Harmonia accept - record human acceptance of the built work so capture can proceed. Use ONLY when explicitly invoked as /harmonia:accept.
Scanned 9/6/2026
Install to Claude Code
Skills Directorynpx -y skills add foliveira/harmonia --skill accept --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Accept?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/foliveira-accept)More formats (shields.io, HTML) on the badges page.
---
name: accept
description: Harmonia accept - record human acceptance of the built work so capture can proceed. Use ONLY when explicitly invoked as /harmonia:accept.
disable-model-invocation: true
---
This is a human-invoked touchpoint. Acceptance is a human act: no other skill or agent - flow explicitly - runs it or `bash ${CLAUDE_PLUGIN_ROOT}/bin/workspace.sh accept` on the developer's behalf. The developer types `/harmonia:accept` only after exercising the built behavior and confirming it matches intent.
Run the acceptance subcommand against the active workspace and surface its output verbatim:
```bash
bash ${CLAUDE_PLUGIN_ROOT}/bin/workspace.sh accept --repo .
```
The script is the single source of truth - it resolves the workspace, digests the attested diff, supersedes any prior rejection, and writes the marker. Do not fork or reinterpret its logic; report what it prints (the marker line, or its refusal and exit code).
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!
