[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6ME7TS5YSVYNBYNPE20KNXE":3,"skill-same:01M6ME7TS5YSVYNBYNPE20KNXE":82},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":39,"linkOnly":40,"markdownContent":41,"markdownBody":42,"frontMatter":43,"refName":48,"commitSha":49,"skillDirectory":50,"forksCount":51,"repositoryHtmlUrl":52,"repositoryHomepageUrl":53,"ownerHtmlUrl":54,"ownerBlogUrl":55,"ownerDescription":56,"updatedAt":57,"install":58,"resources":71},"01M6ME7TS5YSVYNBYNPE20KNXE","context-mgmt",null,"Context engineering: compaction, progressive disclosure, structured notes via AgentDB. Triggers: tokens, compaction, memory, handoff, summarize, context window.","hashgraph-online\u002Fawesome-codex-plugins","hashgraph-online","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F160371962?v=4","01M6CNB6NRJVNNGN14TR01Q6D3","HOL (Hashgraph Online)","01M6JT1HSKKG9V68KQAQGBA7XP",1575,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fariaxhan\u002Fkernel-claude\u002Fskills\u002Fcontext-mgmt\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"context mgmt","context","task","context window","progressive disclosure","window","compaction","via","triggers","tokens","structured","handoff","read","Bash","methodology","engineering","notes","memory","context engineering","summarize","2026-11-10 10:12:30",false,"---\nname: context-mgmt\ndescription: \"Context engineering: compaction, progressive disclosure, structured notes via AgentDB. Triggers: tokens, compaction, memory, handoff, summarize, context window.\"\nallowed-tools: Read, Bash, Task\nkernel:\n  kind: methodology\n  version: 1\n  side_effects: none\n  confirmation: none\n---\n\n\u003Cskill id=\"context-mgmt\">\n\n\u003Cpurpose>\nContext is finite. Every token competes for attention.\nLonger context makes things WORSE (30%+ accuracy drop for middle info).\nProgressive disclosure: load what's needed when it's needed.\n\n**Reasoning fidelity is the real metric, not token count.** Quality degrades at ~60-70% fill, not at the limit.\n\u003C\u002Fpurpose>\n\n\u003Cprerequisite>\nMonitor context usage. Compact or hand off proactively at ~60% capacity — not 80%, not at limit.\nUse native \u002Fcontext command to check usage. This skill is for methodology.\n\u003C\u002Fprerequisite>\n\n\u003Creference>\nSkill-specific: skills\u002Fcontext-mgmt\u002Freference\u002Fcontext-mgmt-research.md\nArchitecture: _meta\u002Fresearch\u002Fcontext-graph-architecture.md\nGraph telemetry (shadow): JSON receipts → `agentdb graph-project` \u002F `graph-suggest` (see orchestration\u002Fagentdb\u002Fgraph-project.py). Canonical JSON manifests remain authoritative.\n\u003C\u002Freference>\n\n\u003Ccore_principles>\n1. COMPACTION: Summarize and reinitialize. Keep architecture decisions, discard noise.\n2. STRUCTURED NOTES: AgentDB + active.md persist across context resets.\n3. MULTI-AGENT: Delegate research to subagents. They explore, report summaries. Cap the return at ~1,000-2,000 tokens (conclusion + path:line evidence, no raw dumps); the exploration context stays in the subagent.\n4. MINIMAL READS: grep\u002Fglob to find, then read specific sections.\n5. TOOL RESULT CLEARING: Old tool output rarely needs to stay in context. When calling the Claude API directly (not via this harness), prefer the server-side `context-management-2025-06-27` beta over hand-rolled truncation: `clear_tool_uses_20250919` clears old tool results past a token trigger (client keeps full history, no sync needed), `clear_thinking_20251015` clears old thinking blocks while preserving cache hits. Client-side SDK compaction (`compaction_control`, TypeScript\u002FRuby) is deprecated; use server-side `compact_20260112` for summarization, which takes its own beta header `compact-2026-01-12`, not `context-management-2025-06-27`: `trigger` is `input_tokens` only (default 150000, minimum 50000), and custom `instructions` replace