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 WackyGem/Fleur --skill fleur-dagster-backfill-runbookgit clone --depth 1 https://github.com/WackyGem/FleurWrote 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/wackygem/fleur/fleur-dagster-backfill-runbook)<a href="https://agentmods.dev/skills/wackygem/fleur/fleur-dagster-backfill-runbook"><img src="https://agentmods.dev/badge/skills/wackygem/fleur/fleur-dagster-backfill-runbook/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/wackygem/fleur/fleur-dagster-backfill-runbook"><img src="https://agentmods.dev/badge/skills/wackygem/fleur/fleur-dagster-backfill-runbook.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 | $0.00046 | $0.02745 |
| Opus 5.5 | $0.00018 | $0.01098 |
| Sonnet 5.5 | $0.00009 | $0.00549 |
| Haiku 4.5 | $0.00005 | $0.00275 |
Grade A, and why
fleur-dagster-backfill-runbook 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 28d 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 — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DG 回填手册
当 pipeline/scheduler 里的回填可以用 dg launch 表达时,使用这个 skill。
规则
- 所有
dg/dagster命令必须使用根目录.env中的DAGSTER_HOME作为 Dagster home - 执行前先在仓库根目录加载
.env:set -a; . ./.env; set +a - 运行回填前先执行
make dagster-home,确保 Dagster home 和 pool 限制已初始化 - 在
pipeline/下执行命令 - 使用
uv run dg ... - 通过
--target-path scheduler指向 scheduler 项目 - 临时回填优先用明确的 asset selection
- 只有当 job 和目标工作负载完全一致时才用 job
流程
- Source 到 ClickHouse raw 的手动修复优先使用统一 raw-only 入口
backfill__fetch_history_sources_to_raw_job。 - Snapshot reference data 也使用
backfill__fetch_history_sources_to_raw_job;start_date和end_date仍必填,但该 scope 会主动忽略日期。 - 历史 source/raw 修复后需要继续推进 dbt、Furnace 和 marts 时,使用
backfill__fetch_history_sources_to_marts_job。 - 日常 source/raw/downstream 主入口使用
daily__fetch_history_sources_to_marts_schedule_job;它不是 history backfill,但复用 source-to-marts registry,把target_date映射为单日增量。 - Jiuyan 异动、行业列表、图片/OCR/OCR snapshot 后续单独设计 job;不纳入本轮统一 source-to-marts 回填模板或 daily source-to-marts 入口。
- 只有调试单个资产、验证单个分区或统一入口暂不覆盖的临时操作,才使用精确 asset selection。
- 判断目标是否分区。
- 从 references/backfill-matrix.md 里选命令模板。
- 需要时先用
uv run dg list defs --target-path scheduler --json验证选择。 - 先跑
dry_run: true,确认计划后再执行真实回填或真实 daily run。
统一 Source/Raw 回填入口
raw-only 首选手动入口:
cd pipeline
uv run dg launch --target-path scheduler \
--job backfill__fetch_history_sources_to_raw_job \
--config-json '{
"ops": {
"backfill__fetch_history_sources_to_raw_controller": {
"config": {
"target_scope": "baostock_daily_kline",
"start_date": "2026-01-01",
"end_date": "2026-06-30",
"execution_mode": "full",
"refresh_prerequisite_snapshots": false,
"overwrite_source_partitions": false,
"dry_run": true
}
}
}
}'
raw-only target_scope:
baostock_daily_klinemarket_events(只纳入 THS limit up pool;Jiuyan 异动不进入统一 raw-only 或 source-to-marts 入口)eastmoney_f10chinabondsnapshot_reference_data(日期字段必填,但该 scope 忽略日期)all_raw_yearly
What ships with it
2 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.
- 28d ago Changed 40ed8cd6172f
- 2mo ago First seen · 241 lines · 46 tokens per session scan A 868f814f0619
fleur-dagster-backfill-runbook is a skill published in the GitHub repository WackyGem/Fleur (142 stars, last pushed 28d ago), licensed MIT. It adds 46 tokens to every session and 2,745 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 2026-08-30.
fleur-dagster-backfill-runbook compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| fleur-dagster-backfill-runbookWackyGem/Fleur | Skill | 142 | 28d ago | MIT | A | 46 | Codex |
| agent-platform-model-registrygoogle/skills | Skill | 22k | yesterday | Apache-2.0 | A | 60 | Claude Code, Codex |
| foundry-config-setupmicrosoft/agent-framework | Skill | 15k | yesterday | MIT | A | 65 | Claude Code, Codex |
| google-cloud-solution-agentic-analytics-spark-knowledge-cataloggoogle/skills | Skill | 22k | yesterday | Apache-2.0 | A | 132 | Claude Code, Codex |
| training-checkwanshuiyin/Auto-claude-code-research-in-sleep | Skill | 19k | 3d ago | MIT | A | 35 | Claude Code |
| nemo-automodel-launcher-configNVIDIA/skills | Skill | 3.9k | yesterday | Apache-2.0 | A | 30 | Claude Code |
| finetuningmicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 132 | Claude Code |