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/cakemail/cakemail-api-documentation-mcpWrote 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/cakemail/cakemail-api-documentation-mcp/create-brownfield-story)<a href="https://agentmods.dev/commands/cakemail/cakemail-api-documentation-mcp/create-brownfield-story"><img src="https://agentmods.dev/badge/commands/cakemail/cakemail-api-documentation-mcp/create-brownfield-story/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/cakemail/cakemail-api-documentation-mcp/create-brownfield-story"><img src="https://agentmods.dev/badge/commands/cakemail/cakemail-api-documentation-mcp/create-brownfield-story.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 | $0.00000 | $0.02010 |
| Opus 5 | $0.00000 | $0.01005 |
| Sonnet 5 | $0.00000 | $0.00402 |
| Haiku 4.5 | $0.00000 | $0.00201 |
Grade C, and why
create-brownfield-story scanned grade C with 1 finding 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 8d 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- Context: Brownfield enhancement to {{existing system}} --> This is a copy
95% identical to create-brownfield-story — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 319 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/create-brownfield-story Task
When this command is used, execute the following task:
Create Brownfield Story Task
Purpose
Create detailed, implementation-ready stories for brownfield projects where traditional sharded PRD/architecture documents may not exist. This task bridges the gap between various documentation formats (document-project output, brownfield PRDs, epics, or user documentation) and executable stories for the Dev agent.
When to Use This Task
Use this task when:
- Working on brownfield projects with non-standard documentation
- Stories need to be created from document-project output
- Working from brownfield epics without full PRD/architecture
- Existing project documentation doesn't follow BMad v4+ structure
- Need to gather additional context from user during story creation
Use create-next-story when:
- Working with properly sharded PRD and v4 architecture documents
- Following standard greenfield or well-documented brownfield workflow
- All technical context is available in structured format
Task Execution Instructions
0. Documentation Context
Check for available documentation in this order:
-
Sharded PRD/Architecture (docs/prd/, docs/architecture/)
- If found, recommend using create-next-story task instead
-
Brownfield Architecture Document (docs/brownfield-architecture.md or similar)
- Created by document-project task
- Contains actual system state, technical debt, workarounds
-
Brownfield PRD (docs/prd.md)
- May contain embedded technical details
-
Epic Files (docs/epics/ or similar)
- Created by brownfield-create-epic task
-
User-Provided Documentation
- Ask user to specify location and format
1. Story Identification and Context Gathering
1.1 Identify Story Source
Based on available documentation:
- From Brownfield PRD: Extract stories from epic sections
- From Epic Files: Read epic definition and story list
- From User Direction: Ask user which specific enhancement to implement
- No Clear Source: Work with user to define the story scope
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.
- 8d ago First seen · 319 lines · 0 tokens per session scan C 948f078b588e
create-brownfield-story is a command published in the GitHub repository cakemail/cakemail-api-documentation-mcp (0 stars, last pushed 11mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,010 tokens. A static security scan graded it C with 1 finding (hidden instructions). It is 95% identical to create-brownfield-story, differing in 2 lines, and is treated as a copy.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.