{"id":50939095,"url":"https://github.com/wolkat/opencode-skill-hush","last_synced_at":"2026-06-17T12:01:46.099Z","repository":{"id":362158205,"uuid":"1255272737","full_name":"wolkat/opencode-skill-hush","owner":"wolkat","description":"OpenCode plugin that suppresses verbose skill content and command template display in the TUI.  Instead of dumping 100+ lines of \u003cskill_content\u003e into the conversation when an agent loads a skill, it shows a one-line placeholder. The skill content still reaches the LLM context.","archived":false,"fork":false,"pushed_at":"2026-06-02T22:14:45.000Z","size":94,"stargazers_count":0,"open_issues_count":1,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-06-03T00:11:07.762Z","etag":null,"topics":["opencode-plugin"],"latest_commit_sha":null,"homepage":"","language":"TypeScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/wolkat.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":"SECURITY.md","support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":"AGENTS.md","dco":null,"cla":null}},"created_at":"2026-05-31T16:15:58.000Z","updated_at":"2026-06-02T22:13:37.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/wolkat/opencode-skill-hush","commit_stats":null,"previous_names":["wolkat/opencode-skill-hush"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/wolkat/opencode-skill-hush","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wolkat%2Fopencode-skill-hush","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wolkat%2Fopencode-skill-hush/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wolkat%2Fopencode-skill-hush/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wolkat%2Fopencode-skill-hush/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/wolkat","download_url":"https://codeload.github.com/wolkat/opencode-skill-hush/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wolkat%2Fopencode-skill-hush/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34447266,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-17T02:00:05.408Z","response_time":127,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["opencode-plugin"],"created_at":"2026-06-17T12:01:45.058Z","updated_at":"2026-06-17T12:01:46.094Z","avatar_url":"https://github.com/wolkat.png","language":"TypeScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"# opencode-skill-hush\n\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)\n[![npm version](https://img.shields.io/npm/v/opencode-skill-hush)](https://www.npmjs.com/package/opencode-skill-hush)\n\nOpenCode plugin that suppresses verbose skill content and command template display in the TUI.\n\nInstead of dumping 100+ lines of `\u003cskill_content\u003e` into the conversation when an agent loads a skill, it shows a one-line placeholder. The skill content still reaches the LLM context -- only the TUI display is shortened.\n\n## Before / After\n\n**Skill load -- Before:**\n\n```\nLoaded skill: bmad-advanced-elicitation\n\n\u003cskill_content name=\"bmad-advanced-elicitation\"\u003e\n# Skill: bmad-advanced-elicitation\n\n# Advanced Elicitation\n**Goal:** Push the LLM to reconsider, refine, and improve its recent output.\n...\nBase directory for this skill: /Users/katops/git/.agents/skills/...\n\u003c/skill_content\u003e\n```\n\n**Skill load -- After:**\n\n```\nskill: bmad-advanced-elicitation\n[Skill \"bmad-advanced-elicitation\" loaded]\n```\n\n**Command template -- Before:**\n\n```\n/commit\nfeat: add new feature (multi-line resolved template...)\n```\n\n**Command template -- After:**\n\n```\n/commit\n[Command: commit]\n```\n\n## Installation\n\n### Global (recommended)\n\n```bash\nnpm install -g opencode-skill-hush\n```\n\n### Or as a local plugin\n\nClone the repo and reference it directly in `opencode.json`:\n\n```json\n{\n  \"plugin\": [\"/path/to/opencode-skill-hush/dist/index.js\"]\n}\n```\n\n## Configuration\n\nAdd to your `opencode.json`:\n\n```json\n{\n  \"plugin\": [\n    [\"opencode-skill-hush\", {\n      \"suppressSkills\": true,\n      \"suppressCommands\": true,\n      \"showLineCount\": false\n    }]\n  ]\n}\n```\n\n### Options\n\n| Option | Type | Default | Description |\n|--------|------|---------|-------------|\n| `suppressSkills` | `boolean` | `true` | Replace skill tool content with placeholder |\n| `suppressCommands` | `boolean` | `true` | Replace command templates with placeholder |\n| `showLineCount` | `boolean` | `false` | Append line count to skill placeholder |\n\nRestart opencode after changing config.\n\n## Structure\n\n```\nopencode-skill-hush/\n├── src/\n│   ├── index.ts            # Plugin entry, exports ContentHushPlugin\n│   └── hooks/\n│       ├── skill.ts        # tool.execute.after handler\n│       ├── command.ts      # command.execute.before handler\n│       ├── chat.ts         # chat.message handler\n│       └── __tests__/      # Unit tests (vitest)\n├── package.json\n├── tsconfig.json\n└── AGENTS.md\n```\n\n## How it works\n\nThree hooks, one plugin:\n\n| Hook | Target | What it does |\n|------|--------|-------------|\n| `tool.execute.after` | `skill` tool | Replaces `output.title` and `output.output` with a minimal placeholder. The tool has already finished, so the LLM context is unaffected. |\n| `command.execute.before` | slash commands | Replaces `output.parts` with a single `[Command: {name}]` text part before it renders. |\n| `chat.message` | TUI chat messages | Detects command templates in chat text parts and replaces them with `[Command: {heading}]`. Matches if the text contains a `\u003cskill_content\u003e` tag (regardless of H2 structure), or starts with an H1 heading (`#`) that has a `/` prefix and includes H2 sections (`##`). Minimum 50 chars. Catches templates that arrive via `chat.message` rather than `command.execute.before`. |\n\n## Development\n\n```bash\nnpm install\nnpm run typecheck\nnpm test\n```\n\n## Contributing\n\nSee [CONTRIBUTING.md](CONTRIBUTING.md) for contribution guidelines and [CODE_OF_CONDUCT.md](CODE_OF_CONDUCT.md) for community standards.\n\n## Security\n\nReport vulnerabilities via [SECURITY.md](SECURITY.md).\n\n## License\n\nMIT License. See [LICENSE](LICENSE).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fwolkat%2Fopencode-skill-hush","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fwolkat%2Fopencode-skill-hush","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fwolkat%2Fopencode-skill-hush/lists"}