the default summarization prompt entirely, so restate the full framing (what to keep: goal, decisions, paths, errors) rather than appending. `pause_after_compaction: true` returns `stop_reason: \"compaction\"` with only the compaction block, so you can re-append recent messages or key instructions, then resend without the flag to continue. Ordering: `clear_thinking_20251015` must precede `clear_tool_uses_20250919` in `edits`. Set `exclude_tools` for results that must survive; clearing tool results invalidates the cached prefix, so set `clear_at_least` so each clear pays for itself. Pair with the `memory_20250818` tool: Claude is warned as the threshold nears and saves state to memory files before results clear. `clear_tool_inputs` (default `false`) also drops call parameters. `clear_thinking_20251015` `keep` defaults are model-specific (newer models keep all turns, older keep the last), so set it explicitly across model tiers. On Fable 5.1\u002FOpus 5.5\u002FSonnet 5.5\u002FHaiku 5.5, server-side edits never invalidate thinking blocks, but hand-editing earlier turns client-side can; for accounts created on\u002Fafter 2026-08-31 a replayed invalidated block is rejected unless you opt into dropping it. Verify clearing fired from `context_management.applied_edits` in the response (`cleared_tool_uses` \u002F `cleared_thinking_turns` and `cleared_input_tokens`; in streaming, the final `message_delta`). Preview savings by passing `context_management` to `count_tokens`: it returns `original_input_tokens` beside the post-clearing `input_tokens`.\n\u003C\u002Fcore_principles>\n\n\u003Ctoken_budget>\n- CLAUDE.md: \u003C150 lines (always loaded)\n- rules\u002F: \u003C100 lines (always loaded)\n- Skills: metadata only at startup, full content on demand\n- Commands: only when invoked\n- Reference docs: only when skill explicitly reads them\n\u003C\u002Ftoken_budget>\n\n\u003Ccompaction_protocol>\n1. CHECK fill level via \u002Fcontext. (gate: \u003C60% → continue; ≥60% → proceed to step 2)\n2. Write critical state: `agentdb write-end '{\"did\":\"X\",\"next\":\"Y\",\"blocked\":\"Z\"}'`\n3. Commit any uncommitted changes. (gate: clean working tree)\n4. Generate handoff if complex work in progress: `\u002Fkernel:handoff`\n5. Trigger compaction.\n6. POST-COMPACT RESTORE:\n   a. Read active.md for project context.\n   b. Run `agentdb read-start` for failures, patterns, contracts.\n   c. Check for pending checkpoints to review.\n\u003C\u002Fcompaction_protocol>\n\n\u003Cfidelity_signals>\nWatch for reasoning degradation BEFORE the token meter shows a problem:\n- Hypothesis depth dropping: agent defaults to first idea, stops exploring alternatives\n- Backtracking absent: errors patched in place instead of root-caused\n- Step count contracting: multi-step plans collapse to one-shot attempts\n- Cross-file awareness fading: agent forgets earlier files in the same session\n- Inline checks disappearing: agent stops verifying assumptions before acting\n\nAny one of these → compact or hand off NOW, even if \u002Fcontext shows \u003C60% fill.\n\u003C\u002Ffidelity_signals>\n\n\u003Cwhat_to_preserve>\nNever compact away:\n- Current task context and goal\n- Active decisions and their rationale\n- Blocking issues and error states\n- File paths currently being worked on\n- Uncommitted changes description\n- Contract IDs and branch names\n\u003C\u002Fwhat_to_preserve>\n\n\u003Cwhat_to_compact>\nAggressively compress:\n- Exploratory searches → \"searched X, found Y at path:line\"\n- File reads → \"read file, key insight: Z\"\n- Successful operations → \"completed: X\"\n- Debugging traces → \"root cause: X, fix: Y\"\n- Tool call history → \"N tool calls, outcome: X\"\n- Research context → offload to AgentDB, keep one-line summary\n\u003C\u002Fwhat_to_compact>\n\n\u003Cfailure_modes>\n1. Agent tries too much at once → context exhausted mid-work\n   Fix: Incremental progress with commits at each step.