "done" is an external signal the agent cannot argue with — a test exit code, a coverage percentage, an empty queue, a fresh evaluator's verdict. They *diverge* — oscillate, thrash, or run the budget to zero — when "done" is a subjective judgment the agent grades itself on. Agents are pathological optimists about their own work; left to self-assess, they declare victory early. There is a subtler failure an objective proof does **not** cure: a signal that is mechanical, default-FAIL, and un-gameable can still measure the **wrong thing**. A test suite green against a mock, a stub, or a fixture is all three of those — and proves nothing about whether the real product works. That is …
Read the whole file at its exact version.
How to install
mdr add ivy00johns/skill-madness/loop-controller@sha256:8714519fa531271dThe line at the top of this page pins the label v1.6.0, 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_od4knriw54psb5ol)
0 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Jul 4, 2026 and Oct 8, 2026, about one every 24 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.6.0 latest | 2026-10-08 | d1d8537 | 24,175 B | A | view · diff |
| v1.2.1 | 2026-07-22 | e29873b | 21,950 B | A | view · diff |
| v1.2.0 | 2026-07-09 | c5074c0 | 21,950 B | A | view · diff |
| v1.1.1 | 2026-07-04 | 93d1c20 | 20,273 B | A | view · diff |
| v1.1.0 | 2026-07-04 | d5c2eab | 20,062 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 (24175 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
ivy00johns/skill-madness · 11 stars · license MIT · pushed 2026-10-25 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_od4knriw54psb5ol GET https://markdownregistry.com/api/v1/resolve?ref=ivy00johns/skill-madness/loop-controller GET https://markdownregistry.com/api/v1/blob/8714519fa531271dac0d2a395def6fe7e1b6f7620d0a79296aac41868f64c151
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.