/swarm
Enable swarm mode for the current session.
If arguments are provided, enable swarm mode first and then execute that task using the swarm-like implementation workflow.
Argument handling:
- If no arguments are provided: only enable swarm mode.
- If the first word of
$ARGUMENTS is a known plugin subcommand (see list below): do NOT treat it as a swarm task. Instead, tell the user to run it as a slash command directly (e.g., /swarm close, /swarm handoff). These are OpenCode plugin commands handled by the swarm plugin's command system, not tasks for the swarm workflow. Do NOT try to interpret or execute them yourself.
- Otherwise: enable swarm mode, then treat
$ARGUMENTS as the task to execute immediately.
SWARM-NAMESPACED subcommands — DO NOT confuse with Claude Code built-in commands
These are invoked as /swarm <subcommand>, NOT as bare /subcommand. The list below is generated from the COMMAND_REGISTRY (src/commands/registry.ts) and includes all registered non-deprecated base commands and subcommands:
Core / state
/swarm status — show current swarm state/swarm show-plan — show current plan (optionally filter by phase number)/swarm plan — deprecated alias for /swarm show-plan/swarm agents — list registered agents/swarm help — show help for swarm commands (optionally [command])/swarm history — show completed phases summary/swarm config — show current resolved configuration/swarm export — export plan and context as JSON/swarm dataset consent — HUMAN-ONLY: grant or revoke the training-content consent (two-step confirm token; quotas clamp to hard ceilings)/swarm dataset withdraw — HUMAN-ONLY: confirmed destructive withdrawal — purge vault content, write a tombstone, revoke exports/swarm dataset export — HUMAN-ONLY: governed deterministic dataset export (preview + confirm token; manifest with sha256 checksums)/swarm evidence — show evidence bundles [taskId]/swarm evidence summary — generate evidence summary with completion ratio and blockers/swarm evidence-summary — deprecated alias for /swarm evidence summary/swarm handoff — prepare state for clean model switch/swarm archive — archive old evidence bundles [--dry-run]/swarm retrieve — retrieve full output from a summary <id>/swarm rollback — restore swarm state or project files to a checkpoint/swarm reset — clear swarm state files [--confirm]/swarm reset-session — clear session state, preserve plan/evidence/knowledge/swarm recover — settle wedged coder settlements [task_id] [--force] (human-only)/swarm checkpoint — manage project checkpoints [save|restore|delete|list] <label>/swarm finalize — finalize the swarm project and archive evidence/swarm close — deprecated alias for /swarm finalize/swarm auto-proceed — toggle or set auto-proceed override [on|off]/swarm concurrency — manage runtime concurrency override [set|status|reset]
Harness evolution
/swarm blueprint validate — validate a declarative harness blueprint or atomic blueprint patch/swarm blueprint current — show the ledger-derived current harness blueprint projection/swarm blueprint history — show bounded hash-verified harness version history/swarm blueprint diff — compare two stored harness blueprint versions/swarm blueprint export — export a canonical stored harness blueprint/swarm harness candidate validate — validate an inert harness candidate manifest/swarm harness candidate show — show bounded harness candidate metadata without raw patch content/swarm harness candidate diff — show candidate file and blueprint-change metadata without raw patch content
Diagnostics / health
/swarm diagnose / /swarm diagnosis — run health check on swarm state (diagnosis is a deprecated alias)/swarm config doctor — run config doctor checks/swarm config-doctor — deprecated alias for /swarm config doctor/swarm doctor — deprecated alias for /swarm config doctor/swarm doctor tools — run tool registration coherence check/swarm doctor-tools — deprecated alias for /swarm doctor tools/swarm preflight — run preflight automation checks/swarm lanes — list active, awaiting-merge, and conflicted worktree lanes/swarm sync-plan — ensure plan.json and plan.md are synced/swarm benchmark — show performance metrics [--cumulative] [--ci-gate] [--max-cost-usd <n>]/swarm review — run the independent review model against a selected Git diff/swarm costs — show per-agent and