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.
git clone --depth 1 https://github.com/alisunstar/OpenSunstarWrote 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/commands/alisunstar/opensunstar/backfill)<a href="https://agentmods.dev/commands/alisunstar/opensunstar/backfill"><img src="https://agentmods.dev/badge/commands/alisunstar/opensunstar/backfill/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/commands/alisunstar/opensunstar/backfill"><img src="https://agentmods.dev/badge/commands/alisunstar/opensunstar/backfill.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 | $0.00000 | $0.00450 |
| Opus 5.5 | $0.00000 | $0.00180 |
| Sonnet 5.5 | $0.00000 | $0.00090 |
| Haiku 4.5 | $0.00000 | $0.00045 |
Grade A, and why
backfill 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
/rd:backfill — 知识回补
阶段 7：把本次需求过程中产生的新知识回补到知识库候选区，闭环最后一环。
先读规则
- 读
.specs/<change-id>/IMPLEMENTATION-CHECK.md（对账结果，识别新知识） - 读
knowledge/KNOWLEDGE-RULES.md（回补约定） - 读
knowledge/candidate/（现有候选，避免重复）
执行
- 识别本次需求产生的新知识（业务理解、技术决策、踩坑经验、模板更新）
- 每条知识标 source=evidence/confidence，写入候选清单
- 候选内容写入
knowledge/candidate/目录（经候选管道）
回补路径
本命令产 KNOWLEDGE-BACKFILL.md
→ 候选写入 .opensunstar/wiki/candidates/
→ GUI 验收导入候选到正式 wiki
→ 建立知识基线（baseline synced）
→ 下一需求 ROUTING 命中已回补知识
何时澄清
- 候选与现有正式知识冲突 → 暂停，等 owner 裁决
何时停止
- 无新知识可回补 → 正常结束（不是所有需求都产回补）
产物
.specs/<change-id>/KNOWLEDGE-BACKFILL.md（回补候选清单 + 内容）knowledge/candidate/{candidate-id}.md（候选文件，标 sourceType=backfill）
人工确认
是 — 产出回补候选后暂停，等 GUI 验收导入后建立基线。
闭环意义
回补是三层资产闭环的最后一环——RD 过程产出的知识回补到 wiki，wiki 的 ROUTING 又指导下一轮 RD，形成复利。
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 · 47 lines · 0 tokens per session scan A 12e4a015514d
backfill is a command published in the GitHub repository alisunstar/OpenSunstar (31 stars, last pushed 14d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 450 tokens. 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 commands, from other repositories
import
Import issues and memories from JSONL.
lavra-learn
Curate raw knowledge comments into structured, well-tagged entries for future auto-recall.
lavra-recall
Search knowledge base mid-session and inject relevant context.
lavra-checkpoint
Save session progress by filing beads, capturing knowledge, and syncing state.
speckit.archive
Archive a feature specification into main project memory after merge, resolving gaps and conflicts.
save-memory
You are saving what you learned this session into the megamemory knowledge graph. This is YOUR memory — record anything valuable for future sessions: what you understood about the project, what you built, decisions that were made, patterns you noticed, or intent the user shared.