marshal — Claude Code skill: autonomous task orchestration
The marshal skill for Claude Code parses a task, gathers context from code and project memory, and chains skills. It runs in one session and asks only if it cannot continue.
MIT ★ 937 updated 2026-10-29
/plugin marketplace add SethGammon/Citadel
/plugin install citadel@citadel-localWhat marshal does
Marshal breaks tasks into structured steps: parse intent → plan chain → execute → report. It reads the project's architecture documents (AGENTS.md, CLAUDE.md) first, identifies which files to touch and what mode to work in. Then invokes skills in sequence, gathers context in parallel, and verifies each result.
Two modes: /marshal [direction] runs the full loop from analysis to report; /marshal assess [area] performs investigation only, no changes. Built-in timeouts on sub-agents (10 minutes for skills, 15 for research) prevent hanging. If the direction is ambiguous, it asks one clarifying question but won't request detailed step-by-step guidance.
Git history, code patterns, and documentation are gathered automatically. If something blocks on the first attempt, it tries once more with a different approach. Output is a structured report with line references and a HANDOFF block showing what changed and how to undo it.
What it helps with
- navigate multi-step tasks without manual verification at each step
- auto-gather context from docs and project memory before acting
- select and chain the right skill at each stage
- get a structured report with file references and reasoning
- revert changes if something goes wrong
Example prompts for the agent
- Orchestrate a security audit: scan logs, find anomalies, recommend fixes
- Improve code in
src/auth—analyze current state, identify issues, fix them - Research the architecture and suggest how to refactor backend modules
How to install marshal
1Plugin marketplace
/plugin marketplace add SethGammon/Citadel/plugin install citadel@citadel-localThis installs the whole citadel plugin with all its skills
2Skills CLI (Vercel)
npx skills add SethGammon/Citadel --skill marshal -a claude-code3Manually: put the files in place
~/.claude/skills/marshal/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/marshal/
1Skills CLI (Vercel)
npx skills add SethGammon/Citadel --skill marshal -a codex2Manually: put the files in place
.agents/skills/marshal/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add SethGammon/Citadel --skill marshal -a cursor2Manually: put the files in place
.cursor/skills/marshal/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install SethGammon/Citadel skills/marshal2Manually: put the files in place
.github/skills/marshal/SKILL.md1Skills CLI (Vercel)
npx skills add SethGammon/Citadel --skill marshal -a gemini-cli2Platform CLI
gemini skills install https://github.com/SethGammon/Citadel --path skills/marshalManually: put the files in place
.devin/skills/marshal/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about marshal
How do I install marshal in Claude Code?
Run /plugin marketplace add SethGammon/Citadel, then /plugin install citadel@citadel-local and npx skills add SethGammon/Citadel --skill marshal -a claude-code. The skill loads into ~/.claude/skills/marshal/SKILL.md.
What does marshal do?
It takes a task description (broad or narrow) and autonomously chains skills, gathers project context, performs actions, and reports findings with code references. It doesn't ask unnecessary questions.
When should I use marshal instead of other skills?
Use marshal for bounded multi-step work that completes in one session: audits, fixes that require investigation, code improvements. Don't use it for work spanning multiple sessions (use /archon) or tasks that parallelize into 3+ streams (use /fleet).
Source text
SKILL.md · MIT
---
name: marshal
license: MIT
description: >-
Meta-orchestrator that takes any direction — broad, specific, or vague — and
autonomously chains skills and context into actionable work. Gathers context
from codebase, docs, and memory. Only asks the user when it genuinely cannot
proceed. Single-session orchestrator.
user-invocable: true
auto-trigger: false
trigger_keywords:
- orchestrate
- chain skills
- multi-step
last-updated: 2026-03-20
---
# /marshal — Session Commander
## Orientation
Use Marshal when the task is:
- Multi-step but bounded (completable in one session)
- Needs investigation before action
- Spans multiple skills but doesn't need campaign persistence
- Too complex for a single skill but doesn't need Archon/Fleet
**Don't use when:** the task spans multiple sessions (use /archon); work decomposes into 3+ parallel streams (use /fleet); you only need research with no action (use /research).