\n2. Later agent assumes done prematurely → work incomplete\n   Fix: Explicit done-when criteria with evidence required.\n\u003C\u002Ffailure_modes>\n\n\u003C\u002Fskill>\n","\u003Cskill id=\"context-mgmt\">\n\n\u003Cpurpose>\nContext is finite. Every token competes for attention.\nLonger context makes things WORSE (30%+ accuracy drop for middle info).\nProgressive disclosure: load what's needed when it's needed.\n\n**Reasoning fidelity is the real metric, not token count.** Quality degrades at ~60-70% fill, not at the limit.\n\u003C\u002Fpurpose>\n\n\u003Cprerequisite>\nMonitor context usage. Compact or hand off proactively at ~60% capacity — not 80%, not at limit.\nUse native \u002Fcontext command to check usage. This skill is for methodology.\n\u003C\u002Fprerequisite>\n\n\u003Creference>\nSkill-specific: skills\u002Fcontext-mgmt\u002Freference\u002Fcontext-mgmt-research.md\nArchitecture: _meta\u002Fresearch\u002Fcontext-graph-architecture.md\nGraph telemetry (shadow): JSON receipts → `agentdb graph-project` \u002F `graph-suggest` (see orchestration\u002Fagentdb\u002Fgraph-project.py). Canonical JSON manifests remain authoritative.\n\u003C\u002Freference>\n\n\u003Ccore_principles>\n1. COMPACTION: Summarize and reinitialize. Keep architecture decisions, discard noise.\n2. STRUCTURED NOTES: AgentDB + active.md persist across context resets.\n3. MULTI-AGENT: Delegate research to subagents. They explore, report summaries. Cap the return at ~1,000-2,000 tokens (conclusion + path:line evidence, no raw dumps); the exploration context stays in the subagent.\n4. MINIMAL READS: grep\u002Fglob to find, then read specific sections.\n5. TOOL RESULT CLEARING: Old tool output rarely needs to stay in context. When calling the Claude API directly (not via this harness), prefer the server-side `context-management-2025-06-27` beta over hand-rolled truncation: `clear_tool_uses_20250919` clears old tool results past a token trigger (client keeps full history, no sync needed), `clear_thinking_20251015` clears old thinking blocks while preserving cache hits. Client-side SDK compaction (`compaction_control`, TypeScript\u002FRuby) is deprecated; use server-side `compact_20260112` for summarization, which takes its own beta header `compact-2026-01-12`, not `context-management-2025-06-27`: `trigger` is `input_tokens` only (default 150000, minimum 50000), and custom `instructions` replace the default summarization prompt entirely, so restate the full framing (what to keep: goal, decisions, paths, errors) rather than appending. `pause_after_compaction: true` returns `stop_reason: \"compaction\"` with only the compaction block, so you can re-append recent messages or key instructions, then resend without the flag to continue. Ordering: `clear_thinking_20251015` must precede `clear_tool_uses_20250919` in `edits`. Set `exclude_tools` for results that must survive; clearing tool results invalidates the cached prefix, so set `clear_at_least` so each clear pays for itself. Pair with the `memory_20250818` tool: Claude is warned as the threshold nears and saves state to memory files before results clear. `clear_tool_inputs` (default `false`) also drops call parameters. `clear_thinking_20251015` `keep` defaults are model-specific (newer models keep all turns, older keep the last), so set it explicitly across model tiers. On Fable 5.1\u002FOpus 5.5\u002FSonnet 5.5\u002FHaiku 5.5, server-side edits never invalidate thinking blocks, but hand-editing earlier turns client-side can; for accounts created on\u002Fafter 2026-08-31 a replayed invalidated block is rejected unless you opt into dropping it. Verify clearing fired from `context_management.applied_edits` in the response (`cleared_tool_uses` \u002F `cleared_thinking_turns` and `cleared_input_tokens`; in streaming, the final `message_delta`). Preview savings by passing `context_management` to `count_tokens`: it returns `original_input_tokens` beside the post-clearing `input_tokens`.