hyper-code-review skill
✓ VerifiedPerforms natural-language code reviews by running Codex against git branches, working trees, or specific commits to identify potential issues.
- GitHub stars
- 5
- Files
- 2
- Last commit
- Nov 9, 2026
- License
- MIT
- Allowed tools
- —
What does the hyper-code-review skill do?
hyper-code-review performs natural-language code reviews by running Codex against git branches, working trees, or specific commits to identify potential issues.
Summary generated from the skill's SKILL.md.
About the hyper-code-review skill
Performing natural-language code reviews on git branches, working trees, or specific commits is what this skill enables for developers. It acts as a code review gate that should be used after producing changes but before committing or merging. By running Codex via a read-only sandbox, the tool analyzes the broader context of a change rather than just the literal lines modified.
An agent should load this skill when a user requests a critique of their work through commands like "review my code" or by using the specific /hyperclaude:hyper-code-review invocation. The process produces a markdown file containing findings categorized by severity, such as Blocker, Major, or Minor, which is saved to a local directory. This tool is specifically designed for critiquing code and diffs, making it distinct from plan review tools that focus on architectural intentions rather than implementation details.
What an agent can do with it
- 1Review uncommitted local changesAsk the agent to critique all current changes in your working directory before you stage them.
- 2Compare a branch against mainPerform a review of the differences between your current branch and the main branch.
- 3Resume a previous review sessionContinue a code review that was previously interrupted or needs more context.
Written from the skill's SKILL.md. Every use case is checked against a quote from it.
How to install the hyper-code-review skill
Each command copies the skill folder into the client's skills directory. Restart the client or start a new session to load it.Install the hyper-code-review skill in Plugin
/plugin marketplace add zeikar/hyperclaude /plugin install hyperclaude@hyperclaude
Install the hyper-code-review skill in Claude Code
~/.claude/skills/hyper-code-review/SKILL.md
$ npx degit zeikar/hyperclaude/skills/hyper-code-review ~/.claude/skills/hyper-code-reviewInstall the hyper-code-review skill in Claude Code (project)
.claude/skills/hyper-code-review/SKILL.md
$ npx degit zeikar/hyperclaude/skills/hyper-code-review .claude/skills/hyper-code-reviewInstall the hyper-code-review skill in Codex
~/.agents/skills/hyper-code-review/SKILL.md
$ npx degit zeikar/hyperclaude/skills/hyper-code-review ~/.agents/skills/hyper-code-reviewInstall the hyper-code-review skill in Gemini CLI
~/.gemini/skills/hyper-code-review/SKILL.md
$ npx degit zeikar/hyperclaude/skills/hyper-code-review ~/.gemini/skills/hyper-code-reviewInstall the hyper-code-review skill in Claude.ai
npx degit zeikar/hyperclaude/skills/hyper-code-review hyper-code-review && zip -r hyper-code-review.zip hyper-code-review # claude.ai → Customize → Skills → + → Create skill → Upload a skill → hyper-code-review.zip
Automated checks
Ran Nov 15, 2026Full report →Passed our automated checks. That is not a security audit: read the scripts before you let an agent run them. How checks work
- Source repository linked and reachablezeikar/hyperclaude/skills/hyper-code-review is public and reachablegithub.com/zeikar/hyperclaude/tree/HEAD/skills/hyper-code-re ↗Pass
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit 2026-11-09github.com/zeikar/hyperclaude/commits ↗Pass
- No download-and-run or credential theft in scriptsNo scripts in the skill folderPass
- No hidden instructions in SKILL.mdNo override phrases, safeguard switches, credential requests or hidden charactersgithub.com/zeikar/hyperclaude/blob/HEAD/skills/hyper-code-re ↗Pass
- Pre-approved tools are scopedNo pre-approved tools; the agent asks before using onegithub.com/zeikar/hyperclaude/blob/HEAD/skills/hyper-code-re ↗Pass
- SKILL.md follows the Agent Skills formatValid name and description; says when to use it; 91 linesgithub.com/zeikar/hyperclaude/blob/HEAD/skills/hyper-code-re ↗Pass
SKILL.md
View on GitHubhyper-code-review
Code review gate. Calls Codex via codex exec --sandbox read-only - with a code-review prompt template (templates/codex/code-review.md) against a branch diff, uncommitted working-tree changes, or a specific commit; the prompt instructs Codex to run the target git commands itself (read-only sandbox) and review with broadened blast-radius context — not only the literal changed lines. Saves the output to .hyperclaude/code-reviews/<timestamp>-<slug>.md; you read the file and surface the findings.
When to use
- User typed
/hyperclaude:hyper-code-review(with or without an argument). - After a non-trivial change set is staged or committed locally and a Codex critique is wanted.
When to skip
- The change is a tiny one-line tweak where a full review adds no value.
- You want a plan critique, not a code critique — use
/hyperclaude:hyper-plan-reviewinstead.
How to invoke
Invocation argument: $ARGUMENTS
--resume is supported. Paths with spaces are unsupported.
Argv grammar (summary)
Pre-normalize: if the first token is uncommitted case-insensitively, lowercase it. Then apply:
/^(?:(uncommitted|[0-9a-f]{7,40}|vs\s+[A-Za-z0-9._/][A-Za-z0-9._/-]*))?(?:\s*(--resume)(?:\s+(?!-)(\S+))?)?\s*$/
Group 1 = target, Group 2 = --resume token, Group 3 = artifact path. Bare --resume → --resume auto. Empty Group 1 → bridge default (--base main).
