Borrowing it
Nothing to install: this file belongs to asasugar/SuperSpec. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/asasugar/SuperSpec/master/.cursor/commands/ss-specs.mdgit clone --depth 1 https://github.com/asasugar/SuperSpecWrote 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/asasugar/superspec/ss-specs)<a href="https://agentmods.dev/commands/asasugar/superspec/ss-specs"><img src="https://agentmods.dev/badge/commands/asasugar/superspec/ss-specs/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/asasugar/superspec/ss-specs"><img src="https://agentmods.dev/badge/commands/asasugar/superspec/ss-specs.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 | $0.00014 | $0.00442 |
| Opus 5.5 | $0.00006 | $0.00177 |
| Sonnet 5.5 | $0.00003 | $0.00088 |
| Haiku 4.5 | $0.00001 | $0.00044 |
Grade A, and why
/ss-specs 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
Purpose When spec.md may exceed 300 lines due to multiple independent capability domains, split into capability-specific spec files.
When to Split
- Change spans multiple system modules (e.g., auth + API + UI)
- Single spec.md expected to exceed 300 lines
- Need parallel development of independent capabilities
When NOT to Split
- Single module change or spec.md < 200 lines
- Capabilities are tightly coupled
- Rapid prototyping or experimental changes
Capability Domain Types
auth (authentication/authorization) · api (REST/GraphQL) · ui (frontend) · data (models/schema) · workflow (business processes) · integration (external systems) · infra (deployment)
Spec Template
---
name: <name>-<capability>
status: draft
strategy: {{strategy}}
depends_on: []
capability: <capability-name>
---
# Spec: <name> - <Capability>
## Capability Scope
## User Stories
### US-<capability>-1: [Title]
## Functional Requirements
### FR-<capability>-1: [Title]
## Cross-Capability Dependencies
- Depends on `auth/spec.md` FR-auth-2
- Provides API-1 for `ui/spec.md`
## Edge Cases
ID Convention: US-<cap>-<n>, FR-<cap>-<n>, AC-<cap>-<n>.<sub>
Steps
- Identify 2-5 independent capability domains in proposal.md
- Create
specs/<capability>/spec.mdfor each, using template above - Document splitting rationale in design.md
- Group tasks by capability in tasks.md
- Validate: clear boundaries, explicit dependencies, each spec < 300 lines, IDs follow convention
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 · 55 lines · 14 tokens per session scan A 4ea67bad3a3e
/ss-specs is a command published in the GitHub repository asasugar/SuperSpec (18 stars, last pushed 7mo ago), licensed MIT. It adds 14 tokens to every session and 442 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
CHANGELOG
All notable changes to the @mstar-harness/commands package are documented in this file.
feature-00c-resume
Retoma execucao feature-00c pausada por bloqueio humano ou schedule entre ondas. Valida hash (FR-014 + FR-PRE-004), aplica resposta a bloqueios, delega proxima onda ao agente-00c-feature-orchestrator.
iteration-loop
Run a whole iteration Phase 1→6 autonomously — code-first direction lock with a retained prototype, then execute → close → PR → merge-ready → post-merge close. Optional direction hint and scale S|M|L|XL; explicit autonomous opt-in, no grill-me, no routine confirmation.
amazing-e2e-check
Run explicitly requested E2E, browser, device, or installed-deployment scenarios in an independent verification workflow.
OPSX: Continue
Continue working on a change - create the next artifact (Experimental).
reverse-spec
A command for reverse specification: examining an existing project and producing documentation that describes its behavior and design.