\n\u003C\u002Fcore_principles>\n\n\u003Ctoken_budget>\n- CLAUDE.md: \u003C150 lines (always loaded)\n- rules\u002F: \u003C100 lines (always loaded)\n- Skills: metadata only at startup, full content on demand\n- Commands: only when invoked\n- Reference docs: only when skill explicitly reads them\n\u003C\u002Ftoken_budget>\n\n\u003Ccompaction_protocol>\n1. CHECK fill level via \u002Fcontext. (gate: \u003C60% → continue; ≥60% → proceed to step 2)\n2. Write critical state: `agentdb write-end '{\"did\":\"X\",\"next\":\"Y\",\"blocked\":\"Z\"}'`\n3. Commit any uncommitted changes. (gate: clean working tree)\n4. Generate handoff if complex work in progress: `\u002Fkernel:handoff`\n5. Trigger compaction.\n6. POST-COMPACT RESTORE:\n   a. Read active.md for project context.\n   b. Run `agentdb read-start` for failures, patterns, contracts.\n   c. Check for pending checkpoints to review.\n\u003C\u002Fcompaction_protocol>\n\n\u003Cfidelity_signals>\nWatch for reasoning degradation BEFORE the token meter shows a problem:\n- Hypothesis depth dropping: agent defaults to first idea, stops exploring alternatives\n- Backtracking absent: errors patched in place instead of root-caused\n- Step count contracting: multi-step plans collapse to one-shot attempts\n- Cross-file awareness fading: agent forgets earlier files in the same session\n- Inline checks disappearing: agent stops verifying assumptions before acting\n\nAny one of these → compact or hand off NOW, even if \u002Fcontext shows \u003C60% fill.\n\u003C\u002Ffidelity_signals>\n\n\u003Cwhat_to_preserve>\nNever compact away:\n- Current task context and goal\n- Active decisions and their rationale\n- Blocking issues and error states\n- File paths currently being worked on\n- Uncommitted changes description\n- Contract IDs and branch names\n\u003C\u002Fwhat_to_preserve>\n\n\u003Cwhat_to_compact>\nAggressively compress:\n- Exploratory searches → \"searched X, found Y at path:line\"\n- File reads → \"read file, key insight: Z\"\n- Successful operations → \"completed: X\"\n- Debugging traces → \"root cause: X, fix: Y\"\n- Tool call history → \"N tool calls, outcome: X\"\n- Research context → offload to AgentDB, keep one-line summary\n\u003C\u002Fwhat_to_compact>\n\n\u003Cfailure_modes>\n1. Agent tries too much at once → context exhausted mid-work\n   Fix: Incremental progress with commits at each step.\n2. Later agent assumes done prematurely → work incomplete\n   Fix: Explicit done-when criteria with evidence required.\n\u003C\u002Ffailure_modes>\n\n\u003C\u002Fskill>\n",{"name":5,"kernel":44,"description":7,"allowed-tools":47},{"kind":33,"version":45,"confirmation":46,"side_effects":46},1,"none","Read, Bash, Task","main","2b63f856ce19c2a797929cacabd9e0fc936812fa","plugins\u002Fariaxhan\u002Fkernel-claude\u002Fskills\u002Fcontext-mgmt",491,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins","https:\u002F\u002Fhol.org\u002Fplugins\u002Fbest-codex-plugins","https:\u002F\u002Fgithub.com\u002Fhashgraph-online","https:\u002F\u002Fhol.org","Open-source standards and developer tools for interoperable AI agents: discovery, identity, communication, payments, privacy and security.","2026-11-14 14:06:13",{"source":8,"skillName":5,"commands":59,"prompt":69,"zipAvailable":70},[60,63,66],{"tool":61,"command":62},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill context-mgmt",{"tool":64,"command":65},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill context-mgmt",{"tool":67,"command":68},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill