Team Agent Orchestration
affaan-m/ECC
Run team-based orchestration for agent squads: work items with owners and scope, agent Kanban state, branch isolation, control pane visibility, and merge gates.
Orchestrate full epic development end-to-end. An agent skill from redhat-cop/vault-config-operator.
Apache-2.0Auto-check passed
Install Bmad Epic Dev
$ npx skills add redhat-cop/vault-config-operator --skill bmad-epic-dev -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install redhat-cop/vault-config-operator bmad-epic-dev --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/redhat-cop/vault-config-operator.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/bmad-epic-dev .claude/skills/bmad-epic-dev && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "bmad-epic-dev" agent skill from https://github.com/redhat-cop/vault-config-operator/tree/main/.claude/skills/bmad-epic-dev into .claude/skills/bmad-epic-dev/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bmad-epic-dev", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/redhat-cop/vault-config-operator/tree/main/.claude/skills/bmad-epic-devType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add redhat-cop/vault-config-operator --skill bmad-epic-dev -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install redhat-cop/vault-config-operator bmad-epic-dev --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/redhat-cop/vault-config-operator.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/bmad-epic-dev .agents/skills/bmad-epic-dev && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "bmad-epic-dev" agent skill from https://github.com/redhat-cop/vault-config-operator/tree/main/.claude/skills/bmad-epic-dev into .agents/skills/bmad-epic-dev/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bmad-epic-dev", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add redhat-cop/vault-config-operator --skill bmad-epic-dev -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install redhat-cop/vault-config-operator bmad-epic-dev --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/redhat-cop/vault-config-operator.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/bmad-epic-dev .cursor/skills/bmad-epic-dev && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "bmad-epic-dev" agent skill from https://github.com/redhat-cop/vault-config-operator/tree/main/.claude/skills/bmad-epic-dev into .cursor/skills/bmad-epic-dev/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bmad-epic-dev", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/redhat-cop/vault-config-operator.git --path .claude/skills/bmad-epic-dev--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add redhat-cop/vault-config-operator --skill bmad-epic-dev -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install redhat-cop/vault-config-operator bmad-epic-dev --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/redhat-cop/vault-config-operator.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/bmad-epic-dev .gemini/skills/bmad-epic-dev && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "bmad-epic-dev" agent skill from https://github.com/redhat-cop/vault-config-operator/tree/main/.claude/skills/bmad-epic-dev into .gemini/skills/bmad-epic-dev/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bmad-epic-dev", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install redhat-cop/vault-config-operator bmad-epic-devInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add redhat-cop/vault-config-operator --skill bmad-epic-dev -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/redhat-cop/vault-config-operator.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/bmad-epic-dev .github/skills/bmad-epic-dev && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "bmad-epic-dev" agent skill from https://github.com/redhat-cop/vault-config-operator/tree/main/.claude/skills/bmad-epic-dev into .github/skills/bmad-epic-dev/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bmad-epic-dev", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add redhat-cop/vault-config-operator --skill bmad-epic-dev -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install redhat-cop/vault-config-operator bmad-epic-dev --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/redhat-cop/vault-config-operator.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/bmad-epic-dev .opencode/skills/bmad-epic-dev && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "bmad-epic-dev" agent skill from https://github.com/redhat-cop/vault-config-operator/tree/main/.claude/skills/bmad-epic-dev into .opencode/skills/bmad-epic-dev/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bmad-epic-dev", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
bmad-epic-dev- GitHub stars
- 167
- Token cost
- ~1k tokens
- SKILL.md length
- 527 words
- Files
- 6 (incl. scripts, references)
- Skills in repo
- 19
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Orchestrate full epic development end-to-end. An agent skill from redhat-cop/vault-config-operator.
- The user says dev this epic
- SKILL.md covers Overview and On Activation
- Runs Python scripts from its folder; calls python3
- Implement epic [number]
What it does
Bmad Epic Dev is an agent skill from redhat-cop/vault-config-operator. Orchestrate full epic development end-to-end. Use when the user says 'dev this epic' or 'implement epic [number]'.
Its SKILL.md is about 1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 8 other files, including scripts and reference files (for example `references/phase-logic.md`, `scripts/epic-plan.py` and `scripts/finalize-story.py`).
The repository describes itself as: An operator to support Haschicorp Vault configuration workflows from within Kubernetes. The licence is Apache-2.0.
