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 commands/asasugar/superspec/ss-creategit clone --depth 1 https://github.com/asasugar/SuperSpecWhat 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 | $0.00027 | $0.01813 |
| Opus 5 | $0.00014 | $0.00907 |
| Sonnet 5 | $0.00005 | $0.00363 |
| Haiku 4.5 | $0.00003 | $0.00181 |
Grade A, and why
/ss-create 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 3d 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User Input
$ARGUMENTS
You MUST consider the user input before proceeding (if not empty).
Outline
The text the user typed after /ss-create is the feature description. Do not ask the user to repeat it unless they provided an empty command.
Guardrails
- Read
superspec.config.jsonfirst → getlang,specDir,boost,strategy,context,branchPrefix,branchTemplate,changeNameTemplate - Pre-task review (refer to AGENTS.md "Before ANY Task"):
- Read
contextfiles, README, architecture docs - Inspect
{specDir}/changes/→ avoid duplicate changes viadepends_on
- Read
- Never create change folders manually — use
superspec create <feature>CLI - Do not write any code during the proposal stage. Only create design documents
Input Parsing Rules
From user input, extract: mode flags, feature name, intent type, developer, lang.
| Extract | Rule | Example |
|---|---|---|
| Mode flags | Detect -b/--boost/boost → boost mode; -c/--creative/creative → creative mode; --no-branch → skip branch; flags can be combined |
/ss-create -b add auth → boost; /ss-create -b -c refactor login → boost+creative |
| Feature name | Remove flags from input, convert remainder to camelCase. Chinese → translate to English first | "add user auth" → addUserAuth; "添加用户认证" → addUserAuth |
| Intent type | Semantic inference from input | add/new/implement → feature; fix/bug/hotfix → hotfix; refactor/optimize → refactor; docs → docs; test → test; build/deps → chore; default → feature |
| Developer | "@username" or "Developer: xxx" → extract (remove "@"). Fallback: git user name | "添加todolist @jay" → user=jay |
| Lang | CJK chars → zh; explicit "zh"/"中文" → zh; "en"/"English" → en; fallback: config lang |
"添加todolist" → zh |
Naming Templates
Config supports custom templates with variables {date}, {feature}, {user}, {intentType}, {prefix}:
branchTemplate(default:{intentType}-{date}-{feature}-{user})changeNameTemplate(default:{intentType}-{date}-{feature}-{user})
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.
- 3d ago First seen · 129 lines · 27 tokens per session scan A bc4338c5501a
/ss-create is a command published in the GitHub repository asasugar/SuperSpec (15 stars, last pushed 5mo ago), licensed MIT. It adds 27 tokens to every session and 1,813 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
OPSX: Archive
Archive a completed change in the experimental workflow.
iteration-loop
Autonomous full iteration loop for cloud agents — Phase 1 (code-first auto direction lock + compass/plans + Review & Edit chain) through Phase 2–5 (execute → close → PR → merge-ready). Optional args: direction, scale (S|M|L|XL, default M). Not Done until Phase 5 exit checklist passes. Minimal human intervention; no…
codebase-audit
Survey a codebase as a senior advisor and produce prioritized, self-contained improvement plans. Read-only on source code. Use standalone before iteration-start to discover what's worth doing, or independently to build a prioritized backlog.
review-code
将所选变更作为严格缺陷门禁进行审查，或使用 --audit 审计路径.
implement-tasks
执行实现任务，支持条件 TDD 工作流（代码使用 TDD，文档/配置直接实现）.
pr
基于 git diff 和可选的 spec.md 集成生成结构化的 Pull Request (GitHub) 或 Merge Request (GitLab) 描述.