Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/epicsagas-orchestrate
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: data, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/orchestrate
What's inside
- Skill name
orchestrate- Description
- Trigger: active multi-agent run. Handles inbox reading, dep resolution, message formatting, handoffs. Also provides status dashboard and intervention control via internal modes.
- License
- Apache-2.0
- Instructions
- 240 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Skill: Orchestrate
**CRITICAL**: Run `HARNESS_DIR=$(epic-harness path)` first. NEVER use `.harness/` in the project directory.
## Mode: auto (default)
Triggered automatically when an active multi-agent orchestration is detected.
### Step 1: Check orchestration state
1. Run `HARNESS_DIR=$(epic-harness path)`
2. Read `$HARNESS_DIR/orchestrator/run.json`
3. If no active run, this skill does not apply — return
### Step 2: Read agent inbox
1. Read `$HARNESS_DIR/orchestrator/agents/{my_id}/inbox.jsonl`
2. Process any pending messages from other agents or user interventions
3. Messages from other agents: integrate into current task context
4. Messages from user (via intervene redirect): adjust task accordingly
### Step 3: Check control directives
1. Read `$HARNESS_DIR/orchestrator/control.json`
2. If a directive targets this agent (or "all"), act on it:
- **pause**: halt work after current tool call, wait for resume
- **cancel**: stop immediately, set status to "cancelled"
- **redirect**: adopt the new instruction, discard current task
- **resume**: resume from paused state
3. After acting on a directive, increment `generation` in control.json to acknowledge
### Step 4: Check dependencies
1. Read `$HARNESS_DIR/orchestrator/run.json` dependency graph
2. Identify which agents this agent depends on
3. Read their `status.json` — if any dependency is not DONE, wait
4. If all dependencies are DONE, proceed with task
### Step 5: Execute with progress reporting
While working on the assigned task:
1. The Rust `orchestrate` hook automatically appends events to `stream.jsonl` on each tool call
2. Status updates happen automatically via the hook
3. No manual progress reporting needed — the hook handles it
### Step 6: Complete and hand off
When task is complete:
1. Report status via structured output format (DONE/DONE_WITH_CONCERNS/BLOCKED/NEEDS_CONTEXT)
2. The `orchestrate` hook will evaluate dependencies and notify downstream agents
3. If results should be shared with specific agents, include in the output summary
---
## Mode: status — Orchestration Dashboard
Read-only view of the current orchestration run. Displayed when user runs `/status` or asks about orchestration state.
### Step 1: Check orchestration state
1. Check if `$HARNESS_DIR/orchestrator/run.json` exists
2. If the file does not exist, output:
> No active orchestration. Run `/go` or `/orbit` to start.
3. If `status` is not `"running"`, output:
> Last orchestration ended with status: **{status}**. No active run.
4. If `status` is `"running"`, proceed to Step 2.
### Step 2: Read all agent states
Extract the agent list from `run.json.agents`. For each agent `{id}`:
1. Read agent status from `$HARNESS_DIR/orchestrator/agents/{id}/status.json` (mark `unknown` if missing)
2. Read the last 5 events from `$HARNESS_DIR/orchestrator/agents/{id}/stream.jsonl` (show "no events yet" if missing)
3. Calculate elapsed time:
- `started_at` set, `completed_at` not set: elapsed = now - `started_at`
- Both set: elapsed = `completed_at` - `started_at`
- Format as `Xm Ys` or `Xh Ym`
4. Read the dependency graph from `run.json.dependencies`
### Step 3: Render dashboard
Output a formatted dashboard (keep total under 30 lines):
```
## Orchestration Dashboard
- **Run ID**: {run.id}
- **Status**: {run.status}
- **Elapsed**: {total_elapsed since run.started_at}
- **Agents**: {count where status=running} / {total} active
| Agent | Role | Status | Elapsed | Last Event |
|-------|------|--------|---------|------------|
| {id} | {role} | {status} | {elapsed} | {summary of last event} |
### Dependency Graph
{render with ASCII arrows, e.g.:}
builder ──→ reviewer ──→ integrator
builder ──→ tester
### Recent Events (last 5 across all agents)
- [{timestamp}] {agent_id}: {event_summary}
### User Interventions
{read control.json; show directives if any, else "none"}
```
**Dependency graph rendering rules:**
- Read edges from `run.json.dependencies` (format: `{"agent_a": ["agent_b", "agent_c"]}`)
- Render using `──→` arrows
- If no dependencies exist, output: "No inter-agent dependencies."
