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-auto)<a href="https://agentmods.dev/commands/alisunstar/opensunstar/backfill-auto"><img src="https://agentmods.dev/badge/commands/alisunstar/opensunstar/backfill-auto/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-auto"><img src="https://agentmods.dev/badge/commands/alisunstar/opensunstar/backfill-auto.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 | $0.00568 |
| Opus 5.5 | $0.00000 | $0.00227 |
| Sonnet 5.5 | $0.00000 | $0.00114 |
| Haiku 4.5 | $0.00000 | $0.00057 |
Grade A, and why
backfill-auto 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-auto — 回补生成器适配器（外置）
知识×RD 连接适配器：读取本 change 的过程资产（REVIEW.md / IMPLEMENTATION-CHECK.md / .specs/LESSONS.md），自动产出回补候选写入 wiki 候选管道。核心只承接候选（发现/导入/lint/验收），生成智能在外侧（K1/K2）。
先读规则
- 读
.specs/<change-id>/REVIEW.md、IMPLEMENTATION-CHECK.md、.specs/LESSONS.md - 读 knowledge/KNOWLEDGE-RULES.md 与 wiki SCHEMA（候选页格式）
- 只提取“稳定结论”：被证据支撑、与单次需求解耦、可复用的业务/技术事实
执行
- 从对账 changed/blocked 的裁决记录、REVIEW 的 4R 发现、LESSONS 的失败记录中抽取稳定结论；
- 每条结论标：证据（产物路径+条目）、目标页类型（runbook/decision/flow）、confidence；
- 一次性需求特例、未裁决推断一律剔除；
- 写候选目录（generator-adapter 协议）：
.opensunstar/wiki/candidates/rd-backfill-auto-<YYYYMMDD>/ ├── candidate.json # engine: "rd-backfill-auto", source_commit, created_at └── wiki/ ├── index.md └── runbooks/<page>.md # wiki schema frontmatter - 不直写正式 wiki/，不宣称已同步（控制面专属权力）。
何时停止
- 三类过程资产均缺失 → 停止，提示先跑 /rd:validate 与 /rd:backfill（人工版）。
- 无可复用稳定结论 → 产出空索引候选并说明理由，不凑数。
人工确认
是 — 候选经 GUI 验收导入后才建基线；comparable=false 时不下优劣结论。
与 /rd:backfill 的关系
- /rd:backfill = 人工版（人主导列清单）；本命令 = 自动版（Agent 起草）；
- 两者产物同管道同门禁，可并存对照（同 commit 质量对照机制既有）。
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 · 39 lines · 0 tokens per session scan A e4a72c47d9ca
backfill-auto 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 568 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
template
Manage issue templates for streamlined issue creation.
speckit.opsmill.retrospect
Run a session retrospective that surfaces context-management gaps and routes them to approved follow-up actions.
create-issue
Transform feature descriptions, bug reports, or improvement ideas into well-structured GitHub issues.
pr
Handle the full workflow from current branch state to an open, CI-monitored pull request.
mach12:gh-pr-read
Read a GitHub pull request's title, body, and all top-level PR conversation comments; optionally locate an HTML-marker comment.
scramjet:troubleshoot
Diagnose unexpected command behavior and recommend safe resolution.