per-task token/cost telemetry [--json]/swarm learning — show learning metrics and violation trends/swarm guardrail explain — dry-run: show what guardrails would do (executes nothing)/swarm guardrail-explain — deprecated alias for /swarm guardrail explain/swarm guardrail-log — read the guardrail decision log/swarm coupling — measure plan coupling and rank modules driving conflicts/swarm dark-matter — detect hidden file couplings via co-change NPMI analysis/swarm simulate — dry-run hidden coupling analysis with configurable thresholds/swarm ci-simulate — create a temporary merge-result worktree and run CI pre-merge/swarm ci — advisory headless CI: read-only gate/evidence evaluation with machine exit codes (0 = all gates pass; Markdown + [SWARM_CI_JSON] report; bunx opencode-swarm ci outside OpenCode)/swarm qa-gates — view or modify QA gate profile for the current plan/swarm report — query the SQLite observability sink (filters: --task/--session/--trace/--run/--since, --json)/swarm dashboard — show the opt-in local mission-control dashboard URL and status (issue #2509; disabled unless dashboard.port > 0)/swarm acknowledge-spec-drift — acknowledge spec drift and suppress further warnings
Knowledge / memory / curation
/swarm knowledge — list knowledge entries/swarm knowledge migrate — migrate knowledge entries to the current format/swarm knowledge quarantine — move a knowledge entry to quarantine/swarm knowledge restore — restore a quarantined or archived knowledge entry/swarm knowledge unactionable — list unactionable knowledge entries pending hardening/swarm knowledge retry-hardening — reset retire candidates for re-hardening/swarm knowledge hive-quarantine — human-only exact-ID quarantine of hive-store entries with backup and rollback (issue #2033)/swarm memory — show Swarm memory commands/swarm memory status — show Swarm memory provider, JSONL, and migration status/swarm memory pending — show pending Swarm memory proposals/swarm memory recall-log — summarize Swarm memory recall usage/swarm memory value-log — show Swarm memory Q-value and reward updates/swarm memory compact — compact deleted/superseded/expired scratch memories/swarm memory stale — list stale and low-utility Swarm memories/swarm memory export — export current Swarm memory to JSONL files/swarm memory evaluate — run golden Swarm memory recall evaluation fixtures/swarm memory audit-verify — verify the memory audit-log hash chain (tamper detection)/swarm memory import — import legacy JSONL memory into SQLite/swarm memory migrate — run the one-time legacy JSONL to SQLite migration/swarm memory consolidation-log — summarize recent memory consolidation passes/swarm memory link — share memory across linked worktrees (requires memory.link.enabled)/swarm memory link status — show whether memory is cohort-linked (distinct from knowledge link)/swarm memory unlink — stop sharing memory; copies cohort family back to local/swarm curate — run knowledge curation and hive promotion review/swarm consolidate — run quota-bounded skill-improver consolidation/swarm promote — manually promote a lesson to hive knowledge/swarm link — tie this worktree to a shared swarm knowledge store/swarm link status — show whether this worktree shares knowledge via a link/swarm unlink — stop sharing swarm knowledge for this worktree/swarm write-retro — write a retrospective evidence bundle for a completed phase/swarm skill-opt — governed single-skill optimizer (plan|run|status|diff|approve|reject|rollback|history); disabled by default (skill_opt.enabled)/swarm skill-opt plan — propose an optimization round (dry-run; no mutation)/swarm skill-opt run — execute the optimization loop (requires skill_opt.enabled=true and --confirm)/swarm skill-opt status — show the current candidate lifecycle state/swarm skill-opt diff — show baseline-vs-candidate diff summary for a candidate/swarm skill-opt approve — activate a pending candidate (human-only; requires --expected-content-hash)/swarm skill-opt reject — record a rejection for a candidate (no active-skill mutation)/swarm skill-opt rollback — restore the pre-activation snapshot (appends a rolled_back event)/swarm skill-opt history — show the append-only lifecycle event log for a candidate/swarm harness-opt — governed HarnessOpt capstone (plan|run|status|stop|history); disabled by