- Parallel execution (use Fleet)
## Commands
| Command | Behavior |
|---|---|
| `/marshal [direction]` | Full loop: understand → plan → execute → report |
| `/marshal assess [area]` | Read-only: understand the area, produce findings, don't fix |
## Protocol
### Phase 1: UNDERSTAND
Parse the user's direction into structured intent:
1. Read AGENTS.md, then CLAUDE.md if present, to understand the project's architecture and conventions
2. Identify: scope (which files/directories), perspective (user, developer, admin),
mode (audit, fix, build, improve, map), depth (surface scan vs deep investigation)
3. If the direction is ambiguous, make a reasonable interpretation and state it.
Do NOT ask clarifying questions unless genuinely stuck.
### Phase 2: PLAN CHAIN
Map the intent to a sequence of actions:
| Direction Pattern | Chain |
|---|---|
| "audit [area]" | explore → analyze → report findings |
| "fix [thing]" | investigate root cause → fix → verify → report |
| "map [area]" | read files in parallel → synthesize → produce analysis |
| "improve [area]" | audit current state → identify gaps → implement → verify |
| "what should [X] be" | research → analyze options → recommend with reasoning |
| "research [topic]" | search codebase + web → synthesize → report |
Announce the chain before executing: "I'll [step 1], then [step 2], then [step 3]."
### Phase 3: EXECUTE
For each step in the chain:
1. Load the relevant skill if one exists (e.g., `/review` for audit steps)
2. Gather context: read relevant files, check git history, search for patterns
3. Perform the action
4. Check the result against the plan — did it produce what was expected?
5. If a step fails, try one alternative approach before escalating
### Phase 4: REPORT
Produce a structured report:
```
=== Marshal Report ===
Direction: {original direction}
Scope: {what was examined}
Findings:
- {finding 1 with file:line reference}
- {finding 2}
Actions Taken:
- {what was changed, if anything}
Recommendations:
- {next steps if applicable}
```
### Phase 5: LEARN
If the investigation revealed reusable patterns or pitfalls:
- Note them in the report
- Suggest creating a skill if a pattern will recur: "This pattern would
make a good skill. Run `/create-skill` to capture it."
## Agent Timeouts
When Marshal spawns sub-agents (e.g., for parallel investigation or delegated
skill execution), it must enforce execution time limits. Sub-agents can hang
indefinitely on tool calls — the circuit breaker catches failures, not hangs.
### Default Timeouts
| Agent Type | Default Timeout |
|---|---|
| Skill-level agents | 10 minutes |
| Research agents | 15 minutes |
Timeouts are configurable in `harness.json` under `agentTimeouts` (same config
Fleet uses). If an agent exceeds its timeout:
1. Log the timeout in telemetry
2. Check for partial output — extract usable findings if any
3. Try one alternative approach (simpler prompt, reduced scope)
4. If retry also times out, skip and note the gap in the report
Never wait indefinitely. A timed-out agent's scope becomes a "gap" in the
Marshal Report's Findings section.
## Fringe Cases
- **Direction is vague** (e.g., "do the thing", "fix it", "make it better"): Ask one clarifying question before proceeding. Do not attempt to guess scope on truly ambiguous input — one focused question is cheaper than executing the wrong plan.
- **A sub-task fails on first attempt**: Retry once with a different approach (narrower scope, different tool, simpler method). If the second attempt also fails, record the blocker in the report and move on.
- **No relevant files found for the stated scope**: Report the empty result honestly. Do not fabricate findings. Suggest the user verify the scope or file paths.
- **CLAUDE.md missing**: Proceed without it. Note the absence in the report so the user knows project conventions weren't applied.
- **Typecheck not configured**: Skip the verification step and note it as "unverified" in the report rather than blocking completion.
## Quality Gates
- Every finding must cite a specific file and line number
- Every action must be verified (typecheck passes, tests pass)
- If a fix was applied, confirm the original issue is resolved
- The report must be concise — no filler, no repetition
- If you're stuck on a step for more than 3 attempts, skip it and report the blocker
## Exit Protocol
1. Output the Marshal Report (format above)
2. If work items were discovered but not addressed, suggest creating intake items
3. Output a HANDOFF block summarizing what was done
```
---HANDOFF---
- What: {behavior changed or goal achieved — not the file name, the outcome}
- Decisions: {key tradeoffs made — include the alternative that was rejected}
- Unresolved: {what is still open or blocked — actionable next step}
- Reversibility: {green | amber | red} — {how to undo}
---
```
© SethGammon · MIT · SethGammon/Citadel