Orchestrate Round

What it does

When your agent uses it

• In single-session mode
• A project-level session mode must drive dispatch order
• Manually advancing the state machine

Example prompts

• “/orchestrate-round”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

1. 1git status — what files changed?
2. 2git diff — what's the actual content?
3. 3Read the artifact (verdict / handoff / etc.) directly
4. 4Run any mechanical fact-table commands the artifact claims passed
5. 5Run state.yaml schema validation
6. 6Only THEN advance the state machine

What it can do on your machine

Read from SKILL.md and the folder at commit 8539955. 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

  Shell commands in SKILL.md call:

  • git

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

  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

Orchestrate Round loads about 1.5k tokens when it runs, and up to ~4.7k if it reads all its reference files. Until then it costs about 76 tokens; SKILL.md has 462 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~76

When it runs · the whole SKILL.md, loaded when a task matches

~1.5k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~4.7k

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

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from Arch1eSUN/Arcgentic at commit 8539955, republished under its MIT licence (© Arch1eSUN). 462 words, ~1,548 tokens.

name

orchestrate-round

description

Main-session orchestrator for arcgentic rounds. Use when in single-session mode, when a project-level session mode must drive dispatch order, or when manually advancing the state machine. Dispatches role sub-agents, verifies structured outputs, and owns PASS-only close-round execution.

LOAD pre-round-scan skill → run scan
LOAD state.yaml → identify current_state
IF project.session_mode is present:
  → use it; do not ask the user for mode again
ELSE:
  → run `arcgentic session-mode recommend`
  → store the project-level decision before dev starts
RUN `arcgentic orchestrator-dispatch --round <round-id> --handoff <path> --mode <mode>`
DETERMINE next action:
  IF current_state in {intake, planning}:
    → role = planner; dispatch planner-agent OR print planner role prompt
  IF current_state in {awaiting_dev_start, dev_in_progress, needs_fix, fix_in_progress}:
    → role = developer; dispatch developer-agent OR print developer role prompt
  IF current_state == awaiting_audit / audit_in_progress:
    → role = auditor; LOAD audit-round skill OR dispatch auditor-agent
  IF current_state == passed:
    → role = planner for next-phase decision OR run orchestrator-owned close-round
  IF current_state == closed:
    → ROUND COMPLETE; refresh state.yaml prior-round-anchor; start next round
EXECUTE action → wait for structured artifact
VERIFY artifact against state.yaml schema
CALL transition.sh with appropriate gate
LOOP

Use the Task tool with:
  description: "Audit round <round-id>"
  subagent_type: "general-purpose"  # or platform-specific
  prompt: |
    You are the auditor for arcgentic round <round-id>. Your job:
    1. Read $PLUGIN_ROOT/skills/audit-round/SKILL.md and its references/
    2. Read .agentic-rounds/state.yaml
    3. Read the handoff doc at <handoff-path>
    4. Read every commit in <dev_commits>
    5. Produce a verdict file at <verdict-path> following verdict-template.md
    6. Mechanically verify every fact in your fact table
    7. Apply lesson-codification-protocol.md
    8. Update state.yaml's current_round.audit_verdict block
    9. Return: "DONE — verdict at <verdict-path>, outcome <PASS|NEEDS_FIX>"

arcgentic orchestrator-dispatch \
  --round <round-id> \
  --handoff <handoff-path> \
  --mode <single-session|multi-session>

arcgentic v2-session-plan --state .agentic-rounds/state.yaml --host codex

© Arch1eSUN, MIT. 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 3 other files (references) in skills/orchestrate-round of Arch1eSUN/Arcgentic.

• SKILL.md
• references/single-vs-multi-session.md
• references/state-machine-overview.md
• references/sub-agent-dispatch.md

Open the folder on GitHubat commit 8539955