default (harness_opt.enabled)/swarm harness-opt plan — freeze the comparative task set and report loop status (dry-run)/swarm harness-opt run — execute one governed optimization round in a disposable worktree (human-only; requires harness_opt.enabled=true and --confirm; a test split consumes the held-out set once)/swarm harness-opt compare — separately executable comparative evaluation: baseline/ablation/simple-agent arms, manifest validation, independent-oracle verdict, retained pilot record (human-only; --confirm)/swarm harness-opt status — show loop status and the latest round lineage summary/swarm harness-opt stop — human-only operator stop with a recorded reason/swarm harness-opt history — list durable round lineage records (bounded)
Architect MODE workflows
/swarm brainstorm — enter architect MODE: BRAINSTORM (seven-phase planning)/swarm loop — enter architect MODE: LOOP (compound-engineering loop)/swarm council — enter architect MODE: COUNCIL (multi-model deliberation)/swarm clarify — clarify and refine an existing feature specification/swarm specify — generate or import a feature specification/swarm analyze — analyze spec.md vs plan.md for requirement coverage gaps/swarm sdd — manage OpenSpec-compatible SDD artifacts/swarm sdd status — show OpenSpec-compatible SDD status/swarm sdd validate — validate OpenSpec-compatible artifacts/swarm sdd project — materialize the effective spec into .swarm/spec.md/swarm epic — toggle Epic Mode (autonomous coupling-aware parallel activation)/swarm turbo — toggle Turbo Mode strategy [on|off|lean|standard|epic|status]/swarm full-auto — toggle Full-Auto Mode; accepts on [mode], off, or status/swarm guardrail reset — reset an action-local guardrail circuit after external repair/swarm post-mortem — run the post-mortem agent (project-end synthesis)
Read-only audits / research
/swarm deep-dive / /swarm deep dive — launch deep codebase audit (parallel explorers, dual reviewers, critic)/swarm deep-research / /swarm deep research — launch cited multi-source deep research pass/swarm codebase-review / /swarm codebase review — run codebase-review-swarm/swarm design-docs / /swarm design docs — generate or sync language-agnostic design docs
PR / issue workflows
/swarm issue — ingest a GitHub issue (intake → localization → resolution spec) [--plan] [--trace] [--no-repro]/swarm pr-review — launch deep PR review with multi-lane analysis/swarm pr-feedback — ingest and close known PR feedback (review comments, CI failures, conflicts)/swarm abort-pr-workflow — clear a stuck PR_REVIEW/PR_FEEDBACK mechanical gate and stop the auto-resume loop (human-only escape hatch)/swarm pr-feedback-loop — stop the autonomous PR babysitting settling loop for this session (stop <reason...>; cancels any armed publication via the #2584 route, records a terminal cancelled state with the operator reason, clears unsettled monitor events, and writes a cleanup receipt; human-only)/swarm approve-plan-critic — record a MANUAL plan-critic approval to unblock the ratchet-tighter critic_pre_plan execution gate when the critic already returned APPROVED but the snapshot was not recorded (human-only escape hatch)/swarm approve-write — issue one exact, session-bound, one-shot write approval for a candidate action and content hash (human-only)/swarm ci-monitor — drive an already-reviewed, approved PR to green and merged (monitor CI, fix, merge; max 5 fix cycles)/swarm pr subscribe / /swarm pr-subscribe — subscribe session to PR state-change notifications/swarm pr unsubscribe / /swarm pr-unsubscribe — unsubscribe session from PR notifications/swarm pr status / /swarm pr-status — show PR monitor subscription status
CRITICAL NAMING CONFLICTS
These swarm subcommands share exact names with CC built-in commands.
Invoking the bare form instead of /swarm <name> causes irreversible damage:
| Swarm Command |
CC Built-in |
Damage |
/swarm plan |
CC /plan |
Enters CC plan mode — blocks execution |
/swarm reset |
CC /reset |
Wipes entire conversation context |
/swarm checkpoint |
CC /checkpoint |
Reverts conversation history |
/swarm history |
CC /history |
Shows CC conversation history instead of swarm phase history |
All swarm commands: /swarm <subcommand>. Never the bare name.
COMMAND INVOCATION RULE
All commands in this list are invoked as /swarm <subcommand>.
