OpenParable
Skip to content
← Back to skills

Bounded Work Item

Productivity
bounded-work-item

Bounded Work Item is an Agent Skill for productivity published in the SeemSeam/claude_codex_bridge repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Execute one bounded CCB work item and report evidence without changing workflow authority.

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/SeemSeam/claude_codex_bridge/blob/HEAD/docs/plantree/plans/agentic-loop-workflow/drafts/agentroles.ccb_worker/skills/bounded-work-item/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/bounded-work-item, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

Bounded Work Item

Use this skill when orchestrator assigns a single work node.

Inputs

  • node id
  • task packet reference
  • assigned scope and non-goals
  • acceptance criteria
  • verification expectation

Output

Return exactly one result class:

  • done
  • blocked
  • needs_rework

Include files touched, commands run, verification evidence, and unresolved blockers.