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/sdsrss/gsd-liteWrote 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/sdsrss/gsd-lite/status)<a href="https://agentmods.dev/commands/sdsrss/gsd-lite/status"><img src="https://agentmods.dev/badge/commands/sdsrss/gsd-lite/status/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/sdsrss/gsd-lite/status"><img src="https://agentmods.dev/badge/commands/sdsrss/gsd-lite/status.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 | $0.00009 | $0.00902 |
| Opus 5.5 | $0.00004 | $0.00361 |
| Sonnet 5.5 | $0.00002 | $0.00180 |
| Haiku 4.5 | $0.00001 | $0.00090 |
Grade A, and why
status 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 5d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
STEP 1: 读取状态
读取 .gsd/state.json:
- 如果文件不存在 → 告知用户 "未找到 GSD 项目状态，请先运行 /gsd:start 或 /gsd:prd"，停止
- 如果文件损坏 → 告知用户并停止
STEP 2: 展示进度面板
从 canonical fields 实时推导所有展示数据 (不使用任何 derived/cached 值):
项目概览
项目: {project}
工作流模式: {workflow_mode}
计划版本: {plan_version}
总体进度
- 从
phases数组推导:- 总 phase 数:
total_phases - 已完成 phase 数: lifecycle=accepted 的 phase 数量
- 总 task 数: 所有 phase 的
tasks之和 - 已完成 task 数: 所有 phase 的
done之和 - 进度百分比:
已完成 task / 总 task * 100
- 总 phase 数:
进度: ████████░░░░ {done}/{total} tasks ({percentage}%)
阶段: {completed_phases}/{total_phases} phases
各阶段状态
遍历 phases 数组，展示每个 phase:
Phase {id}: {name}
状态: {lifecycle}
任务: {done}/{tasks}
审查: {phase_review.status} (如有)
交接: {phase_handoff 各项状态}
当前活跃任务
- 从
current_phase+current_task推导:
当前任务: {current_task} — {task_name}
任务状态: {task.lifecycle}
审查级别: {task.level}
重试次数: {task.retry_count}
审查状态
- 如果
current_review存在:
审查中: {current_review.scope} — {current_review.scope_id}
审查阶段: {current_review.stage}
Blocked 摘要
- 遍历当前 phase 的 todo，找出 lifecycle=blocked 的 task:
Blocked 任务:
- {task_id}: {blocked_reason}
解除条件: {unblock_condition}
如无 blocked task → 不显示此段
下一步操作建议
根据 workflow_mode 推导:
| workflow_mode | 建议 |
|---|---|
| planning | "正在修订计划：用 state-patch 改计划，改完把 workflow_mode 设回 executing_task 再 /gsd:resume" |
| executing_task | "自动执行中，等待完成" |
| reviewing_task | "L2 审查进行中" |
| reviewing_phase | "L1 阶段审查进行中" |
| awaiting_clear | "请执行 /clear 然后 /gsd:resume 继续" |
| awaiting_user | "有 blocked 问题需要用户决策，运行 /gsd:resume 查看详情" |
| paused_by_user | "已暂停，运行 /gsd:resume 继续" |
| reconcile_workspace | "工作区不一致，运行 /gsd:resume 进行 reconcile" |
| replan_required | "计划需要更新，运行 /gsd:resume 查看详情" |
| research_refresh_needed | "研究已过期，运行 /gsd:resume 刷新" |
| completed | "项目已完成" |
| failed | "项目执行失败，运行 /gsd:resume 查看详情" |
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.
- 5d ago Changed 951cb48f6b92
- 1mo ago First seen · 115 lines · 9 tokens per session scan A 90e1f425e7de
status is a command published in the GitHub repository sdsrss/gsd-lite (4 stars, last pushed 4d ago), licensed MIT. It adds 9 tokens to every session and 902 once invoked, about $0.0000 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 commands, from other repositories
create-plan
Writes an implementation plan as a file artifact in the task directory (.ork/tasks/TASK/NN-plan-SLUG.md) with phases, exact file changes and runnable success criteria, so reviewers comment on the file instead of in chat. Use when a task has its research done and needs a reviewable plan before code; pair with…
check-approvals
Check pending approvals and send reminders where overdue. "who still owes an approval".
save
Save current work state for next session. Creates/updates .planning/ files (CHECKPOINT.md, STATE.md, settings.json) so Heimdall resumes with full context. NOT a rewind — saves forward progress. Run before closing a session or at any milestone.
status
Show current Heimdall state — project phase, active agents, quality gates, conflicts.
create-ticket
Create a work-item ticket (GitHub issue / Jira) from an existing requirements.md, then promote its draft spec folder to docs/specs/ /.
finish-tasks
Finalize a work item after all tasks are done — cleanup (currently closing the ticket) and mark the work complete.