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 skills add terryso/claude-bmad-skills --skill bmad-epic-pipeline-worktreegit clone --depth 1 https://github.com/terryso/claude-bmad-skillsWrote 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/terryso/claude-bmad-skills/bmad-epic-pipeline-worktree)<a href="https://agentmods.dev/skills/terryso/claude-bmad-skills/bmad-epic-pipeline-worktree"><img src="https://agentmods.dev/badge/skills/terryso/claude-bmad-skills/bmad-epic-pipeline-worktree/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/skills/terryso/claude-bmad-skills/bmad-epic-pipeline-worktree"><img src="https://agentmods.dev/badge/skills/terryso/claude-bmad-skills/bmad-epic-pipeline-worktree.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 | $0.00020 | $0.01694 |
| Opus 5 | $0.00010 | $0.00847 |
| Sonnet 5 | $0.00004 | $0.00339 |
| Haiku 4.5 | $0.00002 | $0.00169 |
Grade A, and why
bmad-epic-pipeline-worktree 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 10d 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 — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BMAD Epic Pipeline (Worktree Edition)
Deliver all incomplete user stories in Epic {ARGUMENT} using configurable pipeline, each story developed in isolated worktree and merged only after tests pass.
Pre-step: Determine Epic Number
If no epic number is provided ({ARGUMENT} is empty):
- Read
_bmad-output/implementation-artifacts/sprint-status.yaml(ordocs/sprint/sprint-status.yaml) - Find all stories with status not
done(format:X-Y-story-name) - Extract Epic numbers X from these stories
- Select the smallest Epic number as
{ARGUMENT} - Output:
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
📌 Auto-selected Epic: {ARGUMENT} (has incomplete stories)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Example:
- Status file has
3-2-llm-prompt-template: backlog,3-3-xxx: in-progress,4-1-xxx: done - Incomplete Epics: 3
- Auto-select Epic: 3
Difference from bmad-epic-worktree
| Feature | bmad-epic-worktree | bmad-epic-pipeline-worktree |
|---|---|---|
| Story delivery | bmad-story-worktree | bmad-story-pipeline-worktree |
| Workflow config | Fixed 8-step flow | Configurable via workflow-steps.md |
| Customization | Limited | Full pipeline customization |
| Safety level | High | High |
Execution Strategy
- Read all incomplete stories under the Epic
- Sort by Story number ascending
- Execute
/bmad-story-pipeline-worktreefor each story sequentially - Only start next story after previous one completes
- If any story fails, stop and preserve current state
Execution Flow
Step 1: Collect Epic Story List
Read sprint-status.yaml, collect all incomplete stories under specified Epic:
Task(
subagent_type: general-purpose,
description: "Collect Epic {ARGUMENT} story list",
prompt: "Read _bmad-output/implementation-artifacts/sprint-status.yaml (or docs/sprint/sprint-status.yaml), collect all stories for Epic {ARGUMENT}:
1. Filter entries with key format '{ARGUMENT}-Y-story-name'
2. Keep only stories with status not 'done'
3. Sort by Story number Y ascending
4. Return story list with format:
- Story number: 'X.Y', Story name, Current status
- Number of incomplete stories
If no incomplete stories found, return 'Epic {ARGUMENT} has no incomplete stories'"
)
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.
- 10d ago First seen · 223 lines · 20 tokens per session scan A 5c9d4c66dc86
bmad-epic-pipeline-worktree is a skill published in the GitHub repository terryso/claude-bmad-skills (41 stars, last pushed 5mo ago), licensed MIT. It adds 20 tokens to every session and 1,694 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 2026-09-01.
Other skills, from other repositories
friction-log
File contributor or agent papercuts as GitHub issues labeled friction, or investigate those issues as the daily friction-log Cloud Agent. Use when you hit repo friction, when asked to log friction, or when spawned to resolve open friction issues.
split-and-ship
Execute an approved split plan, shipping each change group separately as its own branch and PR or as sequential commits on the current branch. Use when the user asks to "split and ship", "ship the split plan", "create separate PRs", or "split changes into branches".
loopit
Drive a task queue (loop-tasks.md) to completion in ANY repo — detect the repo's own rules, then for each task plan → /review-plan → implement → verify → /review → fix all findings → commit → push → client doc → mark done. Autonomous between tasks; pauses only for genuine product decisions.
wrap-phase
Wraps up a development phase by cleaning AGENTSYNC.md, summarizing work, and committing changes.
github-pr-workflow
GitHub PR lifecycle: branch, commit, open, CI, merge.
commit-history
List recent git commits linked to agent sessions, optionally filtered by branch or repo. Use when the user asks "show agent commits", "what has the agent shipped", "list linked commits", or wants commits with their session context.