hyper-recap SKILL.md skillA
hyper-recap 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-recap@git:20260929.2ab108aPins git:20260929.2ab108a 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-recap/SKILL.md- Versions recorded
- 7
- Latest version
- git:20260929.2ab108a, committed Sep 29, 2026
- First version recorded
- Jul 13, 2026
- Size
- 20,189 bytes
- Repository stars
- 5
- License
- MIT
Use at cycle completion to write a human-readable recap of what was built and why — "recap this cycle", "summarize what we built", "cycle recap", "write up what changed this cycle". Also when the user invokes /hyperclaude:hyper-recap. Claude-only — no Codex, no agent dispatch — runs after a plan is implemented and reviewed, and writes a recap to .hyperclaude/recaps/. Recaps ONE completed detailed plan / milestone archived under .hyperclaude/plans/done/. Distinct from /hyperclaude:hyper-memory…
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-recap Cycle-completion recap. An AI-run cycle leaves the codebase changed but the human out of the loop: the request, the judgments taken, the alternatives rejected, and the critic rounds are all in the AI's head or scattered across gitignored artifacts. That is cognitive debt — without a write-up a human can't reconstruct *why* and *how* the AI built what it built. This skill collapses one completed cycle into a single human-readable recap under `.hyperclaude/recaps/`. **Claude-only — no Codex, no agent dispatch.** It joins the non-Codex-spawning set alongside `hyper-interview`, `hyper-memory`, and `hyper-setup`. It never calls the bridge and never dispatches an agent — it only reads `.hyperclaude/` artifacts + in-session context and writes one markdown file. The recap unit is **ONE completed detailed plan / milestone** (a plan archived under `.hyperclaude/plans/done/`). Epic-level rollup across milestones is out of scope. This is **NOT a PR draft** — it explains the cycle to a human, it does not propose or format changes for merge. ## When to use - User typed `/hyperclaude:hyper-recap [path|slug]`. …
Read the whole file at its exact version.
How to install
mdr add zeikar/hyperclaude/hyper-recap@sha256:d4f54f9e17236f28The line at the top of this page pins the label git:20260929.2ab108a, 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_fhcehaw2krj7hnlv)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 7 versions of this file, between Jul 13, 2026 and Sep 29, 2026, about one every 13 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260929.2ab108a latest | 2026-09-29 | 2ab108a | 20,189 B | A | view · diff |
| git:20260928.478f445 | 2026-09-28 | 478f445 | 20,550 B | A | view · diff |
| git:20260715.31f2991 | 2026-07-15 | 31f2991 | 20,251 B | A | view · diff |
| git:20260714.cd198de | 2026-07-14 | cd198de | 20,107 B | A | view · diff |
| git:20260713.70e64c2 | 2026-07-13 | 70e64c2 | 18,694 B | A | view · diff |
| git:20260713.20e53b1 | 2026-07-13 | 20e53b1 | 17,712 B | A | view · diff |
| git:20260713.5197a6b | 2026-07-13 | 5197a6b | 17,588 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 (20189 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 · 5 stars · license MIT · pushed 2026-10-14 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_fhcehaw2krj7hnlv GET https://markdownregistry.com/api/v1/resolve?ref=zeikar/hyperclaude/hyper-recap GET https://markdownregistry.com/api/v1/blob/d4f54f9e17236f28b4b09e776ff646e9293aba890e4e44e890ce394b6b3d5370
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.