Harmonia reject - record that the developer rejected the built work, blocking capture until it is re-accepted or abandoned. Use ONLY when explicitly invoked as /harmonia:reject.
Scanned 9/6/2026
Install to Claude Code
Skills Directorynpx -y skills add foliveira/harmonia --skill reject --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Reject?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/foliveira-reject)More formats (shields.io, HTML) on the badges page.
---
name: reject
description: Harmonia reject - record that the developer rejected the built work, blocking capture until it is re-accepted or abandoned. Use ONLY when explicitly invoked as /harmonia:reject.
disable-model-invocation: true
---
This is a human-invoked touchpoint. Rejection is a human act: no other skill or agent - flow explicitly - runs it or `bash ${CLAUDE_PLUGIN_ROOT}/bin/workspace.sh reject` on the developer's behalf.
`--reason <text>` is required - a reason-less rejection carries no signal. Ask the developer for the reason if they did not give one, then run:
```bash
bash ${CLAUDE_PLUGIN_ROOT}/bin/workspace.sh reject --repo . --reason "<the developer's reason>"
```
Surface the script's output verbatim. The script is the single source of truth - it resolves the workspace, guards the base ref, supersedes any prior acceptance, and writes the `rejected` marker (timestamp, reason, diff digest). A live rejection blocks `/harmonia:capture` through `verify-acceptance` until the developer re-accepts (which supersedes it) or abandons the task. Do not fork its logic.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
