一键导入
resume-skill-listing-suppression
Mark the current skill listing as already sent when resuming so the transcript does not receive a redundant payload.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Mark the current skill listing as already sent when resuming so the transcript does not receive a redundant payload.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Collapse multiple change sources into one caller-facing boolean so headless bootstraps know whether a downstream refresh is necessary.
After awaiting persistence work, update the shared budget state for each `tool_use_id` exactly once so no concurrent reader ever sees a half-committed decision.
Issue continuation nudges while the turn stays under budget, then halt once diminishing returns or the budget cap justify stopping.
Lazily extract referenced files for bundled skills so large prompts stay offline until needed.
Persist a cache-safe stop-hook context snapshot only for main session queries so later helpers can resume from stable state without fork pollution.
Sweep stale extension caches before activation, then fall back to a sticky manual-refresh flag if the live refresh fails.
| name | resume-skill-listing-suppression |
| description | Mark the current skill listing as already sent when resuming so the transcript does not receive a redundant payload. |
| metadata | {"author":"ychampion"} |
Domain: command-surfaces
Trigger: Apply when a resume flow already contains a previous skill_listing attachment and injecting another would waste ~600 tokens.
Source Pattern: Distilled from reviewed command-surface and listing-control patterns.
Treat a resume run as continuing an existing transcript: before recomputing skill_listing, mark every command that already exists in the transcript as sent by setting suppressNext = true and filling sentSkillNames for that agentId. Return early without emitting any listing so the resume session does not repeat the large skill payload, even though the future process loses the ability to announce cross-process deltas until the next full session.
suppressNextSkillListing() so external flows (conversation recovery) can set a flag that the next listing should be skipped.suppressNext; if true, mark all current commands as sent, reset the flag, and return [].sentSkillNames map keyed by agentId (main thread uses empty string) so per-agent delta tracking remains correct.When a session is resumed, call suppressNextSkillListing() right before getSkillListingAttachments so it returns [] and the transcript keeps the listing it already has instead of receiving another copy.
sentSkillNames or unset suppressNext during resume; you need to pretend the listing is still current.