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 nexus-research-lab/nexus --skill goal-managergit clone --depth 1 https://github.com/nexus-research-lab/nexusWrote 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/nexus-research-lab/nexus/goal-manager)<a href="https://agentmods.dev/skills/nexus-research-lab/nexus/goal-manager"><img src="https://agentmods.dev/badge/skills/nexus-research-lab/nexus/goal-manager/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/nexus-research-lab/nexus/goal-manager"><img src="https://agentmods.dev/badge/skills/nexus-research-lab/nexus/goal-manager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00055 | $0.00918 |
| Opus 5 | $0.00028 | $0.00459 |
| Sonnet 5 | $0.00011 | $0.00184 |
| Haiku 4.5 | $0.00006 | $0.00092 |
Grade A, and why
goal-manager 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 today.
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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Goal Manager
Goal 是跨物理 round 持续追求的服务端目标,不是普通聊天、Task、WorkGraph 或 Automation 的别名。Objective 说明最终要实现什么;Execution 另行记录责任如何交付。
入口与命令协议
-
先通过
nexus.command读取当前 Goal:{"domain":"goal","action":"inspect"}get_goal是固定入口的语义名:inspect 省略operation,无需request_id,不能通过 invoke 调用。误用时按返回 JSON 纠正,不补参数重试原调用或等待注册。不要使用 shell、临时文件或/goal文本代替 command。 -
读取最新 Goal/objective revision 与 completion criteria 后选择 operation;mutation 前读取 fresh exact contract:
{"domain":"goal","action":"contract","operation":"<operation>"}完整遵守返回的 contract。
-
业务输入是
additionalProperties=false的 closed object,直接放在工具的input字段中,只写 fresh schema 暴露的业务字段。不要提交 Goal/owner/Agent/Session/Room/round identity、authority、revision、receipt 或其他隐藏字段。 -
相同语义重试复用 request ID;operation、目标或输入变化时生成新 ID。只有顶层
is_error=false且data.outcome=applied表示状态已改变;nextAction只给 domain-qualified 恢复方向,不携带新 authority,继续前仍读取目标 domain 的 current state 与 exact contract。
按当前动作读取参考
inspect为空且有显式 Goal 意图,或用户明确替换 current objective:references/create-and-retarget.md- 判断 Goal complete/blocked,提交 Goal Objective Alignment,或处理完成拒绝:references/complete-and-block.md
- shared Room Goal 的 Lead、协作与关闭条件:references/room-goals.md
只读取当前动作需要的参考;operation 字段、枚举和长度始终以 fresh exact contract 为准。
暂停与恢复
当 current Goal 为 paused 时,恢复动作由用户执行。请明确告知用户:在当前对话输入框上方的 Goal 状态栏中,点击右侧的 ▶「继续」按钮。
用户点击「继续」后,Nexus 会自动重新调度该 Goal,无需再发一条消息。新的 Goal continuation 负责继续审计和收尾,并在满足完成条件后标记 Goal 完成。
不变量
- 创建前 objective 必须完整、具体、execution-ready;仍缺少会实质改变结果的信息时先取得最少必要输入,不创建占位 Goal。
- current Goal 存在时不创建第二个。用户明确纠正 objective 时 retarget 同一 Goal,保留 identity 与累计用量。
token_budget只在用户明确给出正数预算时设置;暂停、恢复、预算和用量限制属于用户或系统控制面。- Plan Mode 中 Goal mutation 只做 validation,不改变 Goal、Execution、Plan 或 cancellation state;需要持久化时离开 Plan Mode,重新读取 current state 与 exact contract 后再 invoke。
update_goal只标记complete|blocked,不创建、retarget、暂停或改预算。complete 只在 objective 真实满足且没有 required work 时使用;blocked 必须满足连续三次同一 blocker 的模型行为门槛。- 提醒、定时与周期任务使用 Automation;WorkGraph 责任使用
execution-orchestrator。 goal/audit_objective_alignment是 confirmed Goal+WorkGraph 的完成审计;execution/audit_execution_alignment只是非终态 Execution Gate,不能互换。
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- today Changed a7e14574768d
- 6d ago Changed · +6 lines 659360443d43
- 11d ago First seen · 46 lines · 55 tokens per session scan A 2d4e8e3dc88d
goal-manager is a skill published in the GitHub repository nexus-research-lab/nexus (145 stars, last pushed today), licensed Apache-2.0. It adds 55 tokens to every session and 918 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
harness-creator
Build, audit, and improve harnesses that make AI coding agents reliable: AGENTS.md/CLAUDE.md instruction files, feature/state tracking, verification gates, scope boundaries, session handoff, memory persistence, context budgets, tool-permission safety, and multi-agent coordination. Use this whenever a coding agent is…
agent-optimization
Improve an Agent State through versioned scores and score-linked Traces from a frozen Benchmark.
agent-evaluation
Run one specified Test Agent on one specified Benchmark Case exactly once, privately score that execution, and return one protocol result.
data-analysis
Complete data-analysis tasks with bounded inspection, correct data semantics, native artifact handling, complete delivery, and risk-based verification.
ceo-setup
One-time onboarding for the executive/manager commitment workflow — delegation-heavy, meeting prep, decision capture, morning and evening digests. Creates a commitments project and installs two dashboard widgets. After successful setup this skill is excluded from selection until the marker file is deleted.
developer-setup
One-time onboarding for the developer workflow — installs github-workflow missions, creates the commitments workspace, registers per-repo projects, writes calibration memories. After successful setup this skill is excluded from selection until the marker file is deleted.