context-mgmt","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fariaxhan\u002Fkernel-claude\u002Fskills\u002Fcontext-mgmt\u002FSKILL.md",true,[72,78],{"path":73,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":76,"sourceHtmlUrl":77},"reference\u002Fcontext-mgmt-research.md","REFERENCE","参考文档",6511,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fariaxhan\u002Fkernel-claude\u002Fskills\u002Fcontext-mgmt\u002Freference\u002Fcontext-mgmt-research.md",{"path":79,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":80,"sourceHtmlUrl":81},"reference\u002Fcontext-research.md",5271,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fariaxhan\u002Fkernel-claude\u002Fskills\u002Fcontext-mgmt\u002Freference\u002Fcontext-research.md",[83,93,101,109,117,125],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":87,"licenseFileUrl":88,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":92},"01M7DV332YQMGD8WTRJ9DZQXTB","worktable-review-with-annotations","Create, inspect, reply to, update, or resolve situated Worktable annotations. Use when feedback belongs to a Doc section, block, text range, or HTML Doc, or when the user asks to address existing review feedback and coordinate a requested artifact edit.","MIT","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":87,"licenseFileUrl":97,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":92},"01M7DV2YGHCZVBEB1AHYB6CGHE","worktable-find-and-synthesize-context","Find, assess, and synthesize context from Worktable Docs and Records. Use when the user asks what a workspace contains, wants workspace-backed research, needs current facts reconciled across artifacts, or requests a cited synthesis without changing workspace state.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FSKILL.md",[],[],{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":87,"licenseFileUrl":105,"sourceHtmlUrl":106,"categories":107,"keywords":108,"publishedAt":92},"01M7DV2TQN1H11ME2SAF9MXN7V","worktable-create-or-update-docs","Create, edit, rename, or maintain narrative Worktable Docs. Use for plans, decisions, briefs, notes, research syntheses, and other durable prose when the user requests a new artifact or a safe update to an existing one.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FSKILL.md",[],[],{"skillNo":110,"name":111,"nameZh":6,"description":112,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":87,"licenseFileUrl":113,"sourceHtmlUrl":114,"categories":115,"keywords":116,"publishedAt":92},"01M7DV2NE452NEA8TXATKSNAJH","worktable-create-or-manage-records","Organize repeated structured information as durable Worktable Records. Use for research datasets, inventories, directories, pipelines, trackers, and other collections whose items need identity, fields, filtering, links, validation, or individual updates.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FSKILL.md",[],[],{"skillNo":118,"name":119,"nameZh":6,"description":120,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":87,"licenseFileUrl":121,"sourceHtmlUrl":122,"categories":123,"keywords":124,"publishedAt":92},"01M7DV2HENRBR2KSCVM064WH0Y","worktable-create-or-manage-interactive-html","Create or improve durable visual and interactive artifacts in Worktable. Use for dashboards, trackers, calculators, mini apps, slide presentations, and other requests that benefit from a polished HTML Doc.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FSKILL.md",[],[],{"skillNo":126,"name":127,"nameZh":6,"description":128,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":87,"licenseFileUrl":129,"sourceHtmlUrl":130,"categories":131,"keywords":132,"publishedAt":92},"01M7DV2CADR5R7RQFFYPNAGR9Y","worktable-collaborate-threads","Read, answer, and hand off messages through durable Worktable threads with users or other authenticated participants. Use when the user asks to check addressed messages, reply to a participant, continue a thread, request another agent's help, wait briefly for a response, or watch for comments and messages sent to the agent.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FSKILL.md",[],[]]