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/marcusgoll/spec-flow/creategit clone --depth 1 https://github.com/marcusgoll/Spec-FlowWhat 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 | $0.00018 | $0.01539 |
| Opus 5 | $0.00009 | $0.00770 |
| Sonnet 5 | $0.00004 | $0.00308 |
| Haiku 4.5 | $0.00002 | $0.00154 |
Grade A, and why
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 yesterday.
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 — 282 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/create — Consolidated Creation Command
/create prompt <desc>→ Generate optimized Claude prompts/create command <desc>→ Create new slash command with best practices/create agent <desc>→ Create specialized subagent configuration/create skill <desc>→ Create agent skill with progressive disclosure/create hook→ Create event-driven hook
All creation commands provide expert guidance on structure, best practices, and validation.
Step 1: Parse Type Argument
Extract first argument as type:
$type = first word of $ARGUMENTS
$remaining = rest of $ARGUMENTS
If no type provided: Use AskUserQuestion to ask:
{
"question": "What would you like to create?",
"header": "Extension Type",
"multiSelect": false,
"options": [
{
"label": "prompt",
"description": "Optimized Claude prompt with XML structure"
},
{
"label": "command",
"description": "New slash command following best practices"
},
{
"label": "agent",
"description": "Specialized subagent configuration"
},
{
"label": "skill",
"description": "Agent skill file with progressive disclosure"
},
{
"label": "hook",
"description": "Event-driven hook for tool/session events"
}
]
}
Step 2: Invoke Appropriate Skill
<when_argument_is value="prompt">
Create Prompt
Purpose: Generate optimized, XML-structured prompts with intelligent depth selection.
Invoke skill:
Skill: create-meta-prompts
Pass remaining arguments to skill for prompt generation.
What the skill provides:
- XML-structured prompt templates
- Intelligent depth selection (quick/standard/comprehensive)
- Context engineering best practices
- Progressive disclosure patterns
- Example outputs and validation
</when_argument_is>
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.
- yesterday First seen · 282 lines · 0 tokens per session scan A e6bd1128aba1
create is a command published in the GitHub repository marcusgoll/Spec-Flow (91 stars, last pushed 4mo ago), licensed MIT. It adds 18 tokens to every session and 1,539 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
quick-fix
Fast-track workflow for small bug fixes.
review
Review the current diff for violations of the conventions in AGENTS.md and .cursor/rules/. Report findings ordered by severity; do not fix anything unless asked.
usage-add
PitWay: Accumulate measured planning or qa token usage onto a milestone.
pi-code-review
Adversarial code review via Codex — break confidence in changes, not validate them.
milestone-list
PitWay: List every milestone with a concise one-line status.
setup
Install the claude-pace statusline bundled with this plugin.