For the full regex breakdown, valid/rejected invocation lists, resume identity rules, and per-pattern bridge examples, see references/argv-grammar.md.
Step 1 — Resolve the bridge argv
Parse $ARGUMENTS with the grammar above. Construct an argv array (NOT a single shell string) to pass to the bridge.
| Pattern | Bridge argv |
|---|---|
| Empty (no argument) | ['code-review', '--base', 'main'] |
Literal uncommitted (case-insensitive, pre-normalized to lowercase) |
['code-review', '--uncommitted'] |
7–40 hex chars matching ^[0-9a-f]{7,40}$ |
['code-review', '--commit', '<sha>'] |
Matches ^vs (.+)$ AND rest passes ^[A-Za-z0-9._/-]+$ |
['code-review', '--base', '<ref>'] |
--resume present (Group 2) |
Append ['--resume', <Group 3 or 'auto'>] to above |
| Anything else | Tell the user the contract above, ask them to clarify, STOP. Do NOT fall through to --base <argument> — this is shell-injection-prone and produces bad slug filenames. |
Step 2 — Compose the review brief and/or background
Two distinct, independently-gated channels — do not conflate them:
-
Review brief — compose per
${CLAUDE_PLUGIN_ROOT}/references/review-brief.md, assigning the scratchpad path toBRIEF_FILEper its shell-safety recipe; with no admissible source, omit the flag. Passed when a source exists, fresh AND resumed alike. -
Background (fresh runs only). Skip entirely if resuming (Group 2 matched): do NOT compose or pass
--background— the bridge rejects it alongside any--resume(mutually exclusive), and the prior context already lives in the Codex thread.Otherwise, optionally write 1–3 sentences of neutral, descriptive background — what changed, what it touches, author intent. Skip it for a trivial change (just omit
--background).Guardrail: describe only. Never state what to flag, pre-judge or rank findings, or assign severities — background orients Codex on scope, it must not steer conclusions (builder/critic independence).
Pass it shell-safely (free prose may contain quotes /
$()/ backticks):Writethe summary to a file in the session scratchpad — outside the repo, not viaecho, no hardcoded literal path — assign its path toBACKGROUND_FILE, then pass--background "$(cat "$BACKGROUND_FILE")". The inner quotes protect the path; the outer"$(...)"makes the contents one argv token. Never inline the prose into the command string.
Step 3 — Run the bridge
Use the Bash tool with run_in_background: true (invocation mode: ${CLAUDE_PLUGIN_ROOT}/references/bridge-review-calls.md). Pass each argument as a separate token — never interpolate user-supplied substrings into a single quoted string.
node "${CLAUDE_PLUGIN_ROOT}/scripts/codex-bridge.mjs" code-review <flags from table above> [--resume <Group 3 or 'auto'>] [--review-brief "$(cat "$BRIEF_FILE")"] [--background "$(cat "$BACKGROUND_FILE")"]
Flag selection follows the dispatch table. If --resume was matched (Group 2), append --resume <value> where <value> is Group 3 if present, otherwise auto. See references/argv-grammar.md for a per-pattern cookbook of fully expanded commands. The optional --review-brief "$(cat "$BRIEF_FILE")" token is appended whenever a source exists — fresh or resumed. The optional --background "$(cat "$BACKGROUND_FILE")" token is appended only on a fresh (non-resume) run, following the temp-file recipe in Step 2.
Step 4 — Surface the review
Once the bridge task completes, parse the single JSON line from its stdout. See the Output contract section below for full details on the JSON structure. In brief:
- On success — read the review file with the Read tool and present the findings.
- On failure — surface the error verbatim to the user; do not pretend a review happened. When
resumeStatusisresume-failed, note that the prior context could not be used.
Output contract
Parse the bridge's single stdout JSON envelope per ${CLAUDE_PLUGIN_ROOT}/references/bridge-review-calls.md (envelope shape + strict-parse rule).
Code-review files have YAML frontmatter — among it codex-resume-status (fresh | resumed | fallback | resume-failed), codex-resumed-from when resumed, review-brief when a brief was supplied or carried forward, and the target (base-ref or commit); the full key list is in ${CLAUDE_PLUGIN_ROOT}/docs/architecture.md — followed by a Codex review body (### Findings with Blocker/Major/Minor + ### Verdict). Do not modify the file.
Distinction note
This skill critiques code and diffs. For plan critiques use /hyperclaude:hyper-plan-review.
Files in this skill
2hyper-code-review skill questions
How do I install the hyper-code-review skill in Claude Code?
Run npx degit zeikar/hyperclaude/skills/hyper-code-review ~/.claude/skills/hyper-code-review. Claude Code loads skills from ~/.claude/skills (all projects) or .claude/skills (one project) and uses a skill when its description matches the task.
Which clients can use the hyper-code-review skill?
Any client that reads the Agent Skills format: Claude Code, Codex, Gemini CLI and claude.ai (upload as a ZIP). Scripts in the skill run only where the client allows code execution.
When should I use hyper-code-review?
Use it after producing code changes that need critiquing, such as before a commit or merge, or when invoking the specific command.
Can I use this skill to review a plan instead of code?
No, this skill is specifically for critiquing code and diffs; you should use /hyperclaude:hyper-plan-review for plan critiques.