Skill

always-on-guidance

Provides rules for Claude plugin agents on swarm tool usage, model behaviors, file reservations, task coordination, and TDD. Useful in multi-agent Claude Code workflows.

developer-tools

code-quality

npx claudepluginhub imbios/swarm-tools

Popularity

Parent stars

Shared by

Invocation

How this skill is triggered — by the user, by Claude, or both

Slash command

/swarm:always-on-guidance

User invocable

Model invocable

Inline context

Default effort

Context Preview

The summary Claude sees in its skill listing — used to decide when to auto-load this skill

- Follow instruction priority: system → developer → user → AGENTS.

SKILL.md

44 lines · ~450 tokens

Similar Skills

always-on-guidance

674

Provides rules for Claude plugin agents on swarm tool usage, model behaviors, file reservations, task coordination, and TDD. Useful in multi-agent Claude Code workflows.

swarm

prompt-engineering

Crafts effective prompts, CLAUDE.md instructions, rules, agent system prompts, and skill bodies for reliable Claude Code behavior.

3 tools

claude-code-expert

agent-management

Working with AI coding agents — User Sovereignty, agreement-as-signal, Karpathy/Willison framing, per-model overlays, and the rule to measure your prompt nudges.

gstack-distilled

Stats

LanguageTypeScript

Parent stars1

MaintenanceExcellent

Last CommitMar 31, 2026

Actions

View Source View Plugin View on GitHub View README

Help us improve

Share bugs, ideas, or general feedback.

Stats

Actions

Help us improve

Share bugs, ideas, or general feedback.

Always-On Guidance

Global Rules

Follow instruction priority: system → developer → user → AGENTS.

Use swarm plugin tools (hive_*, swarm_*, swarmmail_*, hivemind_*); avoid deprecated bd/cass references.

Stay within assigned files; reserve before edits with ttl_seconds; release reservations on done; finish swarm work with swarm_complete.

Use TaskCreate/TaskUpdate for visible progress in Claude Code UI alongside hive_* for git-backed persistence.

When CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS is enabled, prefer TeammateTool for real-time coordination and swarmmail_* for persistence.

swarmmail_release_all is coordinator-only for stale/orphaned reservations.

Keep outputs concise and action-oriented.

Model Defaults

Use model aliases (inherit, opus, sonnet, haiku) instead of version numbers.

Opus

Allow brief rationale (1–2 sentences) for decisions.

Use sections when work has multiple phases.

Suggest alternatives only when risk is high, then choose one.

Stay compact; avoid long exposition.

Sonnet/Haiku

Prefer strict checklists and short imperatives.

Ask a single clarifying question if blocked; otherwise proceed.

Avoid speculative reasoning; state decisions plainly.

Keep outputs minimal and non-narrative.

Testing Discipline

Use red → green → refactor when tests cover the touched area.

Use EnterPlanMode for test-driven planning before implementation.

If tests are absent or out of scope, state that explicitly.