hyper-plan-loop SKILL.md skillA
hyper-plan-loop from zeikar/hyperclaude is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add zeikar/hyperclaude/hyper-plan-loop@git:20261007.51d78cfPins git:20261007.51d78cf in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- zeikar/hyperclaude
- Path
skills/hyper-plan-loop/SKILL.md- Versions recorded
- 11
- Latest version
- git:20261007.51d78cf, committed Oct 7, 2026
- First version recorded
- Aug 6, 2026
- Size
- 19,791 bytes
- Repository stars
- 4
- License
- MIT
Use when a plan should be produced and critic-hardened in one gesture — plan → review → revise, repeated until clean. Also when the user invokes /hyperclaude:hyper-plan-loop. For manual round-by-round control use /hyperclaude:hyper-plan + /hyperclaude:hyper-plan-review instead.
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
# hyper-plan-loop
Autonomous plan-hardening gate. Spawns the `planner` agent once, has it write its plan to `.hyperclaude/plans/<YYYYMMDD-HHMM>-<slug>.md`, has it reviewed, and revises via the still-live planner until the review returns no blocking findings (judged by meaning, not severity labels) or the cap is hit. The planner is spawned **once**; every revise round reuses its retained context. The reviewer is Codex `plan-review` through the bridge by default; the adversarial `reviewer` agent takes the seat for the run when the Codex budget is over pace (`${CLAUDE_PLUGIN_ROOT}/references/reviewer-seat.md`).
## When to use
- User typed `/hyperclaude:hyper-plan-loop <task>`.
- User wants an autonomous plan → review → revise cycle in a single gesture.
Skip when:
- The task is one step — dispatch the `implementer` agent directly (pass `run_in_background: false` for the result inline).
- You want hands-on control over each plan / review round — use `/hyperclaude:hyper-plan` + `/hyperclaude:hyper-plan-review` manually.
## Failure & recovery protocol — read first
…Read the whole file at its exact version.
How to install
mdr add zeikar/hyperclaude/hyper-plan-loop@sha256:a7cbe42ef9bfd1b7The line at the top of this page pins the label git:20261007.51d78cf, 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_hkcipxmcetseg56c)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 11 versions of this file, between Aug 6, 2026 and Oct 7, 2026, about one every 6 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261007.51d78cf latest | 2026-10-07 | 51d78cf | 19,791 B | A | view · diff |
| git:20261006.15c3720 | 2026-10-06 | 15c3720 | 19,485 B | A | view · diff |
| git:20260929.d328514 | 2026-09-29 | d328514 | 19,438 B | A | view · diff |
| git:20260929.99a57bc | 2026-09-29 | 99a57bc | 19,342 B | A | view · diff |
| git:20260929.2ab108a | 2026-09-29 | 2ab108a | 19,280 B | A | view · diff |
| git:20260928.edf3982 | 2026-09-28 | edf3982 | 19,274 B | A | view · diff |
| git:20260906.91a1b48 | 2026-09-06 | 91a1b48 | 17,339 B | A | view · diff |
| git:20260902.d3ec574 | 2026-09-02 | d3ec574 | 20,972 B | A | view · diff |
| git:20260902.799e877 | 2026-09-02 | 799e877 | 19,500 B | A | view · diff |
| git:20260817.dcc4029 | 2026-08-17 | dcc4029 | 16,649 B | A | view · diff |
| git:20260806.d27f7f4 | 2026-08-06 | d27f7f4 | 28,493 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 (19791 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
zeikar/hyperclaude · 4 stars · license MIT · pushed 2026-10-14 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_hkcipxmcetseg56c GET https://markdownregistry.com/api/v1/resolve?ref=zeikar/hyperclaude/hyper-plan-loop GET https://markdownregistry.com/api/v1/blob/a7cbe42ef9bfd1b7179410cf50468c51965f9bf6bfc74a91aee0f5e261e19fea
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.