**Event summary formatting:**
- Each event is one line from `stream.jsonl` with fields: `timestamp`, `type`, `message`
- Summarize `message` to at most 60 characters
- Sort by timestamp descending, take top 5
### Step 4: Optional — file change summary
```bash
git diff --stat
```
If changes exist, append:From epicsagas/epic-harness, Apache-2.0.
More from epicsagas/epic-harness
- 0.629score
vuln-scan
epicsagas
Systematic vulnerability scan across injection, auth, data exposure, and dependencies — traced by reading code, not grepping for keywords.
SkillAFreshness: A★ 19Claude Code +9 - 0.629score
document
epicsagas
Documentation generator for public APIs, functions, and modules.
SkillAFreshness: A★ 19Claude Code +9 - 0.629score
team
epicsagas
Org-level agent team designer via `epic team` CLI (cross-project, append-merge).
SkillAFreshness: A★ 19Claude Code +9 - 0.629score
triage
epicsagas
Adversarial validation of vulnerability findings.
SkillAFreshness: A★ 19Claude Code +9 - 0.629score
threat-model
epicsagas
Threat modeling and attack surface analysis.
SkillAFreshness: A★ 19Claude Code +9 - 0.629score
benchmark
epicsagas
Executes Bare-vs-Epic A/B benchmarking, Ring 0 Guard 50 challenge, and full golden set evaluation for epic-harness.
SkillAFreshness: A★ 19Claude Code +9 - 0.629score
agent-introspection
epicsagas
Loop-breaking self-diagnosis.
SkillAFreshness: A★ 19Claude Code +9 - 0.626score
context
epicsagas
Working-state snapshot guidance.
SkillAFreshness: A★ 19Claude Code +9 - 0.626score
orbit
epicsagas
State-persisted autonomous pipeline: spec → go → audit → eval → ship → evolve in one command.
SkillAFreshness: A★ 19Claude Code +9 - 0.626score
reflect
epicsagas
On-demand human self-assessment of AI usage quality.
SkillAFreshness: A★ 19Claude Code +9 - 0.626score
go
epicsagas
Go phase.
SkillAFreshness: A★ 19Claude Code +9 - 0.626score
evolve
epicsagas
Ring 3 evolution engine.
SkillAFreshness: A★ 19Claude Code +9
Signals
- Stars
- 19
- Forks
- 5
- Open issues
- 3
- Last commit (this folder)
- Jun 25, 2026 (4 months ago)
- Last release
- Oct 23, 2026 (4 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Repository
- github.com/epicsagas/epic-harness
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from epicsagas
- 0.641score
book-visuals
epicsagas
Book visual system: art bible and look lock, figure plan per chapter, code-rendered diagrams/charts/technical drawings, diffusion-generated illustrations and…
SkillAFreshness: A★ 38Claude Code +9 - 0.638score
book-game
epicsagas
Game narrative craft reference: branching architecture, quest design, dialogue systems, lore bible, player agency, and game-writing AI tells.
SkillAFreshness: A★ 38Claude Code +9 - 0.638score
book-academic
epicsagas
Academic writing craft reference: IMRAD and discipline structures, literature review, argument chains, citation integrity, academic register in en/ko/ja, and…
SkillAFreshness: A★ 38Claude Code +9 - 0.638score
book-draft
epicsagas
Phase 3: Drafting.
SkillAFreshness: A★ 38Claude Code +9 - 0.638score
book-fiction
epicsagas
Fiction craft reference for all subgenres: structure options, scene design, character depth, dialogue, POV and distance, the fiction-specific AI tells, and…
SkillAFreshness: A★ 38Claude Code +9 - 0.638score
book-edit
epicsagas
Phase 4: Editing.
SkillAFreshness: A★ 38Claude Code +9
Cite this page
orchestrate skill. Agent Mart. https://agentmart.dev/skills/epicsagas-orchestrate (last updated 2026-10-24)