Never invoke the bare subcommand as a standalone slash command.
/plan, /status, /reset, /checkpoint, /agents, /config, /export, /doctor
are Claude Code built-in commands with completely different behaviors.
The /swarm prefix is mandatory, not optional.
Examples:
/swarm — enable swarm mode only/swarm implement OAuth login without breaking existing session handling — enable swarm mode, then execute the task/swarm fix the failing auth refresh tests and verify the session flow — enable swarm mode, then execute the task/swarm close — this is a plugin subcommand; tell the user it will be handled by the plugin command system/swarm handoff — this is a plugin subcommand; tell the user it will be handled by the plugin command system
Behavior model
The canonical swarm behavior model (goal, workflow posture, quality/speed policy, default triage model, and the mandatory implementation closeout gate) lives at .opencode/skills/swarm/SKILL.md. This file holds only the Claude Code /swarm command wiring above; the cross-agent contract is canonical.
1---2name: swarm-23description: Enable a high-quality swarm-like Claude Code workflow for the current session, and optionally execute a task immediately using that mode. Uses parallel subagents for breadth, independent reviewer validation for precision, and critic challenge for final confidence. Use when the user wants swarm-like behavior, higher review rigor, or maximum quality without sacrificing Claude Code speed.4---56# /swarm78Enable swarm mode for the current session.9If arguments are provided, enable swarm mode first and then execute that task using the swarm-like implementation workflow.1011Argument handling:12- If no arguments are provided: only enable swarm mode.13- If the first word of `$ARGUMENTS` is a **known plugin subcommand** (see list below): do NOT treat it as a swarm task. Instead, tell the user to run it as a slash command directly (e.g., `/swarm close`, `/swarm handoff`). These are OpenCode plugin commands handled by the swarm plugin's command system, not tasks for the swarm workflow. Do NOT try to interpret or execute them yourself.14- Otherwise: enable swarm mode, then treat `$ARGUMENTS` as the task to execute immediately.1516### SWARM-NAMESPACED subcommands — DO NOT confuse with Claude Code built-in commands1718These are invoked as `/swarm <subcommand>`, NOT as bare `/subcommand`. The list below is generated from the `COMMAND_REGISTRY` (`src/commands/registry.ts`) and includes all registered non-deprecated base commands and subcommands:1920**Core / state**2122- `/swarm status` — show current swarm state23- `/swarm show-plan` — show current plan (optionally filter by phase number)24- `/swarm plan` — deprecated alias for `/swarm show-plan`25- `/swarm agents` — list registered agents26- `/swarm help` — show help for swarm commands (optionally `[command]`)27- `/swarm history` — show completed phases summary28- `/swarm config` — show current resolved configuration29- `/swarm export` — export plan and context as JSON30- `/swarm dataset consent` — HUMAN-ONLY: grant or revoke the training-content consent (two-step confirm token; quotas clamp to hard ceilings)31- `/swarm dataset withdraw` — HUMAN-ONLY: confirmed destructive withdrawal — purge vault content, write a tombstone, revoke exports32- `/swarm dataset export` — HUMAN-ONLY: governed deterministic dataset export (preview + confirm token; manifest with sha256 checksums)33- `/swarm evidence` — show evidence bundles `[taskId]`34- `/swarm evidence summary` — generate evidence summary with completion ratio and blockers35- `/swarm evidence-summary` — deprecated alias for `/swarm evidence summary`36- `/swarm handoff` — prepare state for clean model switch37- `/swarm archive` — archive old evidence bundles `[--dry-run]`38- `/swarm retrieve` — retrieve full output from a summary `<id>`39- `/swarm rollback` — restore swarm state or project files to a checkpoint40- `/swarm reset` — clear swarm state files `[--confirm]`41- `/swarm reset-session` — clear session state, preserve plan/evidence/knowledge42- `/swarm recover` — settle wedged coder settlements `[task_id] [--force]` (human-only)43- `/swarm checkpoint` — manage