Command reference

Commands are generated from commands/manifest.json. Rebuild this page with npm run docs:commands after changing the manifest. Runtime support is recorded separately in that file; a registered command does not prove the agent host loads it.

Syntax

The native command name is listed below. Legacy invocations use /sherpa <operation> [focus]. For example:

/sherpa status
/sherpa suggest focus on accessibility for campus teams
/sherpa config check

There are no structured command flags for agent workflows. Optional natural-language context is passed as focus. Unknown explicit commands are unavailable. The host's actual invocation format depends on its adapter.

Index

• CORE
• CONFIGURATION
• INTELLIGENCE
• ENGINEERING
• PRODUCT QUALITY
• FINALIZATION

Native command	Description	Router key	Procedure
sherpa-status	Show evidence-backed project status.	status	workflows/status.md
sherpa-next	Identify the single highest-priority next action.	next	workflows/next.md
sherpa-help	List implemented sherpa commands and limitations.	help	SKILL.md#help
sherpa-init	Initialize project-local sherpa state safely.	init	workflows/init.md
sherpa-phase	Show current lifecycle phase and evidence.	phase	SKILL.md#phase
sherpa-config	Show a redacted project configuration overview.	config	workflows/configuration.md
sherpa-config-check	Validate project configuration and secret protections.	config check	workflows/configuration.md
sherpa-suggest	Discover, evaluate, and red-team idea candidates; human selection required.	suggest	workflows/idea-intelligence.md
sherpa-evaluate	Evaluate and compare candidate ideas with evidence.	evaluate	workflows/idea-evaluation.md
sherpa-compare	Compare candidate ideas using the existing idea-evaluation workflow.	compare	workflows/idea-evaluation.md
sherpa-redteam	Challenge project assumptions and readiness using the red-team workflow.	redteam	workflows/red-team.md
sherpa-optimize	Prioritize score-improving work against evidence and criteria.	optimize	workflows/score-optimization.md
sherpa-judge-me	Simulate judge perception using the judge-simulation workflow.	judge-me	workflows/judge-simulation.md
sherpa-repo	Inspect repository evidence as part of project planning.	repo	workflows/project-planning.md
sherpa-architecture	Plan architecture from the selected idea and repository evidence.	architecture	workflows/project-planning.md
sherpa-techstack	Assess technology choices within the project plan.	techstack	workflows/project-planning.md
sherpa-plan	Create an implementation-ready project plan.	plan	workflows/project-planning.md
sherpa-build	Execute an approved implementation task using the existing implementation workflow.	build	workflows/implementation.md
sherpa-verify	Verify implementation through the existing testing and security workflow.	verify	workflows/testing-security.md
sherpa-test	Test implemented scope using the testing and security workflow.	test	workflows/testing-security.md
sherpa-security	Review security using the testing and security workflow.	security	workflows/testing-security.md
sherpa-ux	Review product usability and accessibility readiness.	ux	workflows/ux-review.md
sherpa-accessibility	Review accessibility within the existing UX-review scope.	accessibility	workflows/ux-review.md
sherpa-demo	Prepare an evidence-backed judge-oriented demo plan.	demo	workflows/demo-preparation.md
sherpa-audit	Run the existing final-audit workflow after its prerequisites are met.	audit	workflows/final-audit.md
sherpa-submission	Prepare and verify submission materials without submitting.	submission	workflows/submission.md
sherpa-postmortem	Run the final-phase evidence-based retrospective.	postmortem	workflows/postmortem.md
sherpa-research	Research competitors, markets, technologies, and evidence with verifiable sources.	research	workflows/research.md

Distribution management CLI

This separate executable manages installed files; these are not agent workflows.

Command	Arguments	Behavior
sherpa --version	none	Prints installed CLI version.
sherpa update	optional --yes / -y	Fetches a release and updates managed skill files after checksum verification.
sherpa uninstall	optional --yes / -y	Removes recognized managed skill and CLI files; preserves project state.
sherpa doctor	none	Reports runtime/install information and manifest reachability.
sherpa audit	none	Reports debris, duplicates, empty directories, and file count in managed skill folders.
sherpa clean	--dry-run by default; --yes to remove	Lists recognized generated debris; deletion requires confirmation and is scoped to managed skill folders.
sherpa help	none	Prints CLI usage.

Agent workflows return evidence-based reports or artifacts; they do not promise one fixed output schema. See installation and source command notes.