Plan Orchestrate
Turn a PRD, RFC, or implementation plan into ready-to-paste `/orchestrate custom` lines—one per step—with agent chains picked from the ECC catalogue so you do not hand-compose orchestration.
Overview
Plan Orchestrate is an agent skill most often used in Build (also Validate scope, Build PM) that reads a plan document and emits ready-to-paste `/orchestrate custom` prompts with per-step ECC agent chains.
Install
npx skills add https://github.com/affaan-m/everything-claude-code --skill plan-orchestrateWhat is this skill?
- Generative only: emits `/orchestrate custom` prompts per plan step—never invokes orchestrate itself
- Scopes work with `--scope=all|step:<n>|range:<a>-<b>` and `--dry-run` before you paste
- `--lang` selects reviewer language variant (python, typescript, go, rust, cpp, java, kotlin, flutter, auto)
- Accepts relative or absolute plan paths including `@docs/...` references
- Edge-case handling when the plan lacks clear numbering—still decomposes when content is readable
Adoption & trust: 1.2k installs on skills.sh; 210k GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
You have a solid multi-step plan but composing the right agent chain for every step by hand is slow and error-prone.
Who is it for?
Builders with an existing numbered or narrative implementation plan who use ECC `/orchestrate` and want consistent agent chains per step.
Skip if: One-off orchestrate tasks, empty or unreadable plans, or teams that want the skill to execute orchestration automatically.
When should I use this skill?
User has a multi-step plan document and wants orchestrate prompts per step; phrases like "orchestrate this plan" or "compose chains for this plan".
What do I get? / Deliverables
You get one copy-paste `/orchestrate custom` line per plan step with catalogue-matched chains, then run orchestration on your schedule.
- One `/orchestrate custom` prompt per plan step
- Per-step agent chain design aligned to ECC catalogue
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Plans are usually written during validate scope or build PM; execution wiring belongs on the build shelf as agent orchestration prep. Decomposes plan steps into per-step agent chains and ECC catalogue picks—core agent-tooling work before you paste invocations.
Where it fits
After scoping a feature, you point the skill at the scope doc to get orchestrate lines before full implementation.
An RFC with ten sections becomes ten `/orchestrate custom` invocations with reviewer lang set to typescript.
You dry-run chain decomposition for steps 3–5 only before pasting into Claude Code.
How it compares
Use instead of manually browsing the ECC catalogue for every plan step—this is a prompt generator, not a runtime orchestrator.
Common Questions / FAQ
Who is plan-orchestrate for?
Solo and indie builders on Everything Claude Code who maintain PRDs or implementation plans and drive work through `/orchestrate custom` without hand-picking agents each time.
When should I use plan-orchestrate?
During validate when a scoped plan is ready to operationalize, and during build when breaking an RFC or PM doc into agent chains—say "orchestrate this plan" or "compose chains for this plan" after the document exists.
Is plan-orchestrate safe to install?
It only reads plan files and generates text prompts; review the Security Audits panel on this Prism page and your repo’s skill source before trusting paths to sensitive docs.
SKILL.md
READMESKILL.md - Plan Orchestrate
# Plan Orchestrate Bridge a plan document to `/orchestrate custom` by emitting one ready-to-paste invocation per step. The skill is generative only — it never executes `/orchestrate`. The user pastes each line when ready. ## When to Activate - User has a multi-step plan document (PRD, RFC, implementation plan) and wants to drive it through `/orchestrate`. - User says "orchestrate this plan", "give me orchestrate prompts for each step", "compose chains for this plan". - A step-by-step plan exists but the user does not want to manually pick agents per step. Skip when: - The work is one ad-hoc step → call `/orchestrate custom` directly. - The plan is unreadable or empty. Lack of explicit numbering alone is not a skip condition — see the "No clear steps" edge case below. ## Inputs ``` <plan-doc-path> [--lang=python|typescript|go|rust|cpp|java|kotlin|flutter|auto] [--scope=all|step:<n>|range:<a>-<b>] [--dry-run] ``` - `<plan-doc-path>` — required; relative or absolute path (`@docs/...` accepted). - `--lang` — reviewer language variant; defaults to `auto` (detected from project). - `--scope` — limits emitted steps; defaults to `all`. - `--dry-run` — print decomposition + chain rationale only; do not emit final prompts. ## Authoritative `/orchestrate` shape (do not deviate) ``` {ORCH_CMD} custom "<agent1>,<agent2>,...,<agentN>" "<task description>" ``` Where `{ORCH_CMD}` is determined in Phase 0 (see below). The command string in the emitted output **always uses one concrete form** — never both, never a placeholder. - `custom` is a sequential chain; each agent's HANDOFF feeds the next. - Comma-separated agent list. No spaces preferred; one space tolerated. - No `--mode` / `--gate` / `--agents=...` flags exist — never invent them. - Agent names come from the catalogue in this skill. Embedded double quotes in the task description are escaped as `\"`. ## ECC install form and namespacing Two install forms determine the prefix on **both** the slash command and every agent name. The two MUST stay in sync — one form per output, never mixed: Let `<claude-home>` denote the Claude Code home directory: `~/.claude` on macOS/Linux, `%USERPROFILE%\.claude` on Windows. Resolve it the way the host platform resolves the user home directory (do not hardcode `~`). | Form | Detection | `{ORCH_CMD}` | Agent name format | |---|---|---|---| | Plugin install (1.9.0+) | `<claude-home>/plugins/marketplaces/everything-claude-code/` exists | `/everything-claude-code:orchestrate` | `everything-claude-code:<name>` | | Legacy bare install | Above absent; agent files under `<claude-home>/agents/` | `/orchestrate` | `<name>` | Why this matters: under the plugin install, agents register as `everything-claude-code:tdd-guide`. Bare names force fuzzy matching, which fails intermittently under parallel calls. Under legacy, the prefixed forms are not registered and fail outright. ## Available agent catalogue (must pick from these) General: - `planner` — requirement restatement, risk decomposition, step planning - `architect` — architecture, system design, refactor proposals - `tdd-guide` — write tests → implement → 80%+ coverage - `code-reviewer` — generic code review - `security-reviewer` — security audit, OWASP, secret leakage - `refactor-cleaner` — dead code, duplicates, knip-class cleanup - `doc-updater` — documentation, codemap, README - `docs-lookup` — third-party library API lookups (Context7) - `e2e-runner` — end-to-end test orchestration - `database-reviewer` — PostgreSQL schema, migration, performance - `harness-optimizer` — local agent harness configuration - `loop-opera