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 keepergit 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/keeper)<a href="https://agentmods.dev/skills/xwen0857/agent-orchestrator/keeper"><img src="https://agentmods.dev/badge/skills/xwen0857/agent-orchestrator/keeper/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/keeper"><img src="https://agentmods.dev/badge/skills/xwen0857/agent-orchestrator/keeper.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 | $0.00040 | $0.00601 |
| Opus 5.5 | $0.00016 | $0.00240 |
| Sonnet 5.5 | $0.00008 | $0.00120 |
| Haiku 4.5 | $0.00004 | $0.00060 |
Grade A, and why
keeper 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 1mo 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.
What it actually says
Keeper
核心职责
- 维护知识库质量：发现重复、候选合并、条目降级与归档建议。
- 维护经验权重：基于反馈日志重算
score/status，同步治理信号。 - 维护容量边界：控制低价值条目膨胀，输出清理与拆分建议。
- 维护审计可见性：生成 keeper 报告，供 orchestrator 读取与决策。
启用开关（强约束）
templates/coordination/planner/config/current.md中keeper_enabled: true才允许执行。- 当
keeper_enabled: false时，keeper 必须 no-op 并返回禁用状态。
输入路径
knowledge-base/entriesknowledge-base/feedback/kb_feedback.ndjsonknowledge-base/references/weighting-model.mdtemplates/coordination/planner/config/current.mdtemplates/coordination/planner/properties.md
输出路径
templates/coordination/orchestrator/keeper-report.mdtemplates/coordination/orchestrator/keeper-report.json
运行脚本
keeper/scripts/keeper_run.shkeeper/scripts/keeper_ingest_candidates.shkeeper/scripts/kb_semantic_dedupe.pykeeper/scripts/keeper_scheduler.shscripts/run_keeper.sh
最小执行流程
- 读取开关与参数；若禁用则直接退出。
- 先消费
knowledge-base/inbox/pending候选并执行去重整并/入库。 - 执行 KB 分数重算：
agent-orchestrator/scripts/kb_recompute_scores.sh。 - 统计条目状态分布、低分条目、疑似重复条目。
- 输出 keeper 报告，供 orchestrator 汇总。
去重与整并规则（V1）
- 使用
kb_semantic_dedupe.py计算相似度，超过阈值（默认0.85）进入merge_candidates。 status=DEPRECATED且 30 天无命中，进入archive_candidates。HUMAN_OVERRIDE连续上升条目进入watch_candidates。- keeper 报告输出
split_candidates与 7 天趋势指标，用于收敛拆分/归档策略。
What ships with it
6 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.
- 1mo ago First seen · 48 lines · 40 tokens per session scan A 7681f87ba403
keeper is a skill published in the GitHub repository Xwen0857/agent-orchestrator (2 stars, last pushed 7mo ago), licensed MIT. It adds 40 tokens to every session and 601 once invoked, about $0.0002 per session on Opus 5.5. 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
lesson
Store a lesson learned from the current conversation. Triggered by /lesson command. Use when Master signals that the recent conversation contains a pitfall, fix, or key insight that should be persisted to long-term memory.
harness-24h
A production-grade framework for long-running, autonomous agents based on Harness Engineering principles. Features three-layer self-healing memory, circuit breaker protection, KAIROS dream-mode consolidation, and multi-agent coordination. When a user describes a task idea, Agent automatically initializes the…
init
A project-memory setup workflow for long-running coding work, creating a .workflow directory with status and review files.
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.
sandbase
Access 2,000+ AI models and API tools through one MCP interface for inference, media generation, search, scraping, embeddings, social data, and structured retrieval. Use sandbasediscover before building custom integrations or declaring external data inaccessible; prefer an existing dedicated tool or API key when the…
retrieval-practice-generator
Generate low-stakes retrieval-practice questions with grounded answer notes and implementation guidance. Use for quiz starters, revision activities, delayed recall, misconception checks, or adapting recall difficulty.