Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Xwen0857/agent-orchestrator --skill planner-coregit clone --depth 1 https://github.com/Xwen0857/agent-orchestratorWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/xwen0857/agent-orchestrator/planner-core)<a href="https://agentmods.dev/skills/xwen0857/agent-orchestrator/planner-core"><img src="https://agentmods.dev/badge/skills/xwen0857/agent-orchestrator/planner-core/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/xwen0857/agent-orchestrator/planner-core"><img src="https://agentmods.dev/badge/skills/xwen0857/agent-orchestrator/planner-core.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00027 | $0.01903 |
| Opus 5 | $0.00014 | $0.00951 |
| Sonnet 5 | $0.00005 | $0.00381 |
| Haiku 4.5 | $0.00003 | $0.00190 |
Grade A, and why
planner-core scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Planner Core
Agent Identity
planner-core 是专用 planning agent,不是通用 helper 脚本。
- 它负责规划理解、第一层初次拆分决策、拆分决策、首波释放决策。
- 它不负责持续运营、轮询、worker/tester 执行、长期心跳控制。
- 它产出的核心结果是结构化
PlannerDecision与SplitPlan,后续脚本只负责应用这些决策。
Decision Priority Ladder
以下优先级是硬规则,不允许实现层随意改变:
- planner-managed ingress(入口不再存 mode 字段)
- child task internal guardrail
- agent-first initial meta decomposition
- soft granularity guardrails / fallback
- decision apply path
Two-Layer Planning Semantics
- planner ingress 是隐式且始终由 planner 管理。
planner-core总是执行第一层 Initial Meta Decomposition。- 第一层主原则是
functional_decoupling:优先识别功能/职责边界。 - 第二层 Worker Refinement 是必经阶段,主原则是
engineering_decoupling。 - 规则系统只做软约束:限制碎片上限与下限,避免过粗或过碎。
Leaf Dependency Model (Current Scope)
refinement_partition.leaf_units必须形成最小可消费链路:module_id/module_titlecomponent_candidatedepends_on_component_candidatesdepends_on_leaf_ids
- 该链路是 planning-time coordination hint,不是完整 DAG 调度系统。
- 当前允许的语义模式固定为
component_semantic_linearized。 - 必须 fail-fast 校验:缺失引用、自依赖、未来依赖、组件依赖不一致都直接失败。
- Planner 不变量唯一规范来源:
templates/coordination/orchestrator/planner_invariants.md。 - Planner 依赖语义与默认值分离:
templates/coordination/orchestrator/planner_dependency_semantics.json负责组件依赖映射。templates/coordination/orchestrator/planner_dependency_defaults.json负责 mode/note/fallback summary 默认值。
split_plan.schema_version = planner-split-plan-v1、dependency_mode = component_semantic_linearized、summary_note = planning_hint_not_scheduler_dag由契约与配置一致性测试守护,变更时必须同步更新文档与测试。
Planner Projection Boundary
orchestrate-planner-projection.ts负责把SplitPlan + PlannerDecision投影成可渲染语义。orchestrate-view-model.ts仅负责组装 status/run 响应参数,不再承载 planner 语义推导核心逻辑。
Planner Boundary Matrix
orchestrate-planner-contract.ts仅允许 types + re-exports。orchestrate-planner-split-plan-contract.ts仅允许 normalize/validate/fail-fast/fallback split plan 逻辑。orchestrate-planner-projection.ts是 planner 语义唯一投影入口。orchestrate-view-model.ts只做响应参数编排。
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 139 lines · 27 tokens per session scan A 5b7ebe1c315e
planner-core is a skill published in the GitHub repository Xwen0857/agent-orchestrator (2 stars, last pushed 5mo ago), licensed MIT. It adds 27 tokens to every session and 1,903 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
meeting-note-summarizer
Turn meeting notes or transcripts into factual summaries, decisions, questions, and action items. Use when a user wants a concise recap or needs explicit owners and deadlines extracted without filling in missing details.
anysearch
Real-time search engine supporting web search, vertical domain search, parallel batch search, and URL content extraction.
daily-standup-journal
Generate concise daily standups, reflection prompts, and weekly retrospectives for individuals or teams. Use for planning a day, surfacing blockers, reviewing user-provided entries, or drafting a check-in without assuming prior history.
decision-matrix
Compare options with weighted scoring, pros and cons, pre-mortems, opportunity costs, and ICE prioritization. Use when a user wants to reason through a choice, expose assumptions, or rank alternatives.
dev-workflow
The complete development workflow for SkillHub contributors including local dev, staging validation, testing, and PR creation. Ensures agents follow the correct sequence of steps.
study-strategy-selector
Recommend practical study strategies matched to the material, learning goal, assessment, time, and learner constraints. Use for revision planning, homework routines, independent study, replacing ineffective habits, or adapting recall, spacing, explanation, and practice activities.