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 skills/choucrifahed/agent-plugins/bmad-github-story-devnpx skills add choucrifahed/agent-plugins --skill bmad-github-story-devgit clone --depth 1 https://github.com/choucrifahed/agent-pluginsWrote 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/choucrifahed/agent-plugins/bmad-github-story-dev)<a href="https://agentmods.dev/skills/choucrifahed/agent-plugins/bmad-github-story-dev"><img src="https://agentmods.dev/badge/skills/choucrifahed/agent-plugins/bmad-github-story-dev.svg" alt="Measured on agentmods" 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 | $0.00078 | $0.03102 |
| Opus 5 | $0.00039 | $0.01551 |
| Sonnet 5 | $0.00016 | $0.00620 |
| Haiku 4.5 | $0.00008 | $0.00310 |
Grade A, and why
bmad-github-story-dev 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 — 344 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Story Dev: Detect Context + Sync + Verify + Git Setup + BMAD Dev-Story + PR
You are developing a story. This skill handles the full lifecycle:
- Detect the current working context (main checkout vs. existing story worktree)
- Sync local state (light refresh)
- Pick the target story (from branch name, user argument, or next
status:readyGitHub issue) - Verify the story file is committed
- Flip the GitHub issue status label atomically (acts as the cross-agent "lock")
- Set up a git worktree/branch — or reuse the current one
- Run the BMAD dev-story operation with auto-commits per task
- Create a PR when development is complete
This skill is safe to run from main or from inside a story/<key> worktree. It does not require any commits on
main before branching, so it composes cleanly with orchestrators like Conductor that spawn agents in pre-created
worktrees.
Phase 0: Detect Worktree Context
Run these together and record the results:
git rev-parse --is-inside-work-tree
git rev-parse --show-toplevel
git branch --show-current
Classify the context using the branch name as the primary signal:
| Branch name | Context | Worktree creation in Phase 5 |
|---|---|---|
main (or the repo's main branch) |
main checkout | Create a new worktree |
story/<key> matching the plugin's convention |
existing story worktree | Reuse — skip creation |
| any other branch | unrecognized | STOP and ask the user |
If the branch is unrecognized (not main and not story/<key>), print:
Current branch is `<branch>`. This skill expects either `main` or a `story/<key>` branch.
Switch to `main` (or to the story worktree you want to continue) and re-run.
Save the classification as {{context}} = main | worktree | unrecognized and the current branch as {{branch}}.
Phase 1: Sync First
Read and follow ${CLAUDE_PLUGIN_ROOT}/references/sync-first.md.
On main this runs the full /story-sync reconciliation so BMAD's dev-story (Phase 6) sees a current sprint-status.yaml. In a worktree, it does a git fetch and warns that sprint-status.yaml may lag main.
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 · 344 lines · 78 tokens per session scan A c68c54616c9f
bmad-github-story-dev is a skill published in the GitHub repository choucrifahed/agent-plugins (7 stars, last pushed 1mo ago), licensed MIT. It adds 78 tokens to every session and 3,102 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
qa/e2e-playwright
Playwright E2E 测试完整方法论，涵盖项目初始化、Page Object Model、认证复用、API Mock、视觉回归、多浏览器测试、CI 集成和调试技巧.
backend/testing-guide
后端测试编写指南，包括单元测试、集成测试和E2E测试的编写方法和最佳实践.
architect/architecture-design
系统架构设计方法论，包含架构模式选择、系统分层、目录结构设计.
architect/data-api-design
Skill "architect/data-api-design" from echoVic/boss-skill, covering 数据模型与api设计方法论, 适用场景, 数据模型设计, 1. 实体识别 and 2. 关系识别.
backend/api-development
后端API开发方法论，包括RESTful/GraphQL设计、请求验证、错误处理和安全实现.
brainstorming
需求澄清 Skill。当用户只给了模糊描述时自动触发，通过业务提问把一句话翻译成完整需求，交给 Boss 流水线执行。 Triggers: '我想做一个', '帮我做', '有个想法', 'brainstorm', '帮我规划一下', '做个XX', 'I want to build' Does NOT trigger: 需求已经完整（包含做什么 + 给谁用 + 核心场景） 纯技术问题或 bug 修复 Output: .boss/ /design-brief.md 需求设计简报.