When your agent uses it
- The user says dev this epic
- Implement epic [number]
Example prompts
- “dev this epic”
- “implement epic [number]”
- “/bmad-epic-dev”
Requirements
- Python 3
What it can do on your machine
Read from SKILL.md and the folder at commit 99762c2. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 4 files in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
python3
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Bmad Epic Dev loads about 1k tokens when it runs, and up to ~8.9k if it reads all its reference files. Until then it costs about 32 tokens; SKILL.md has 527 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
The full file from redhat-cop/vault-config-operator at commit 99762c2, republished under its Apache-2.0 licence (© redhat-cop). 527 words, ~1,024 tokens.
Download SKILL.mdSave it as
.claude/skills/bmad-epic-dev/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.- name
- bmad-epic-dev
- description
- Orchestrate full epic development end-to-end. Use when the user says 'dev this epic' or 'implement epic [number]'.
Epic Dev
Overview
This skill drives an entire epic from backlog to done — creating story specs, implementing each story, and running adversarial code review — all with fresh LLM context per step. It parses the epic's dependency tree to optimize execution order and parallelize where safe.
Act as a disciplined build orchestrator. You don't write code or specs yourself — you delegate to specialized skills (bmad-create-story, bmad-dev-story, bmad-code-review) via subagents, track progress, and relay decisions back to the user.
Args:
- Epic number (e.g.,
13) — required --commit-policy=<auto|ask|skip>— controls git commit behavior (default:auto)auto: commit automatically at prescribed pointsask: prompt user before each commitskip: never commit (user handles commits manually)
--skip-confirmations— suppress soft-gate pauses between phases (for experienced users resuming a known-good epic)
Model configuration:
Different phases use different LLMs by design — code review must run on a different model than the one that wrote the code to avoid self-review bias.
| Phase | Role | Model | Reasoning |
|---|---|---|---|
| Step 0 (planning) | Design & decisioning | Opus 4.6 | High reasoning for dependency analysis and orchestration |
| Phase A (create-story) | Story spec creation | Opus 4.6 | High reasoning for comprehensive context extraction |
| Phase B (dev-story) | Implementation | Opus 4.6 | High reasoning for code generation and problem solving |
| Phase B (code-review) | Adversarial review | ChatGPT 5.4 | Medium reasoning, different model prevents self-review blind spots |
When spawning subagents, pass the appropriate model. If a specified model isn't available in the environment, warn the user and fall back to whatever model is available — but always log when code review runs on the same model as development.
Core contract:
- Every sub-skill runs in a fresh subagent (clean LLM context)
- Sub-skill subagents run autonomously but relay "decision needed" questions back to you for the user
- Code review subagents MUST use a different LLM model than the development subagents
- On any failure: halt with resume instructions — re-invoking with the same epic number picks up where it left off
sprint-status.yamlis the checkpoint — story statuses determine what's been done and what remains- Phase B finalization is a script, not a doc rule. After review, run
python3 ./scripts/finalize-story.py {story-key}. Never hand-edit sprint-status todone. The script refuses unless the story file has a Code Review Record with a Review Model Used, then sets storyStatus:and sprint-status together. After each layer run--check-epic {N}and HALT on failure. - Interactive by default: report progress after each story, soft gates between phases
- Phase A (story specs) parallelizes by dependency layer via concurrent subagents
- Phase B (implementation) parallelizes by dependency layer via git worktrees — each story gets its own branch and working directory, merged back after review
Show full SKILL.md (103 more words)Show less
On Activation
Load available config from {project-root}/_bmad/config.yaml and {project-root}/_bmad/config.user.yaml (root level and bmm section). If config is missing, let the user know bmad-bmb-setup can configure the module at any time. Use sensible defaults for anything not configured.
Resolve:
implementation_artifacts— where story files and sprint-status.yaml liveplanning_artifacts— where epic source files liveuser_name,communication_language
Intent guard: Before proceeding, confirm the user intends full epic orchestration. If the input looks like a single story reference (e.g., "13.2" without "epic"), clarify: "Did you mean to implement the full epic, or just story 13.2? For a single story, use bmad-dev-story instead."
Then read fully and follow ./references/phase-logic.md.
© redhat-cop, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 5 other files (scripts, references) in .claude/skills/bmad-epic-dev of redhat-cop/vault-config-operator.
