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 agentmods add skills/rubenzarroca/sdd-plugin/sdd-statusnpx skills add rubenzarroca/sdd-plugin --skill sdd-statusgit clone --depth 1 https://github.com/rubenzarroca/sdd-pluginWrote 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/rubenzarroca/sdd-plugin/sdd-status)<a href="https://agentmods.dev/skills/rubenzarroca/sdd-plugin/sdd-status"><img src="https://agentmods.dev/badge/skills/rubenzarroca/sdd-plugin/sdd-status.svg" alt="Measured on agentmods" 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 | $0.00064 | $0.00946 |
| Opus 5 | $0.00032 | $0.00473 |
| Sonnet 5 | $0.00013 | $0.00189 |
| Haiku 4.5 | $0.00006 | $0.00095 |
Grade A, and why
sdd-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 6d 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/sdd:status — Show SDD state and progress
You are a status reporter. Your only job is to read .sdd/state.json and present the current SDD state. Be fast and compact.
Read ONLY state.json. Do NOT read specs, plans, code, constitution, or any other file. This command must be ultra-lightweight.
Step 1: Read state
Read .sdd/state.json. If the file does not exist, report:
SDD not initialized. Run /sdd:init to set up.
And stop.
Step 2: Parse and present
From state.json, extract and display:
Case A: $ARGUMENTS contains a feature name
Show detailed status for that specific feature:
- Feature name + current state
- All tasks with their statuses (✓ completed, ▶ in_progress, ⏳ pending)
- Timestamps for completed tasks
- Dependencies between tasks
- Any validation alerts stored in the feature entry
If the feature does not exist in state.json, say so and list available features.
Case B: There is an active feature (active_feature is not null)
Present this format:
Project: {project}
Active: {feature-name} [{state}] — {completed}/{total} tasks completed
Last: {task-id} ✓ {task title}
Next: {task-id} ⏳ {task title}
Session notes: "{last_session_notes}"
- Omit "Session notes" line if
last_session_notesis null. - Omit "Last/Next" lines if the feature has no tasks (states before
tasked).
Workflow guidance: If completed_features is less than 3 (or missing) in state.json, append a brief orientation line after the status:
If completed_features < 2, include a one-line phase description before the next step:
Phase: {state} — {phase description}
→ Next step: /sdd:{next-command} {feature-name}
Phase descriptions (hardcoded — no file reads needed):
specified: "Spec written, ready for gap analysis"clarified: "Gaps resolved, ready for technical planning"planned: "Architecture decided, ready for task decomposition"tasked: "Tasks created, ready to start building"implementing: "Building in progress"validating: "All tasks done, ready for spec-vs-code verification"
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.
- 6d ago First seen · 128 lines · 64 tokens per session scan A 16ea0b20039c
sdd-status is a skill published in the GitHub repository rubenzarroca/sdd-plugin (6 stars, last pushed 6mo ago), licensed MIT. It adds 64 tokens to every session and 946 once invoked, about $0.0003 per session on Opus 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
review
Business review — weekly health check, monthly close, or ad-hoc audit. Subcommands: weekly, monthly, check. Use for periodic reviews or metrics assessment.
scheduler
Manage scheduled jobs — create, update, list, run remote agents on cron. Use when setting up recurring tasks, checking job status, or managing automation.
do
Alias for /brana:backlog start with freeform text. Routes to the best skill or creates a task. Use /brana:backlog start directly for the same behavior.
github-issue-triage
当用户要拉取并分析 GitHub 仓库的 open issues、给所有 issue 排优先级、产出 triage 报告,或要定期(配合 /schedule)巡检新 issue 时使用。按「数据正确性/崩溃 > 高价值&高呼声 > 体验 > 长尾」四级分流,结合社区呼声(👍/💬)与产品核心卖点相关度,可选结合代码库验证 bug 真实性,输出可维护的 .docs/issue-triage.md。触发关键词:"分析 github issue"、"issue 优先级 / triage"、"梳理 issues 排优先级"、"看下还有哪些有价值的需求或急需修的 bug"、"定期拉取 issue 分析"、"triage open…
backlog
Manage the backlog — plan, track, navigate phases and epics. Use when planning phases, viewing roadmaps, or restructuring work.
onboard
Scan and diagnose a project, or scaffold a new client from scratch. Works for code and venture clients. Auto-detects project type.