project checkpoints `[save|restore|delete|list] <label>`44- `/swarm finalize` — finalize the swarm project and archive evidence45- `/swarm close` — deprecated alias for `/swarm finalize`46- `/swarm auto-proceed` — toggle or set auto-proceed override `[on|off]`47- `/swarm concurrency` — manage runtime concurrency override `[set|status|reset]`4849**Harness evolution**5051- `/swarm blueprint validate` — validate a declarative harness blueprint or atomic blueprint patch52- `/swarm blueprint current` — show the ledger-derived current harness blueprint projection53- `/swarm blueprint history` — show bounded hash-verified harness version history54- `/swarm blueprint diff` — compare two stored harness blueprint versions55- `/swarm blueprint export` — export a canonical stored harness blueprint56- `/swarm harness candidate validate` — validate an inert harness candidate manifest57- `/swarm harness candidate show` — show bounded harness candidate metadata without raw patch content58- `/swarm harness candidate diff` — show candidate file and blueprint-change metadata without raw patch content5960**Diagnostics / health**6162- `/swarm diagnose` / `/swarm diagnosis` — run health check on swarm state (`diagnosis` is a deprecated alias)63- `/swarm config doctor` — run config doctor checks64- `/swarm config-doctor` — deprecated alias for `/swarm config doctor`65- `/swarm doctor` — deprecated alias for `/swarm config doctor`66- `/swarm doctor tools` — run tool registration coherence check67- `/swarm doctor-tools` — deprecated alias for `/swarm doctor tools`68- `/swarm preflight` — run preflight automation checks69- `/swarm lanes` — list active, awaiting-merge, and conflicted worktree lanes70- `/swarm sync-plan` — ensure plan.json and plan.md are synced71- `/swarm benchmark` — show performance metrics `[--cumulative] [--ci-gate] [--max-cost-usd <n>]`72- `/swarm review` — run the independent review model against a selected Git diff73- `/swarm costs` — show per-agent and per-task token/cost telemetry `[--json]`74- `/swarm learning` — show learning metrics and violation trends75- `/swarm guardrail explain` — dry-run: show what guardrails would do (executes nothing)76- `/swarm guardrail-explain` — deprecated alias for `/swarm guardrail explain`77- `/swarm guardrail-log` — read the guardrail decision log78- `/swarm coupling` — measure plan coupling and rank modules driving conflicts79- `/swarm dark-matter` — detect hidden file couplings via co-change NPMI analysis80- `/swarm simulate` — dry-run hidden coupling analysis with configurable thresholds81- `/swarm ci-simulate` — create a temporary merge-result worktree and run CI pre-merge82- `/swarm ci` — advisory headless CI: read-only gate/evidence evaluation with machine exit codes (0 = all gates pass; Markdown + [SWARM_CI_JSON] report; `bunx opencode-swarm ci` outside OpenCode)83- `/swarm qa-gates` — view or modify QA gate profile for the current plan84- `/swarm report` — query the SQLite observability sink (filters: --task/--session/--trace/--run/--since, --json)85- `/swarm dashboard` — show the opt-in local mission-control dashboard URL and status (issue #2509; disabled unless `dashboard.port` > 0)86- `/swarm acknowledge-spec-drift` — acknowledge spec drift and suppress further warnings8788**Knowledge / memory / curation**8990- `/swarm knowledge` — list knowledge entries91- `/swarm knowledge migrate` — migrate knowledge entries to the current format92- `/swarm knowledge quarantine` — move a knowledge entry to quarantine93- `/swarm knowledge restore` — restore a quarantined or archived knowledge entry94- `/swarm knowledge unactionable` — list unactionable knowledge entries pending hardening95- `/swarm knowledge retry-hardening` — reset retire candidates for re-hardening96- `/swarm knowledge hive-quarantine` — human-only exact-ID quarantine of hive-store entries with backup and rollback (issue #2033)97- `/swarm memory` — show Swarm memory commands98- `/swarm memory status` — show Swarm memory provider, JSONL, and migration status99- `/swarm memory pending` — show pending Swarm memory proposals100- `/swarm memory recall-log` — summarize Swarm memory recall usage101- `/swarm memory