- SKILL.md
- references/phase-logic.md
- scripts/epic-plan.py
- scripts/finalize-story.py
- scripts/tests/test-epic-plan.py
- scripts/tests/test-finalize-story.py
Open the folder on GitHubat commit 99762c2
Compare with similar skills
Bmad Epic Dev next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Bmad Epic Dev this skillredhat-cop/vault-config-operator | 167 | — | ~1k | Automated safety check: Pass | Apache-2.0 | |
| Team Agent Orchestrationaffaan-m/ECC | 275k | 1 repos | ~1.2k | Automated safety check: Pass | MIT | |
| Orca Orchestrationstablyai/orca | 87k | — | ~916 | Automated safety check: Pass | MIT | |
| Agent Orchestrator Taskruvnet/ruflo | 74k | 3 repos | ~1k | Automated safety check: Pass | MIT | |
| Plan Orchestrateaffaan-m/ECC | 275k | 1 repos | ~4.5k | Automated safety check: Pass | MIT | |
| Orchestratesickn33/agentic-awesome-skills | 47k | 1 repos | ~692 | Automated safety check: Pass | MIT |
Similar skills
Orca Orchestration
stablyai/orca
Coordinate supervised Orca workers: threaded messages, blocking ask/reply, task dispatch, worker_done/escalation waits, task DAGs, decision gates, coordinator…
Agent Orchestrator Task
ruvnet/ruflo
Agent skill for orchestrator-task - invoke with $agent-orchestrator-task
Plan Orchestrate
affaan-m/ECC
Read a plan document, decompose it into steps, design a per-step agent chain from the ECC catalogue, and emit ready-to-paste /orchestrate custom prompts.
Orchestrate
sickn33/agentic-awesome-skills
Coordinate focused subagents on substantial work, keep their ownership non-overlapping, and integrate verified results.
Swarm Orchestration
ruvnet/ruflo
Coordinates a hierarchical swarm of specialized agents through the claude-flow CLI for work that spans several files or modules at once.
More from redhat-cop/vault-config-operator
All 19 skills in this repoBmad Bmb Setup
redhat-cop/vault-config-operator
Sets up BMad Builder module in a project. An agent skill from redhat-cop/vault-config-operator.
Bmad Eval Runner
redhat-cop/vault-config-operator
Run a skill's evals and report results. An agent skill from redhat-cop/vault-config-operator.
Bmad Agent Builder
redhat-cop/vault-config-operator
Builds, edits or analyzes Agent Skills through conversational discovery.
Bmad Workflow Builder
redhat-cop/vault-config-operator
Builds, converts, and analyzes workflows and skills. An agent skill from redhat-cop/vault-config-operator.
Bmad Init
redhat-cop/vault-config-operator
Initialize BMad project configuration and load config variables.
Bmad Module Builder
redhat-cop/vault-config-operator
Plans, creates, and validates BMad modules. An agent skill from redhat-cop/vault-config-operator.
Questions about Bmad Epic Dev
What does Bmad Epic Dev do?
Orchestrate full epic development end-to-end. An agent skill from redhat-cop/vault-config-operator. Bmad Epic Dev is an agent skill from redhat-cop/vault-config-operator. Orchestrate full epic development end-to-end.
When should I use Bmad Epic Dev?
Bmad Epic Dev fits situations like: the user says dev this epic; implement epic [number].
How do I install Bmad Epic Dev in Claude Code?
Run `npx skills add redhat-cop/vault-config-operator --skill bmad-epic-dev -a claude-code`. Or copy the skill folder (.claude/skills/bmad-epic-dev in redhat-cop/vault-config-operator) into .claude/skills/bmad-epic-dev in your project. Claude Code loads it when a task matches its description.
How do I install Bmad Epic Dev in Codex?
Run `npx skills add redhat-cop/vault-config-operator --skill bmad-epic-dev -a codex`. Or copy the skill folder (.claude/skills/bmad-epic-dev in redhat-cop/vault-config-operator) into .agents/skills/bmad-epic-dev in your project. Codex loads it when a task matches its description.
Can I use Bmad Epic Dev in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add redhat-cop/vault-config-operator --skill bmad-epic-dev -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/bmad-epic-dev, .gemini/skills/bmad-epic-dev, .github/skills/bmad-epic-dev and .opencode/skills/bmad-epic-dev in your project.
What does Bmad Epic Dev need to run?
Going by SKILL.md and its folder, Bmad Epic Dev needs Python for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: Python 3.
Does Bmad Epic Dev access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Bmad Epic Dev safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Bmad Epic Dev use?
Bmad Epic Dev is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Bmad Epic Dev use?
About 1k tokens (SKILL.md is roughly 4.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 7.9k tokens, read only when the agent opens those files.
What are the alternatives to Bmad Epic Dev?
Skills that share tags, products or a category with Bmad Epic Dev: Team Agent Orchestration (affaan-m/ECC, 275k stars), Orca Orchestration (stablyai/orca, 87k stars), Agent Orchestrator Task (ruvnet/ruflo, 74k stars) and Plan Orchestrate (affaan-m/ECC, 275k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Bmad Epic Dev?
redhat-cop (a GitHub organization) maintains it in redhat-cop/vault-config-operator, which has 167 GitHub stars. The repository holds 19 skills in this directory. The repository was last updated on October 7, 2026.
Source: redhat-cop/vault-config-operator on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.