Agent skill · AI & Agents

agent-work

Agent Work registry (works / work_versions): how agent outputs — github/linear entities, files, documents, tasks — get registered, deduped, and rendered as cards, and how to extend it with a new skill provider, a new shell CLI scanner, or a new Work type.

LobeHub80,937★ · +310/wk · 1 repos on radarProfile →
claude-codeNOASSERTION
Install
npx skills add lobehub/lobehub --skill agent-work --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 1
SKILL.md size: 13 KB
Bundled scripts: none
Path: .agents/skills/agent-work/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 81,252 · +315 this week
Language: TypeScript
Read our review of the source →

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# Agent Works A **Work** is a durable record of something an agent produced or touched — a GitHub PR/issue, a Linear issue, an entity file (pptx/xlsx/docx/pdf), a document, a task. Works render as cards under the assistant message that produced them and accumulate **versions** across operations, so the same PR edited twice shows one card with history. Two tables (`packages/database/src/schemas/work.ts`): - `works` — one row per resource. Identity/dedup key: `(resourceType, resourceId)` within the user/workspace scope. `currentVersionId` soft-references the latest version. - `work_versions` — one row per registration event. Dedup: unique `(workId, toolCallId)`, so a retried registration with the same real tool call id is a no-op. Versions carry provenance (source message, producing tool) and operation-level `cumulativeCost` / `cumulativeUsage`. ## Type registry `packages/database/src/models/work/registry.ts` is the single registry of Work types (`document` / `external` / `file` / `task`): `WORK_TYPE_ADAPTERS` is `satisfies Record<WorkType, WorkTypeAdapter>`, so a type added to `@lobechat/types` without an adapter is a compile error. **Read-path compatibility gate**: `OPT_IN_WORK_TYP

What's inside
Steps it walks through
  1. Type registry
  2. Registration write paths
  3. Execution-time: skill providers
  4. Completion-time: the shell Work scan framework
  5. Cost granularity: execution-time vs completion-time
  6. Display anchor & completion marker
  7. Key decisions (from the Work PRs)
  8. Extension recipes
  9. File map
More from lobehub
All skills →
About this skill
What does the agent-work skill do?

Agent Work registry (works / work_versions): how agent outputs — github/linear entities, files, documents, tasks — get registered, deduped, and rendered as cards, and how to extend it with a new skill provider, a new shell CLI scanner, or a new Work type.

How do I install it?

Run `npx skills add lobehub/lobehub --skill agent-work --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From lobehub/lobehub, a repository with 81,252 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going