value-log` — show Swarm memory Q-value and reward updates102- `/swarm memory compact` — compact deleted/superseded/expired scratch memories103- `/swarm memory stale` — list stale and low-utility Swarm memories104- `/swarm memory export` — export current Swarm memory to JSONL files105- `/swarm memory evaluate` — run golden Swarm memory recall evaluation fixtures106- `/swarm memory audit-verify` — verify the memory audit-log hash chain (tamper detection)107- `/swarm memory import` — import legacy JSONL memory into SQLite108- `/swarm memory migrate` — run the one-time legacy JSONL to SQLite migration109- `/swarm memory consolidation-log` — summarize recent memory consolidation passes110- `/swarm memory link` — share memory across linked worktrees (requires `memory.link.enabled`)111- `/swarm memory link status` — show whether memory is cohort-linked (distinct from knowledge link)112- `/swarm memory unlink` — stop sharing memory; copies cohort family back to local113- `/swarm curate` — run knowledge curation and hive promotion review114- `/swarm consolidate` — run quota-bounded skill-improver consolidation115- `/swarm promote` — manually promote a lesson to hive knowledge116- `/swarm link` — tie this worktree to a shared swarm knowledge store117- `/swarm link status` — show whether this worktree shares knowledge via a link118- `/swarm unlink` — stop sharing swarm knowledge for this worktree119- `/swarm write-retro` — write a retrospective evidence bundle for a completed phase120- `/swarm skill-opt` — governed single-skill optimizer (plan|run|status|diff|approve|reject|rollback|history); disabled by default (`skill_opt.enabled`)121- `/swarm skill-opt plan` — propose an optimization round (dry-run; no mutation)122- `/swarm skill-opt run` — execute the optimization loop (requires `skill_opt.enabled=true` and `--confirm`)123- `/swarm skill-opt status` — show the current candidate lifecycle state124- `/swarm skill-opt diff` — show baseline-vs-candidate diff summary for a candidate125- `/swarm skill-opt approve` — activate a pending candidate (human-only; requires `--expected-content-hash`)126- `/swarm skill-opt reject` — record a rejection for a candidate (no active-skill mutation)127- `/swarm skill-opt rollback` — restore the pre-activation snapshot (appends a rolled_back event)128- `/swarm skill-opt history` — show the append-only lifecycle event log for a candidate129- `/swarm harness-opt` — governed HarnessOpt capstone (plan|run|status|stop|history); disabled by default (`harness_opt.enabled`)130- `/swarm harness-opt plan` — freeze the comparative task set and report loop status (dry-run)131- `/swarm harness-opt run` — execute one governed optimization round in a disposable worktree (human-only; requires `harness_opt.enabled=true` and `--confirm`; a test split consumes the held-out set once)132- `/swarm harness-opt compare` — separately executable comparative evaluation: baseline/ablation/simple-agent arms, manifest validation, independent-oracle verdict, retained pilot record (human-only; `--confirm`)133- `/swarm harness-opt status` — show loop status and the latest round lineage summary134- `/swarm harness-opt stop` — human-only operator stop with a recorded reason135- `/swarm harness-opt history` — list durable round lineage records (bounded)136137**Architect MODE workflows**138139- `/swarm brainstorm` — enter architect MODE: BRAINSTORM (seven-phase planning)140- `/swarm loop` — enter architect MODE: LOOP (compound-engineering loop)141- `/swarm council` — enter architect MODE: COUNCIL (multi-model deliberation)142- `/swarm clarify` — clarify and refine an existing feature specification143- `/swarm specify` — generate or import a feature specification144- `/swarm analyze` — analyze spec.md vs plan.md for requirement coverage gaps145- `/swarm sdd` — manage OpenSpec-compatible SDD artifacts146- `/swarm sdd status` — show OpenSpec-compatible SDD status147- `/swarm sdd validate` — validate OpenSpec-compatible artifacts148- `/swarm sdd project` — materialize the effective spec into `.swarm/spec.md`149- `/swarm epic` — toggle Epic Mode (autonomous coupling-aware parallel activation)150- `/swarm turbo` — toggle Turbo Mode