{"version":"2.1.251","anchor":"plugins-can-now-hook-agent-offers-skill-prompts-and-attribut","canonical_anchor":"plugins-can-now-hook-agent-offers-skill-prompts-and-attribut","heading":"Plugins can now hook agent offers, skill prompts and attribution text","tier":"use","area":"Plugins","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.251\/e\/plugins-can-now-hook-agent-offers-skill-prompts-and-attribut","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.251","markdown":"### Plugins can now hook agent offers, skill prompts and attribution text\n\nPlugins can now control which subagents are offered, skill prompt text, and commit attribution.\n\n**What**\n\nThree new points where a plugin can intervene: whether a given subagent type is offered to the model, the text of a skill's prompt before it is used, and the attribution text attached to commits and PRs. Each runs only if a plugin registered a handler for it; otherwise Claude Code's own default behavior runs unchanged.\n\n**Details**\n\n- The agent offer point checks whether any handler is registered for that event before filtering the candidate agent list, so no handler means no extra work.\n- The attribution point is called by the builder that produces commit and PR attribution text, so a plugin can rewrite what gets committed.\n- Each event carries the subject with it: the agent offer event is matched on the agent, its description and its source, and answered with a boolean saying whether to offer it.\n\n**Evidence**\n\n`hasModuleHandlers(\"agent.offer\", { agent: r.agentType })`, `\"skill.prompt\": X.SKILL_PROMPT`, `attribution.text`\n\n- Area: Plugins\n- Tier: Use it now\n- Useful: 4\/5\n- Signal: 4\/5"}