strategy `[on|off|lean|standard|epic|status]`151- `/swarm full-auto` — toggle Full-Auto Mode; accepts `on [mode]`, `off`, or `status`152- `/swarm guardrail reset` — reset an action-local guardrail circuit after external repair153- `/swarm post-mortem` — run the post-mortem agent (project-end synthesis)154155**Read-only audits / research**156157- `/swarm deep-dive` / `/swarm deep dive` — launch deep codebase audit (parallel explorers, dual reviewers, critic)158- `/swarm deep-research` / `/swarm deep research` — launch cited multi-source deep research pass159- `/swarm codebase-review` / `/swarm codebase review` — run codebase-review-swarm160- `/swarm design-docs` / `/swarm design docs` — generate or sync language-agnostic design docs161162**PR / issue workflows**163164- `/swarm issue` — ingest a GitHub issue (intake → localization → resolution spec) [--plan] [--trace] [--no-repro]165- `/swarm pr-review` — launch deep PR review with multi-lane analysis166- `/swarm pr-feedback` — ingest and close known PR feedback (review comments, CI failures, conflicts)167- `/swarm abort-pr-workflow` — clear a stuck PR_REVIEW/PR_FEEDBACK mechanical gate and stop the auto-resume loop (human-only escape hatch)168- `/swarm pr-feedback-loop` — stop the autonomous PR babysitting settling loop for this session (`stop <reason...>`; cancels any armed publication via the #2584 route, records a terminal cancelled state with the operator reason, clears unsettled monitor events, and writes a cleanup receipt; human-only)169- `/swarm approve-plan-critic` — record a MANUAL plan-critic approval to unblock the ratchet-tighter critic_pre_plan execution gate when the critic already returned APPROVED but the snapshot was not recorded (human-only escape hatch)170- `/swarm approve-write` — issue one exact, session-bound, one-shot write approval for a candidate action and content hash (human-only)171- `/swarm ci-monitor` — drive an already-reviewed, approved PR to green and merged (monitor CI, fix, merge; max 5 fix cycles)172- `/swarm pr subscribe` / `/swarm pr-subscribe` — subscribe session to PR state-change notifications173- `/swarm pr unsubscribe` / `/swarm pr-unsubscribe` — unsubscribe session from PR notifications174- `/swarm pr status` / `/swarm pr-status` — show PR monitor subscription status175176### CRITICAL NAMING CONFLICTS177178These swarm subcommands share exact names with CC built-in commands.179Invoking the bare form instead of `/swarm <name>` causes irreversible damage:180181| Swarm Command | CC Built-in | Damage |182|---|---|---|183| `/swarm plan` | CC `/plan` | Enters CC plan mode — blocks execution |184| `/swarm reset` | CC `/reset` | Wipes entire conversation context |185| `/swarm checkpoint` | CC `/checkpoint` | Reverts conversation history |186| `/swarm history` | CC `/history` | Shows CC conversation history instead of swarm phase history |187188All swarm commands: `/swarm <subcommand>`. Never the bare name.189190### COMMAND INVOCATION RULE191192All commands in this list are invoked as `/swarm <subcommand>`.193Never invoke the bare subcommand as a standalone slash command.194`/plan`, `/status`, `/reset`, `/checkpoint`, `/agents`, `/config`, `/export`, `/doctor`195are Claude Code built-in commands with completely different behaviors.196The `/swarm` prefix is mandatory, not optional.197198Examples:199- `/swarm` — enable swarm mode only200- `/swarm implement OAuth login without breaking existing session handling` — enable swarm mode, then execute the task201- `/swarm fix the failing auth refresh tests and verify the session flow` — enable swarm mode, then execute the task202- `/swarm close` — this is a plugin subcommand; tell the user it will be handled by the plugin command system203- `/swarm handoff` — this is a plugin subcommand; tell the user it will be handled by the plugin command system204205## Behavior model206207The canonical swarm behavior model (goal, workflow posture, quality/speed policy, default triage model, and the **mandatory implementation closeout gate**) lives at `.opencode/skills/swarm/SKILL.md`. This file holds only the Claude Code `/swarm` command wiring above; the cross-agent contract is canonical.
zaxbysauce